WO2023189081A1 - 画像処理装置、および画像処理方法、並びにプログラム - Google Patents
画像処理装置、および画像処理方法、並びにプログラム Download PDFInfo
- Publication number
- WO2023189081A1 WO2023189081A1 PCT/JP2023/006809 JP2023006809W WO2023189081A1 WO 2023189081 A1 WO2023189081 A1 WO 2023189081A1 JP 2023006809 W JP2023006809 W JP 2023006809W WO 2023189081 A1 WO2023189081 A1 WO 2023189081A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- imaging ratio
- camera
- imaging
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B15/00—Special procedures for taking photographs; Apparatus therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Definitions
- the present disclosure relates to an image processing device, an image processing method, and a program. More specifically, the present invention relates to an image processing device, an image processing method, and a program that can more reliably perform video generation processing of a subject of interest by image cutting out while suppressing deterioration in image quality.
- processing may be required to generate video data in which an image region of a specific subject of interest, for example, a person to be followed, is extracted from a video shot using a surveillance camera.
- processing may be required to generate tracking video data that cuts out an image area of a specific subject of interest, for example, a specific player.
- a fixed camera is used to capture an image with a large angle of view that includes the subject of interest, and an image area of the subject of interest is extracted from this captured video and generated. Processing is possible.
- Tracked video data can be generated.
- a fixed camera captures a video that covers a wide area, such as the entire or half of the soccer court, and each frame of this video is used to create an image of the player of interest. By cutting out the area, it is possible to generate an image similar to that of only the player of interest.
- Patent Document 1 International Publication No. WO 2016/167016
- the cropped image including the subject of interest In order to not significantly degrade the image quality of the cropped image of the subject of interest, it is necessary to make the cropped image including the subject of interest an image size of a predetermined number of pixels or more.
- a method using a PTZ camera is effective in realizing generation of a cutout image that suppresses deterioration in image quality.
- a PTZ camera is capable of panning, tilting, and zooming processing, and it is possible to direct the photographing direction of the camera toward the subject of interest. Even if the subject of interest moves, it is possible to maintain the subject of interest within a photographing area of a predetermined image size for a longer period of time while photographing.
- pan processing that rotates the shooting direction of a PTZ camera in the horizontal direction and tilt processing that rotates the shooting direction of the camera in the vertical direction, require the operation of a mechanical drive mechanism to rotate the camera itself. There is a problem in that a predetermined drive time is required.
- the present disclosure has been made, for example, in view of the above-mentioned problems, and provides an image processing device and an image processing device that can more reliably perform generation processing of subject tracking video data that involves image extraction while suppressing image quality deterioration.
- the purpose is to provide processing methods and programs.
- the object of the present invention is to provide an image processing device, an image processing method, and a program.
- a first aspect of the present disclosure includes: a cutout area calculation unit that calculates an image area including the subject of interest from an image taken by the camera as an image cutout area; a cropping execution unit that generates a cropped image by cropping the image of the image cropping area calculated by the cropping area calculation unit; As an index value for executing the cutout image generation process including the subject of interest, the cutout image generation is a size ratio between the size of the cutout image and the size of an imaging area corresponding to the entire image area of the image taken by the camera.
- an imaging ratio calculation unit that calculates an imaging ratio for a camera control parameter calculation unit that calculates a camera control parameter for causing the camera to take an image according to an imaging area size determined based on the calculated imaging ratio for generating a cutout image;
- the image processing device causes the camera to perform image capturing using the camera control parameters calculated by the camera control parameter calculation unit.
- a second aspect of the present disclosure includes: An image processing method executed in an image processing device, a cropping area calculating step in which the cropping area calculating unit calculates an image area including the subject of interest from an image taken by the camera as an image cropping area; a cropping execution step in which the cropping execution unit generates a cropped image by cropping the image of the image cropping area calculated in the cropping area calculating step;
- the imaging ratio calculation unit uses the size of the cutout image and the size of the imaging area corresponding to the entire image area of the captured image of the camera as an index value for executing the cutout image generation process including the subject of interest.
- the present invention provides an image processing method that causes the camera to perform image capturing using camera control parameters calculated by the camera control parameter calculation unit.
- a third aspect of the present disclosure includes: A program that causes an image processing device to perform image processing, a cropping area calculation step of causing a cropping area calculating unit to calculate an image area including the subject of interest from an image taken by the camera as an image cropping area; a cropping execution step in which a cropping execution unit generates a cropped image by cropping the image of the image cropping area calculated in the cropping area calculating step; The size of the size of the cut-out image and the size of the image-capturing area corresponding to the entire image area of the captured image of the camera is used as an index value for causing the imaging ratio calculation unit to execute a cut-out image generation process that includes the subject of interest.
- the present invention is a program that causes the camera to perform image capturing using camera control parameters calculated by the camera control parameter calculation unit.
- the program of the present disclosure is, for example, a program that can be provided by a storage medium or a communication medium that is provided in a computer-readable format to an image processing device or computer system that can execute various program codes.
- a program can be provided by a storage medium or a communication medium that is provided in a computer-readable format to an image processing device or computer system that can execute various program codes.
- processing according to the program can be realized on an image processing device or computer system.
- a system is a logical collective configuration of a plurality of devices, and the devices of each configuration are not limited to being in the same housing.
- the optimum imaging ratio (imaging ratio for generating a cropped image), which is an index value for more reliably executing the process of generating a cropped image including the subject of interest from an image taken by a PTZ camera, is set.
- a device and method for calculating are realized. Specifically, for example, in a configuration in which an image cropping area including the subject of interest is calculated from an image taken by a PTZ camera, and an image of the calculated area is cropped to generate a cropped image, the process of generating a cropped image including the subject of interest is further performed.
- an optimum imaging ratio (imaging ratio for generating a cutout image), which is the size ratio of the camera's imaging area to the cutout image. Furthermore, a zoom parameter for photographing an image according to the camera imaging area size calculated from the optimum imaging ratio is calculated, and the PTZ camera is caused to perform image photographing using the calculated parameters.
- a device and a method for calculating an optimal imaging ratio (imaging ratio for generating a cropped image), which is an index value for more reliably executing the process of generating a cropped image including the subject of interest from an image taken by a PTZ camera, are realized. Ru. Note that the effects described in this specification are merely examples and are not limiting, and additional effects may also be provided.
- FIG. 3 is a diagram illustrating an overview of a tracking image generation process for a subject of interest that involves image cutting using a PTZ camera.
- 1 is a diagram illustrating a configuration example of an image processing system including an external device that generates a cutout image consisting of an image region of a subject of interest.
- FIG. 6 is a diagram illustrating an example of setting a cutout region including the whole body region of the subject of interest and an example of setting a cutout region including only the upper body region of the subject of interest.
- FIG. 3 is a diagram illustrating a problem in image cutout processing.
- FIG. 3 is a diagram illustrating a problem in image cutout processing.
- FIG. 2 is a diagram illustrating a specific example of processing executed by the image processing device of the present disclosure.
- FIG. 3 is a diagram illustrating a specific example of imaging ratio changing processing executed by the image processing device of the present disclosure.
- FIG. 3 is a diagram illustrating a specific example of imaging ratio changing processing executed by the image processing device of the present disclosure.
- FIG. 3 is a diagram illustrating an example in which the imaging ratio is changed depending on the speed of the object of interest.
- FIG. 3 is a diagram illustrating rMIN (minimum allowable imaging ratio).
- FIG. 3 is a diagram illustrating an example of rMAX (permissible maximum imaging ratio).
- FIG. 7 is a diagram illustrating an example in which the imaging ratio is changed according to the acceleration of the object of interest.
- FIG. 3 is a diagram illustrating a specific example of imaging ratio changing processing executed by the image processing device of the present disclosure.
- FIG. 3 is a diagram illustrating a specific example of imaging ratio changing processing executed by the image processing device of the present disclosure.
- FIG. 3 is a diagram illustrating an example in which the imaging ratio is changed depending on the
- FIG. 6 is a diagram illustrating an example in which the imaging ratio is changed according to the speed and acceleration of the object of interest.
- FIG. 6 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed of the object of interest.
- FIG. 7 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the acceleration of the object of interest.
- FIG. 6 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed and acceleration of the object of interest.
- FIG. 6 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed and acceleration of the object of interest.
- FIG. 6 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed and acceleration of the object of interest.
- FIG. 7 is a diagram illustrating a specific processing example of the embodiment in which the imaging ratio is changed according to the communication delay time between the camera and the external device.
- FIG. 7 is a diagram showing a flowchart illustrating a processing sequence of an embodiment in which an imaging ratio is changed according to a communication delay time between a camera and an external device.
- FIG. 6 is a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device.
- FIG. 6 is a flowchart illustrating a processing sequence of an embodiment in which the imaging ratio is changed according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device.
- FIG. 2 is a diagram illustrating an example of processing performed by a camera, which is an example of an image processing device of the present disclosure.
- FIG. 2 is a diagram illustrating a configuration example of a camera and an external device that are an example of an image processing device of the present disclosure, and processing to be executed.
- FIG. 2 is a diagram illustrating a configuration example of a camera and an external device that are an example of an image processing device of the present disclosure, and processing to be executed.
- FIG. 1 is a diagram illustrating an example configuration of a camera that is an example of an image processing device of the present disclosure.
- FIG. 2 is a diagram illustrating a configuration example of a camera and an external device that are an example of an image processing device of the present disclosure.
- FIG. 2 is a diagram illustrating a configuration example of a camera and an external device that are an example of an image processing device of the present disclosure.
- 1 is a diagram illustrating an example of a hardware configuration of an image processing device according to an embodiment of the present disclosure
- Example 1 Example of changing the imaging ratio according to at least one of the speed and acceleration of the object of interest 3-1.
- Example 1-1 Example of changing the imaging ratio according to the speed of the object of interest 3-2.
- Example 1-2 Example of changing the imaging ratio according to the acceleration of the object of interest 3-3.
- Example 1-3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest 4.
- Example 2 Example of changing the imaging ratio according to the communication delay time between the camera and the external device 6.
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device 7.
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device 7.
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device 7.
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device 7.
- the configuration example of the image processing device of the present disclosure 8.
- Detailed configuration of the image processing device of the present disclosure 9.
- Example 10 Summary of the structure of this disclosure
- tracking video data when generating tracking video data by extracting the image area of a specific tracking target from footage shot using a surveillance camera, or tracking by cutting out the image area of a specific player from footage shot of a sport such as soccer.
- video data it is possible to perform a process of cutting out and generating an image area including a subject of interest from an image captured by a fixed camera that captures a wide area.
- DNNs deep neural networks
- rule-based models have been used to identify specific information from captured images. It is now possible to detect and follow people with high precision.
- PTZ camera pan, tilt, and zoom control
- the moving speed of the subject of interest which is the tracking target
- the time it takes to drive the camera to a direction where the subject of interest can be photographed becomes long, there is a possibility that the subject of interest may be lost.
- FIG. 1 shows a state in which a PTZ camera 10 is used to capture an image of a subject of interest 21, which is a person to be followed.
- a PTZ camera 10 is used to capture an image of a subject of interest 21, which is a person to be followed.
- an "image” will be explained as including a video that is a moving image and an image frame that constitutes the video.
- FIG. 2 shows an image processing system that includes an external device 30 that receives images taken by the PTZ camera 10 and performs image analysis processing to extract an image region of the subject of interest and generates a cutout image consisting of the image region of the subject of interest. It is a figure showing an example of composition.
- Step S01 First, in step S01, the PTZ camera 10 captures an image.
- the image is a moving image (video).
- the photographed image 20 shown in the figure is an example of one image frame of a moving image (video) photographed by the PTZ camera 10.
- the photographed image 20 includes, for example, a photographed object 21 that is a tracking target.
- step S02 the PTZ camera 10 transmits the captured image to the external device 30, which is an execution device for image analysis processing and image cutting processing.
- Step S03 The external device 30 detects the object of interest 21 from the photographed image 20 received from the PTZ camera 10, and performs an image cutting process of cutting out an image area of the detected object of interest 21.
- the facial image, physical characteristics, etc. of the subject of interest 21 are analyzed in advance, for example, in the external device 30, and the acquired characteristic information is registered in the storage unit.
- the external device 30 performs image matching processing using the registered feature information to detect the object of interest 21 .
- the subject of interest 21 is detected from the captured image 20 by performing AI analysis using at least one of a machine learning model such as the deep neural network described above or a rule-based model.
- a machine learning model such as the deep neural network described above or a rule-based model.
- the external device 30 further executes image cutting processing to cut out the image area of the detected object of interest 21. As shown in the figure, a process is performed in which a part of the image area is cut out as a cutout area 23 from the imaging area 22 that is the entire area of the captured image 20 . For example, an image area including the whole body area of the subject of interest 21 is set as the cutting area 23, and image cutting is executed.
- the setting of the cutout area of the image of the subject of interest 21 is defined in advance. That is, the cropping area setting algorithm is defined in advance, and the external device 30 sets the cropping area 23 including the subject of interest 21 from the image according to this algorithm and executes the image cropping process.
- cutting area setting algorithms There are various types of cutting area setting algorithms. Specifically, for example, a cropping area setting algorithm that includes the whole body area of the subject of interest 21, a cropping area setting algorithm that includes only the upper body area of the subject of interest 21, a cropping area setting algorithm that includes only the face area of the subject of interest 21, etc. It is. Note that the types of cutout area setting algorithms used by the external device 30 are not limited to these examples.
- FIG. 3 shows an example of setting a cutout region including the whole body region of the subject of interest 21 and an example of setting a cutout region including only the upper body region of the subject of interest 21.
- “(1) Whole body shot” shown in FIG. 3 shows an example of a cutting region setting algorithm that includes the whole body region of the subject of interest 21.
- the position of the whole body area of the subject of interest 21 is set approximately at the center of the cutout area 23, and a predetermined length is set on the top, bottom, left and right of the subject of interest 21, for example, about 10% of the height of the subject of interest above and below the subject of interest 21.
- Margin area A rectangular area in which margin areas of about 50% of the width of the subject of interest are set on the left and right sides of the subject of interest 21 is defined as a cutout area 23.
- FIG. 3 shows an example of a cutout region setting algorithm that includes the upper body region of the subject of interest 21.
- the position of the upper body region of the subject of interest 21 is set approximately at the center of the cropping area 23, and a margin area of approximately 10% of the height of the subject of interest is placed above the subject of interest 21, and a margin area corresponding to the width of the subject of interest is placed on the left and right sides of the subject of interest 21.
- a rectangular area with a margin area of about 30% is set as the cutout area 23.
- the image cropping area setting algorithm for the subject of interest 21 is predefined, and the external device 30 sets the cropping area 23 including the subject of interest 21 from the image according to the prescribed algorithm, and performs image cropping processing. Execute.
- step S03 the external device 30 sets a cropping area 23 in each image frame of the photographed image 20 photographed by the PTZ camera 10, and generates a cropped image corresponding to each image frame.
- the external device 30 sets a cropping area 23 in each image frame of the photographed image 20 photographed by the PTZ camera 10, and generates a cropped image corresponding to each image frame.
- the video composed of cutout images generated by the external device 30 can be distributed from the external device 30 to user terminals such as televisions and smartphones, and can also be distributed within the external device 30.
- the configuration may be such that the information is stored in the storage unit.
- Step S04 The external device 30 further performs image analysis when executing the image cutting process in step S03.
- the external device 30 estimates the moving direction and moving speed of the object of interest 21 detected from the captured image 20, and transmits a camera drive instruction to the PTZ camera 10 based on these estimation results in step S04.
- the orientation (pan, tilt settings) and zoom setting information of the PTZ camera 10 is transmitted so that the PTZ camera 10 can track and photograph the object of interest 21.
- Step S05 When the PTZ camera 10 receives camera drive instruction data from the external device 30, in step S05, the camera direction (pan, tilt) and zoom settings are changed or updated based on the received camera drive instruction data.
- the PTZ camera 10 can continuously capture images of the subject of interest 21, and the external device 30 can also It becomes possible to detect the subject of interest 21 and cut out the image area of the subject of interest 21.
- the video composed of the cutout images is a video in which the subject of interest 21 is photographed larger than the subject of interest 21 in the captured image before the cutout.
- the drive mechanism must be operated, a predetermined drive time is required, and if the moving speed of the subject of interest 21 is fast, there is a possibility that the subject of interest may be lost, and as a result, the cropping process that includes the subject of interest 21 may not be possible.
- the problem arises that it disappears. A specific example of this problem will be described with reference to FIG.
- FIG. 4 shows the PTZ camera 10 described with reference to FIG. 2 and the external device 30.
- the PTZ camera 10 photographs images 20a to 20c including the subject of interest 21 at times (t0) to (t2) and transmits them to the external device 30.
- the external device 30 detects the subject of interest 21 from the captured image 20 received from the PTZ camera 10, and sets a cutout area 23 including the whole body area of the subject of interest 21 from the imaging area 22 corresponding to the entire area of the captured image 20. Perform the cutting process.
- the object of interest 21 in the captured image 20a at time (t0) is stationary.
- the external device 30 can perform a process of setting and clipping a clipping region 23a including the whole body region of the subject of interest 21 from the imaging region 22a corresponding to the entire region of the photographed image 20a at time (t0).
- the external device 30 confirms that the subject of interest 21 is stationary through image analysis processing of the captured image 20a at time (t0), and does not send a drive instruction to the PTZ camera 10.
- the object of interest 21 in the photographed image 20b at the next time (t1) starts running toward the right in the figure.
- the external device 30 performs a process of setting and cutting out a cutting area 23b including the whole body area of the subject of interest 21 from the imaging area 22b corresponding to the entire area of the captured image 20b at time (t1).
- the external device 30 confirms that the subject of interest 21 is running toward the right in the figure, and informs the PTZ camera 10 of the current photographing direction.
- a camera drive (PTZ drive) instruction is sent to move the camera to the right. That is, the process (process b) shown in FIG. 4 is executed.
- the PTZ camera 10 When the PTZ camera 10 receives a camera drive (PTZ drive) instruction from the external device 30, it performs a panning operation to move the current shooting direction to the right.
- the photographed image as a result of this operation is the photographed image 20c at time (t2).
- a part of the object of interest 21 in the photographed image 20c is near the end of the photographing range of the PTZ camera 10 or outside the photographing range. This is because the panning operation for moving the photographing direction to the right is performed by a mechanical drive such as a gear mechanism of the PTZ camera 10, and therefore takes time.
- the PTZ camera 10 transmits to the external device 30 the photographed image 20c in which a portion of the subject of interest 21 has protruded from the photographing range at time (t2).
- the external device 30 sets a cropping area 23c that includes the whole body area of the subject of interest 21 from the imaging area 22c that corresponds to the entire area of the captured image 20c at time (t2). Even if an attempt is made to perform the cutting process, it becomes impossible to set the cutting area 23c that includes the whole body area of the subject of interest 21.
- the algorithm for setting a cutout region that includes, for example, the whole body region of the subject of interest 21 is defined in advance. That is, an algorithm is prescribed for cutting out an area with prescribed margins set in each of the upper, lower, left, and right directions of the subject of interest 21.
- FIG. 5 shows the same PTZ camera 10 as in FIG. 4 and an external device 30.
- the PTZ camera 10 and the external device 30 shown in FIG. 5 are located apart from each other and are connected via a communication network such as the Internet, so communication delays may occur.
- the PTZ camera 10 captures a captured image 20p including the subject of interest 21 and transmits it to the external device 30.
- the external device 30 receives this photographed image 20p at time (t1+dt1).
- the external device 30 detects the subject of interest 21 from the captured image 20p received from the PTZ camera 10 at time (t1+dt1), and extracts a cutout area including the whole body area of the subject of interest 21 from the imaging area 22 corresponding to the entire area of the captured image 20p. 23 and performs the cutting process.
- the external device 30 confirms that the subject of interest 21 is running toward the right in the figure through image analysis processing of the photographed image 20p, and moves the current photographing direction to the right with respect to the PTZ camera 10.
- the transmission timing of the camera drive (PTZ drive) instruction from the external device 30 to the PTZ camera 10 is time (t1+dt2). Time td2 has already elapsed since the photographing timing (t1) of the photographed image.
- the PTZ camera 10 performs a panning operation to move the current shooting direction to the right according to a camera drive (PTZ drive) instruction received from the external device 30.
- the timing at which this panning operation is completed is time (t1+dt4), and the photographed image after the completion of this panning operation is the photographed image 20q.
- a part of the body of the object of interest 21 in the photographed image 20q has protruded from the photographing range of the PTZ camera 10. In this way, when the communication delay with the external device 30 is added to the delay due to the mechanical drive of the PTZ camera 10, the possibility of occurrence of an error in tracking the object of interest or an error in cutting out an image further increases.
- the process of the present disclosure solves such problems, and more reliably performs the process of cutting out and recording or distributing a part of the image area including the subject of interest from the image taken by the PTZ camera, while reducing the image quality. This makes it possible to carry out operations in a controlled manner.
- the configuration and processing details of the image processing device of the present disclosure will be described below.
- FIG. 6 is a diagram illustrating a specific example of processing executed by the image processing device of the present disclosure.
- the image processing device of the present disclosure changes the imaging ratio according to at least one of the moving speed or acceleration of the target object to be tracked, processing delay time including communication delay, etc. Execute the control to be executed.
- FIG. 6 shows the following two image capturing examples by the PTZ camera 10.
- the imaging area in the image shooting example after the imaging ratio change is large. Specifically, (b) the size of the imaging area 22b in the image capturing example after the imaging ratio is changed is larger than the size of the imaging area 22a in the image capturing example (a) before the imaging ratio is changed.
- the image processing device of the present disclosure changes the size ratio (imaging ratio) between the size of the imaging area 22 and the cutout area based on whether or not the subject of interest 21 to be tracked is moving at a certain speed. do. If it is detected that the object of interest 21 is moving at a speed higher than a predetermined speed, the size ratio between the size of the imaging area 22 and the size of the cutout area 23 is changed to Processing is performed to change the "imaging ratio" to a higher value than when no movement is detected. That is, the zoom of the PTZ camera 10 is adjusted to widen the shooting range, that is, to widen the angle of view.
- FIG. 7 shows (a) an example of a captured image and (b) an explanatory diagram of the imaging ratio.
- a photographed image 20 including a subject of interest 21 is shown.
- the imaging area 22 corresponds to the entire area of the captured image 20.
- a cutout area 23 is set within this imaging area 22.
- the cutout area 23 is set as, for example, an area including the entire body of the subject of interest 21.
- Imaging ratio explanatory diagram only shows the rectangular frames of the imaging area 22 and the cutout area 23 shown in the example (a) of the captured image.
- FIG. 8 shows a calculation example and a comparative example of the imaging ratio of each of the captured images in FIGS. 6(a) and 6(b) described above.
- the image processing device of the present disclosure performs control to increase the imaging ratio, for example, when the subject of interest is moving at a certain speed. Specifically, processing is performed to widen the angle of view by adjusting the zoom of the PTZ camera. This processing expands the photographable range of the PTZ camera 10, making it possible to continue tracking photographing without losing sight of the subject of interest 21.
- FIG. 9 shows an example of changing the imaging ratio different from that shown in FIG. Similar to FIG. 8, FIG. 9 shows the following two image capturing examples by the PTZ camera 10.
- the same subject of interest 21 is photographed in both (a) and (b), but in the example shown in FIG. 9, the subject of interest 21 is stationary.
- the image processing device of the present disclosure performs control to reduce the imaging ratio, for example, when the subject of interest is stationary or when the subject of interest remains within a predetermined range for a predetermined time or longer. .
- processing is performed to narrow the angle of view by adjusting the zoom of the PTZ camera.
- This processing narrows the photographable range of the PTZ camera 10, and it becomes possible to increase the proportion of the cutout area 23 in the imaging area 22. That is, the proportion of the cutout area 23 that includes the subject of interest 21 increases, and as a result, the number of pixels in the image area of the cutout image 23 increases, so that the image quality of the cutout image 23 can be improved.
- Example 1 Example of changing the imaging ratio according to at least one of the speed and acceleration of the object of interest] Next, a specific example of processing executed by the image processing apparatus of the present disclosure will be described.
- Example 1 Example of changing the imaging ratio according to at least one of the speed or acceleration of the object of interest (Example 2)
- Example 1 an example will be described in which the imaging ratio is changed depending on at least one of the speed and acceleration of the object of interest.
- Example 1 will be further subdivided into the following Examples.
- Example 1-1 Example of changing the imaging ratio according to the speed of the object of interest (Example 1-2)
- the graph shown in FIG. 10 is a graph in which the velocity of the subject of interest (v) is set on the horizontal axis and the imaging ratio is set on the vertical axis.
- the speed of the object of interest (v) on the horizontal axis is, for example, the speed in the captured image of the PTZ camera 10, and specifically, for example, the number of moving pixels of the object of interest per unit time, for example, the moving pixels per second. number (pixels/s).
- the graph shown in FIG. 10 is a graph showing an example of control for changing the imaging ratio according to the speed (v) of the object of interest, which is executed by the image processing device of the present disclosure.
- the image processing device of the present disclosure changes the imaging ratio as shown below according to the speed (v) of the subject of interest as shown in the graph.
- the imaging ratio rMIN (minimum allowable imaging ratio)
- the imaging ratio is changed from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio) according to the speed (v) of the object of interest
- the imaging ratio rMAX (maximum allowable imaging ratio)
- the imaging ratio changes linearly from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio).
- the imaging ratio is set to change in proportion to the change in the speed (v) of the subject of interest, but this is just one example. It may be set to increase or to change so that the imaging ratio increases exponentially as the speed (v) of the subject of interest increases.
- the imaging ratio is rMIN (minimum allowable imaging
- the difference (ratio) between the size of the imaging area 22 and the size of the cutout area 23 is set to be smaller than the imaging ratio when the speed (v) of the subject of interest is greater than v1.
- the imaging ratio is set to rMAX (maximum allowable imaging ratio), and the cutting area 23
- the difference (ratio) between the size of the imaging area 22 and the size of is set to be larger than the imaging ratio when the speed (v) of the subject of interest is smaller than v2.
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- rMIN minimum allowable imaging ratio
- rMIN is a value indicating the lower limit ratio to which the imaging area can be set to be smaller with respect to the cutout area 23.
- This rMIN (minimum allowable imaging ratio) is determined in advance before the start of image capturing, and there are various examples of determination processing for this value, as shown in FIG. 11, for example.
- FIG. 11A is a diagram illustrating an example of determining rMIN (minimum allowable imaging ratio) according to the shot size of the subject of interest, that is, the setting manner of the cutout area for the subject of interest. Note that the setting of the cropping area for the subject of interest is also determined in advance before the start of image capturing.
- rMIN minimum allowable imaging ratio
- the setting of the cropping area for the subject of interest is a full-body shot that includes the whole body of the subject of interest, as shown in (a1) in FIG.
- the value (ratio) of rMIN (minimum allowable imaging ratio) is set relatively small (than in the case of setting a shot that includes only a part of the subject of interest).
- rMIN minimum allowable imaging ratio
- shot size that is, the size on the photographed image of the body area of the subject of interest that should be included in the cropping area (ratio of the body area that should be included in the cropping area to the imaging area).
- rMIN minimum allowable imaging ratio
- (b1) in FIG. 11 is a scene in which the subject of interest moves rapidly (a lot of movement, a lot of movement).
- rMIN minimum allowable imaging ratio
- Hb1/hb1 the value (ratio) of rMIN (minimum allowable imaging ratio) is set relatively large (than in the case of a scene in which there is less movement of the subject of interest).
- rMIN minimum allowable imaging ratio
- rMIN minimum allowable imaging ratio
- rMAX permissible maximum imaging ratio
- rMAX maximum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- the number of pixels (resolution) of the imaging area 22 corresponding to the entire captured image is 3840 x 2160, and the minimum number of pixels to be included in the cutout area 23, that is, the minimum allowable pixel.
- rMAX maximum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- the external device 30 sets the imaging ratio calculated from the graph shown in FIG. 10 as the optimal imaging ratio (imaging ratio for cropped image generation), and captures an image according to the imaging area size determined based on the calculated optimal imaging ratio.
- the PTZ camera 10 is made to execute.
- the "optimal imaging ratio (imaging ratio for cropped image generation)" is an index value for executing the cropped image generation process that includes the subject of interest more reliably than before, and also sets the image quality of the cropped image that includes the subject of interest to a predetermined value. This is an index value for achieving the above image quality.
- the imaging ratio corresponding to the current speed (vt) of the subject of interest 21 is calculated as the optimal imaging ratio.
- the optimal imaging ratio corresponding to the current speed (vt) of the object of interest 21 is the optimal imaging ratio (r1) shown in FIG.
- the ratio is set to rMIN (minimum allowable imaging ratio), and the difference (ratio) of the size of the imaging area 22 to the size of the cutout area 23 is set to be smaller than when the moving speed of the subject of interest is greater than a predetermined value.
- rMIN minimum allowable imaging ratio
- the difference (ratio) of the size of the imaging area 22 to the size of the cutout area 23 is set to be smaller than when the moving speed of the subject of interest is greater than a predetermined value.
- the imaging ratio is set to rMAX (maximum allowable imaging ratio), and the cutting area 23
- the difference (ratio) between the size of the imaging area 22 and the size of is set to be larger than when the moving speed of the object of interest is smaller than a predetermined value.
- the graph shown in FIG. 13 is a graph in which the acceleration of the subject of interest ( ⁇ ) is set on the horizontal axis and the imaging ratio is set on the vertical axis.
- the acceleration of the subject of interest ( ⁇ ) on the horizontal axis is, for example, the acceleration within the image captured by the PTZ camera 10.
- the graph shown in FIG. 13 is a graph showing an example of control for changing the imaging ratio according to the acceleration ( ⁇ ) of the subject of interest, which is executed by the image processing device of the present disclosure.
- the image processing device of the present disclosure changes the imaging ratio as shown below according to the acceleration ( ⁇ ) of the subject of interest as shown in the graph.
- the imaging ratio rMIN (minimum allowable imaging ratio)
- the imaging ratio is changed from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio) according to the acceleration ( ⁇ ) of the subject of interest
- the imaging ratio rMAX (maximum allowable imaging ratio)
- the imaging ratio changes linearly from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio).
- the imaging ratio is set to change in proportion to the change in the acceleration ( ⁇ ) of the subject of interest, but this is just an example. It may be set to increase or to change so that the imaging ratio increases exponentially as the acceleration ( ⁇ ) of the subject of interest increases.
- the external device 30 sets the imaging ratio calculated from the graph shown in FIG.
- the PTZ camera 10 is caused to take an image according to the area size.
- the imaging ratio corresponding to the current acceleration ( ⁇ t) of the subject of interest 21 is calculated as the optimal imaging ratio.
- the optimal imaging ratio corresponding to the current acceleration ( ⁇ t) of the object of interest 21 is the optimal imaging ratio (r2) shown in FIG. 13.
- the image processing device of the present embodiment 1-2 is configured to:
- the imaging ratio is set to rMIN (minimum allowable imaging ratio)
- the difference (ratio) of the size of the imaging area 22 to the size of the cutting area 23 is set to be smaller than when the moving acceleration of the subject of interest is larger than a predetermined value. be done.
- the number of pixels in the cutout area 23 can be set to a larger number, and the deterioration in image quality of the cutout image can be reduced.
- (c) acceleration of the subject of interest ( ⁇ ) ⁇ 2 ⁇ , that is, when the moving acceleration of the subject of interest is larger than a predetermined value, the imaging ratio is set to rMAX (maximum allowable imaging ratio), and the cutting area 23
- the difference (ratio) between the size of the imaging area 22 and the size of is set to be larger than when the moving acceleration of the subject of interest is smaller than a predetermined value.
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- the determination may be made according to the scene state of the photographed image, the setting of the cropping area, the minimum allowable number of pixels of the cropping area 23, or the like.
- This embodiment 1-3 is the same as the embodiment 1-1 described earlier with reference to FIG.
- FIG. 14 shows the graph described in Example 1-1 previously described with reference to FIG. There is. This is a graph in which the horizontal axis is the velocity of the subject of interest (v), and the vertical axis is the imaging ratio.
- FIG. 14 shows the graph described in Example 1-2 previously described with reference to FIG. 13, that is, the example in which the imaging ratio is changed according to the acceleration ( ⁇ ) of the object of interest. There is. This is a graph in which the horizontal axis is the acceleration of the subject of interest ( ⁇ ), and the vertical axis is the imaging ratio.
- the optimal imaging ratio (imaging ratio for cropped image generation) corresponding to the current velocity (v) and acceleration ( ⁇ ) of the subject of interest 21 is individually calculated. calculate.
- the optimum imaging ratio (r1) corresponding to the current speed (vt) of the current subject of interest 21 is acquired.
- the current speed (v) of the subject of interest 21 be the current speed (vt) shown in the graph shown in FIG. 14 (processing A).
- the optimal imaging ratio corresponding to the current speed (vt) of the object of interest 21 is:
- the optimal imaging ratio (r1) is shown in FIG. 14 (processing A).
- the optimum imaging ratio (r2) corresponding to the current acceleration ( ⁇ t) of the current subject of interest 21 is obtained.
- the current acceleration ( ⁇ ) of the subject of interest 21 be the current acceleration ( ⁇ t) shown in the graph shown in FIG. 14 (processing B).
- the optimal imaging ratio corresponding to the current acceleration ( ⁇ t) of the object of interest 21 is:
- the optimum imaging ratio (r2) shown in FIG. 14 (processing B) is obtained.
- processing C is executed.
- processing C a process is performed in which the speed-compatible optimal imaging ratio r1 and the acceleration-compatible optimal imaging ratio r2 are compared, and the larger value is selected as the final optimal imaging ratio.
- the optimum imaging ratio r1 corresponding to speed and the optimum imaging ratio r2 corresponding to acceleration are compared.
- r1>r2 Therefore, a larger value, that is, the speed-compatible optimum imaging ratio r1 is selected as the final optimum imaging ratio. That is, The final optimum imaging ratio is set as r1.
- Example 1-1 Example of changing the imaging ratio according to the speed of the object of interest (Example 1-2)
- the image processing device of the present disclosure is, for example, the external device 30 that constitutes the image processing system shown in FIG. 2 or the PTZ camera 10.
- the processing of the present disclosure can be executed by the PTZ camera 10 alone, or can be executed by using a combination of the PTZ camera 10 and the external device 30.
- Example 1-1 Example of changing the imaging ratio according to the speed of the object of interest
- the image processing device external device 30
- processing according to the flow described below can be executed, for example, according to a program stored in the storage unit of the image processing device, and can be executed, for example, under the control of a control unit having a program execution function such as a CPU. is executed.
- a control unit having a program execution function such as a CPU. is executed.
- Step S101 the image processing device of the present disclosure calculates the velocity (v) of the subject of interest 21 in step S101.
- the image processing device that is, the external device 30 shown in FIG. 2 receives the photographed image (moving image) from the PTZ camera 10, and analyzes the change in the position of the target subject 21 on the photographed image in each image frame constituting the moving image. By doing so, the velocity (v) of the subject of interest is calculated.
- the number of moving pixels of the object of interest per unit time for example, the number of moving pixels per second (pixels/s) is calculated.
- Step S102 the image processing device of the present disclosure calculates the optimum imaging ratio (for cropped image generation image capture ratio).
- the speed-imaging ratio correspondence data is a graph shown in FIG. As explained with reference to FIG. 10, the speed-imaging ratio correspondence data is a graph in which the optimal imaging ratio is defined as follows according to the speed (v) of the subject of interest.
- the optimal imaging ratio rMIN (minimum allowable imaging ratio)
- the optimal imaging ratio is changed from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio) according to the speed (v) of the object of interest
- the optimal imaging ratio rMAX (maximum allowable imaging ratio)
- the imaging ratio corresponding to the current speed (v) of the subject of interest 21 is calculated as the optimal imaging ratio.
- the optimal imaging ratio corresponding to the current speed (vt) of the subject of interest 21 is the optimal imaging ratio (r1) shown in FIG.
- the optimal imaging ratio calculated in step S102 is a value in the range from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio) in the graph shown in FIG.
- step S103 the image processing device determines whether the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is less than a specified threshold.
- step S103 If the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is less than the specified threshold, the determination in step S103 is Yes, and in step S107 it is determined whether or not imaging is finished. If the camera (PTZ camera 10) is not zoomed, the process moves to the next processing frame without performing zoom control of the camera (PTZ camera 10).
- step S103 if the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is smaller than the specified threshold value, no control is performed and a stable image is obtained. This is done in order to continue shooting.
- step S103 determines whether the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is greater than or equal to the specified threshold. If the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is greater than or equal to the specified threshold, the determination in step S103 is No, and the process proceeds to step S104.
- the prescribed threshold value a value predefined in the image processing apparatus is used. For example, if the specified threshold value is preset around 5% and the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is smaller than the specified threshold value (for example, 5%). Based on this, it is possible to perform a process of determining whether or not to perform zoom control. For example, if the prescribed threshold value is 5%, the optimal imaging ratio calculated in step S102 is 2.2 times (220%), and the current imaging ratio is 2.0 times (200%), the calculated optimal imaging ratio is The difference between the ratio and the current imaging ratio is 0.1 (10%), which is greater than the prescribed threshold of 5%, so zoom control is performed.
- zoom control is not performed when the following (Formula 1) holds true.
- Current imaging ratio - specified threshold value ⁇ calculated optimal imaging ratio ⁇ current imaging ratio + specified threshold value... (Formula 1)
- zoom control is performed.
- Step S104 In step S103, if the difference (ratio) between the optimal imaging ratio calculated in step S102 and the current imaging ratio is equal to or greater than the specified threshold, the process advances to step S104.
- the image processing device determines in step S104 whether the optimal imaging ratio calculated in step S102 is larger or smaller than the current imaging ratio.
- step S105 If the optimal imaging ratio is larger than the current imaging ratio, the process advances to step S105. On the other hand, if the optimal imaging ratio is smaller than the current imaging ratio, the process advances to step S106.
- Step S105 If it is determined in step S104 that the optimal imaging ratio calculated in step S102 is larger than the current imaging ratio, the process advances to step S105 and the following processing is executed.
- step S105 the image processing device executes processing to widen the angle of view by adjusting the zoom (angle of view) of the camera in order to increase the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to increase the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before the imaging ratio change shown in FIG. 8(a) to the zoom (angle of view) state after the imaging ratio change shown in FIG. 8(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 8(b) are images shot with a wider angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 8(a).
- step S105 the zoom of the PTZ camera 10 is adjusted to widen the imaging range, that is, to increase the angle of view. Execute the expansion process.
- Step S106 On the other hand, if it is determined in step S104 that the optimal imaging ratio calculated in step S102 is smaller than the current imaging ratio, the process advances to step S106 and the following processing is executed.
- step S106 the image processing device executes processing to narrow the angle of view by adjusting the zoom (angle of view) of the camera in order to reduce the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to reduce the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before changing the imaging ratio shown in FIG. 9(a) to the zoom (angle of view) state after changing the imaging ratio shown in FIG. 9(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 9(b) are images shot with a narrower angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 9(a).
- step S106 the zoom of the PTZ camera 10 is adjusted to narrow the imaging range, that is, to adjust the angle of view. Execute the narrowing process.
- Step S107 After the processing in steps S105 and S106, the process advances to step S107, and in step S107, it is determined whether or not the photographing process has ended.
- step S101 the process returns to step S101 to execute the process for the next photographed image frame.
- the process is finished.
- Example 1-2 Example of changing the imaging ratio according to the acceleration of the object of interest
- the image processing device external device 30
- Step S121 the image processing device of the present disclosure calculates the acceleration ( ⁇ ) of the subject of interest 21 in step S121.
- the image processing device that is, the external device 30 shown in FIG. 2 receives the photographed image (moving image) from the PTZ camera 10, and analyzes the change in the position of the target subject 21 on the photographed image in each image frame constituting the moving image. By doing so, the acceleration ( ⁇ ) of the subject of interest is calculated.
- Step S122 the image processing device of the present disclosure calculates the optimum imaging ratio (for cropped image generation) corresponding to the acceleration ( ⁇ ) of the current subject of interest calculated in step S121, based on the acceleration-imaging ratio correspondence data. image capture ratio).
- the acceleration-imaging ratio correspondence data is a graph shown in FIG. As described with reference to FIG. 13, the acceleration-imaging ratio correspondence data is a graph in which the optimal imaging ratio is defined as follows according to the acceleration ( ⁇ ) of the subject of interest.
- the optimal imaging ratio rMIN (minimum allowable imaging ratio)
- the imaging ratio corresponding to the current acceleration ( ⁇ ) of the subject of interest 21 is calculated as the optimal imaging ratio.
- the optimal imaging ratio corresponding to the current acceleration ( ⁇ t) of the subject of interest 21 is the optimal imaging ratio (r2) shown in FIG.
- the optimal imaging ratio calculated in step S122 is a value in the range from rMIN (minimum allowable imaging ratio) to rMAX (maximum allowable imaging ratio) in the graph shown in FIG.
- step S123 the image processing device determines whether the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is less than a specified threshold value.
- step S123 If the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is less than the specified threshold, the determination in step S123 is Yes, and in step S127 it is determined whether or not imaging is finished. If the camera (PTZ camera 10) is not zoomed, the process moves to the next processing frame without performing zoom control of the camera (PTZ camera 10).
- step S123 if the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is smaller than the specified threshold value, no control is performed and a stable image is obtained. This is done in order to continue shooting.
- step S123 determines whether the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is greater than or equal to the specified threshold. If the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is greater than or equal to the specified threshold, the determination in step S123 is No, and the process proceeds to step S124.
- a value predefined in the image processing apparatus is used. For example, it is possible to perform a process in which the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is determined using a value of about 5% of the current imaging ratio. That is, it is determined whether or not to perform zoom control based on whether the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is smaller than a specified threshold (for example, 5%). This process will be performed.
- Step S124 In step S123, if the difference (ratio) between the optimal imaging ratio calculated in step S122 and the current imaging ratio is equal to or greater than the specified threshold, the process proceeds to step S124.
- the image processing device determines in step S124 whether the optimal imaging ratio calculated in step S122 is larger or smaller than the current imaging ratio.
- step S125 If the optimal imaging ratio is larger than the current imaging ratio, the process advances to step S125. On the other hand, if the optimal imaging ratio is smaller than the current imaging ratio, the process advances to step S126.
- Step S125 If it is determined in step S124 that the optimal imaging ratio calculated in step S122 is larger than the current imaging ratio, the process advances to step S125 and the following processing is executed.
- step S125 the image processing device executes processing to widen the angle of view by adjusting the zoom (angle of view) of the camera in order to increase the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to increase the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before the imaging ratio change shown in FIG. 8(a) to the zoom (angle of view) state after the imaging ratio change shown in FIG. 8(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 8(b) are images shot with a wider angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 8(a).
- step S122 if it is determined that the optimal imaging ratio calculated in step S122 is larger than the current imaging ratio, the zoom of the PTZ camera 10 is adjusted in step S125 to set a wider imaging range, that is, to increase the angle of view. Execute the expansion process.
- Step S126 On the other hand, if it is determined in step S124 that the optimal imaging ratio calculated in step S122 is smaller than the current imaging ratio, the process advances to step S126 and the following processing is executed.
- step S126 the image processing device executes processing to narrow the angle of view by adjusting the zoom (angle of view) of the camera in order to reduce the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to reduce the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before changing the imaging ratio shown in FIG. 9(a) to the zoom (angle of view) state after changing the imaging ratio shown in FIG. 9(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 9(b) are images shot with a narrower angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 9(a).
- step S126 the zoom of the PTZ camera 10 is adjusted to narrow the imaging range, that is, to adjust the angle of view. Execute the narrowing process.
- Step S127 After the processing in steps S125 and S126, the process advances to step S127, and in step S127, it is determined whether or not the photographing process has ended.
- step S121 the process returns to step S121 to execute the process for the next photographed image frame.
- the process is finished.
- Example 1-3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest This example 1-3 will be described with respect to the sequence of processing executed by the image processing device (external device 30).
- Step S141 the image processing device of the present disclosure calculates the velocity (v) and acceleration ( ⁇ ) of the subject of interest 21 in step S141.
- the image processing device that is, the external device 30 shown in FIG. 2 receives a photographed image (moving image) from the PTZ camera 10, and analyzes changes in the position of the object of interest 21 in each image frame constituting the moving image to identify the object of interest. Calculate the velocity (v) and acceleration ( ⁇ ) of .
- Step S142 the image processing device of the present disclosure calculates, based on the speed-imaging ratio correspondence data, the speed-corresponding optimal Calculate the imaging ratio.
- This process is the process previously described with reference to FIG. 14 (process A).
- the speed-imaging ratio correspondence data is a graph shown in FIG. 14 (processing A).
- the imaging ratio corresponding to the current speed of the subject of interest 21 is calculated as the speed-based optimal imaging ratio.
- the optimal imaging ratio corresponding to the current speed (vt) of the subject of interest 21 is the speed-corresponding optimal imaging ratio (r1) shown in FIG. 14 (processing A).
- step S143 the image processing device of the present disclosure calculates the acceleration corresponding optimum image capturing ratio, which is the optimum image capturing ratio corresponding to the acceleration ( ⁇ ) of the current subject of interest calculated in step S141, based on the acceleration-imaging ratio corresponding data. Calculate the imaging ratio.
- This process is the process previously described with reference to FIG. 14 (process B).
- the acceleration-imaging ratio correspondence data is a graph shown in FIG. 14 (processing B).
- the imaging ratio corresponding to the current acceleration of the subject of interest 21 is calculated as the acceleration-compatible optimal imaging ratio.
- the optimal imaging ratio corresponding to the current acceleration ( ⁇ t) of the subject of interest 21 is the acceleration-compatible optimal imaging ratio (r2) shown in FIG. 14 (processing B).
- step S144 the image processing device determines the optimum imaging ratio corresponding to the speed (v) of the object of interest (optimum imaging ratio vx corresponding to speed) and the optimum imaging ratio corresponding to the acceleration ( ⁇ ) of the object of interest (optimum imaging ratio corresponding to acceleration). Compare the ratio ⁇ x).
- This process corresponds to the process in FIG. 14 (process C) described above.
- step S145 If it is determined in step S145 that the velocity-based optimal imaging ratio vx of the subject of interest is equal to or greater than the acceleration-based optimal imaging ratio ⁇ x, the process advances to step S146. On the other hand, if it is determined that the speed-corresponding optimum imaging ratio vx of the subject of interest is less than the acceleration-corresponding optimum imaging ratio ⁇ x, the process advances to step S147.
- Step S146 If it is determined in step S145 that the velocity-based optimal imaging ratio vx of the subject of interest is equal to or greater than the acceleration-based optimal imaging ratio ⁇ x, the process advances to step S146.
- the image processing device selects the speed-corresponding optimal imaging ratio vx of the object of interest, which is a larger value, as the final optimal imaging ratio.
- Step S147 On the other hand, if it is determined in step S145 that the velocity-compatible optimal imaging ratio vx of the subject of interest is less than the acceleration-compatible optimal imaging ratio ⁇ x, the process advances to step S147.
- the image processing device selects the acceleration-compatible optimal imaging ratio ⁇ x of the object of interest, which is a larger value, as the final optimal imaging ratio.
- step S148 the image processing device determines whether the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is less than a specified threshold. judge.
- step S148 If the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is less than the specified threshold, the determination in step S148 is Yes, and the imaging is performed in step S153. It is determined whether or not the shooting has ended, and if the shooting has not ended, the processing moves to the next processing frame without performing zoom control of the camera (PTZ camera 10).
- step S148 the determination process in step S148 is performed to continue stable image capturing without performing control if the difference (ratio) between the optimal imaging ratio and the current imaging ratio is smaller than the specified threshold. It will be held on.
- step S148 determines whether the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is greater than or equal to the specified threshold. If the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is greater than or equal to the specified threshold, the determination in step S148 is No, and the step Proceed to S149.
- a value predefined in the image processing apparatus is used. For example, it is possible to perform a process in which the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is determined using a value of about 5% of the current imaging ratio. be. That is, zoom control is performed based on whether the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is smaller than a specified threshold (for example, 5%). Processing will be performed to determine whether or not to perform.
- a specified threshold for example, 5%
- Step S149 In step S148, if the difference (ratio) between the final optimal imaging ratio selected in step S146 or step S147 and the current imaging ratio is equal to or greater than the specified threshold, the process advances to step S149.
- the image processing device determines in step S149 whether the final optimal imaging ratio selected in step S146 or step S147 is larger or smaller than the current imaging ratio.
- step S151 If the optimal imaging ratio is larger than the current imaging ratio, the process advances to step S151. On the other hand, if the optimal imaging ratio is smaller than the current imaging ratio, the process advances to step S152.
- Step S151 If it is determined in step S146 or step S147 that the final optimal imaging ratio selected is larger than the current imaging ratio, the process advances to step S151 and the following processing is executed.
- step S151 the image processing device executes processing to widen the angle of view by adjusting the zoom (angle of view) of the camera in order to increase the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to increase the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before the imaging ratio change shown in FIG. 8(a) to the zoom (angle of view) state after the imaging ratio change shown in FIG. 8(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 8(b) are images shot with a wider angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 8(a).
- step S146 or step S147 is larger than the current imaging ratio
- the zoom of the PTZ camera 10 is adjusted in step S125 to widen the imaging range. Execute the settings to widen the angle of view.
- Step S152 On the other hand, if it is determined in step S146 or step S147 that the final optimal imaging ratio selected is smaller than the current imaging ratio, the process advances to step S152 and the following processing is executed.
- step S152 the image processing device adjusts the zoom (angle of view) of the camera to narrow the angle of view in order to reduce the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to reduce the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before changing the imaging ratio shown in FIG. 9(a) to the zoom (angle of view) state after changing the imaging ratio shown in FIG. 9(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 9(b) are images shot with a narrower angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 9(a).
- step S152 the zoom control parameters of the PTZ camera 10 are adjusted in step S152 to adjust the imaging range. Perform settings to narrow the angle of view, that is, execute processing to narrow the angle of view.
- Step S153 After the processing in steps S151 and S152, the process advances to step S153, and in step S153, it is determined whether or not the photographing process has ended.
- step S141 the process returns to step S141 to execute the process for the next photographed image frame.
- the process is finished.
- a communication delay occurs between the PTZ camera 10 and the external device 30 that inputs the captured image from the PTZ camera 10 and generates a cutout image, it may cause a tracking error of the subject of interest or , the probability of occurrence of a cutout image generation error increases.
- Embodiment 2 which will be described below, is an embodiment having a configuration that prevents the occurrence of such a situation.
- the graph shown in FIG. 19 is a graph in which the horizontal axis is the communication delay time (dt) between the camera and the external device, and the vertical axis is the imaging ratio correction coefficient.
- the communication delay time (dt) between the camera and the external device on the horizontal axis is, for example, the number of seconds (sec) required for communication between the camera and the external device. Note that the communication delay time may be obtained using the number of delayed frames and the frame rate (FPS).
- the imaging ratio correction coefficient on the vertical axis is, for example, a correction coefficient as a multiplication value used to calculate the optimal imaging ratio by multiplying the "minimum allowable imaging ratio rMIN" described earlier with reference to FIG. 11.
- the imaging ratio correction coefficient is 1.0, and as the communication delay time (dt) between the camera and the external device increases, the imaging ratio correction coefficient also increases. To increase. However, the maximum value is the maximum allowable correction coefficient value kMAX.
- the image processing device changes the imaging ratio as follows according to the graph shown in FIG. 19.
- the imaging ratio correction coefficient is set to change linearly from 1.0 to the maximum allowable correction coefficient value kMAX.
- the external device 30 applies the imaging ratio correction coefficient calculated from the graph shown in FIG. 19 to calculate the optimal imaging ratio (imaging ratio for cropped image generation) using the following calculation formula:
- Optimal imaging ratio (minimum allowable imaging ratio rMIN) x (imaging ratio correction coefficient)
- the value calculated according to the above formula is set as the optimal imaging ratio, and the PTZ camera 10 is caused to perform image imaging according to the imaging area size determined based on the calculated optimal imaging ratio.
- the current communication delay time (dt) between the camera and the external device is the current delay time (ta) shown in the graph shown in FIG.
- the image processing device of the second embodiment changes the imaging ratio correction coefficient from 1.0 to the maximum allowable correction coefficient when the communication delay time (dt) between the camera and the external device is 0 to t1. Change up to kMAX.
- the imaging ratio is set to increase sequentially from rMIN (minimum allowable imaging ratio) according to the delay time. The shorter the delay time, the smaller the difference (ratio) between the size of the imaging area 22 and the size of the cutout area 23 is set. Through this processing, the number of pixels in the cutout area 23 can be set to a larger number, and the deterioration in image quality of the cutout image can be reduced.
- the imaging ratio correction coefficient is set to the maximum allowable correction coefficient value kMAX.
- the imaging ratio is set to rMAX (maximum allowable imaging ratio), and the difference (ratio) of the size of the imaging area 22 to the size of the cutout area 23 is smaller than the case where the communication delay time is smaller than the predetermined value (t1). It is set large. As a result, even if the communication delay time is greater than a predetermined value, it is possible to reduce the possibility that the subject of interest will move out of the photographing range, and it is possible to reliably follow the subject of interest.
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- rMIN minimum allowable imaging ratio
- rMAX maximum allowable imaging ratio
- the determination may be made according to the scene state of the photographed image, the setting of the cropping area, the minimum allowable number of pixels of the cropping area 23, or the like.
- Example 2 Example of changing the imaging ratio according to the communication delay time between the camera and the external device This example 2 will be described with respect to the sequence of processing executed by the image processing device (external device 30).
- Step S201 the image processing device of the present disclosure calculates the communication delay time (dt) between the PTZ camera 10 and the external device 30 in step S201.
- the image processing device that is, the external device 30 shown in FIG. 2 calculates the communication delay time (dt) between the PTZ camera 10 and the external device 30 at each timing of receiving a captured image (moving image) from the PTZ camera 10. .
- the frame rate of images (moving images) captured by the PTZ camera 10 is predefined, and the communication delay time (dt) between the PTZ camera 10 and the external device 30 is calculated by analyzing the reception timing of each image frame. be able to.
- step S202 the image processing device of the present disclosure adjusts the communication delay time (dt) between the PTZ camera 10 and the external device 30 calculated in step S201 based on the communication delay time-imaging ratio correction coefficient correspondence data. Calculate the corresponding imaging ratio correction coefficient.
- the communication delay time-imaging ratio correction coefficient correspondence data calculates the imaging ratio correction coefficient as follows according to the communication delay time (dt) between the PTZ camera 10 and the external device 30. This is a prescribed graph.
- the imaging ratio correction coefficient is changed from 1.0 to the maximum allowable correction coefficient value kMAX according to the communication delay time.
- the imaging ratio correction coefficient is set to the maximum allowable correction coefficient value kMAX.
- step S203 the image processing device uses the imaging ratio correction coefficient calculated in step S202 to determine the optimal imaging ratio (imaging for cropping image generation) according to the communication delay time (dt) between the PTZ camera 10 and the external device 30. ratio).
- the optimal imaging ratio (imaging ratio for cropped image generation) is calculated according to the following formula.
- Optimal imaging ratio (minimum allowable imaging ratio rMIN) x (imaging ratio correction coefficient)
- step S204 the image processing device determines whether the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is less than a specified threshold.
- step S204 determines whether or not imaging is finished. If the camera (PTZ camera 10) is not zoomed, the process moves to the next processing frame without performing zoom control of the camera (PTZ camera 10).
- step S204 if the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is smaller than the specified threshold, no control is performed and a stable image is obtained. This is done in order to continue shooting.
- step S204 determines whether the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is greater than or equal to the specified threshold. If the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is greater than or equal to the specified threshold, the determination in step S204 is No, and the process proceeds to step S205.
- the prescribed threshold value a value predefined in the image processing apparatus is used. For example, it is possible to perform a process in which the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is determined using a value of about 5% of the current imaging ratio. That is, it is determined whether or not to perform zoom control based on whether the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is smaller than a prescribed threshold value (for example, 5%). This process will be performed.
- a prescribed threshold value for example, 5%
- Step S205 In step S204, if the difference (ratio) between the optimal imaging ratio calculated in step S203 and the current imaging ratio is greater than or equal to the specified threshold, the process advances to step S205.
- the image processing device determines in step S205 whether the optimal imaging ratio calculated in step S203 is larger or smaller than the current imaging ratio.
- step S206 If the optimal imaging ratio is larger than the current imaging ratio, the process advances to step S206. On the other hand, if the optimal imaging ratio is smaller than the current imaging ratio, the process advances to step S207.
- Step S206 If it is determined in step S205 that the optimal imaging ratio calculated in step S203 is larger than the current imaging ratio, the process advances to step S206 and the following processing is executed.
- step S206 the image processing device executes processing to widen the angle of view by adjusting the zoom (angle of view) of the camera in order to increase the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to increase the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before the imaging ratio change shown in FIG. 8(a) to the zoom (angle of view) state after the imaging ratio change shown in FIG. 8(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 8(b) are images shot with a wider angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 8(a).
- step S206 the zoom control parameters of the PTZ camera 10 are adjusted to make settings to widen the imaging range, that is, the image Executes the process of widening the corners.
- Step S207 On the other hand, if it is determined in step S205 that the optimal imaging ratio calculated in step S203 is smaller than the current imaging ratio, the process advances to step S207 and the following processing is executed.
- step S207 the image processing device executes processing to narrow the angle of view by adjusting the zoom (angle of view) of the camera in order to reduce the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to reduce the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before changing the imaging ratio shown in FIG. 9(a) to the zoom (angle of view) state after changing the imaging ratio shown in FIG. 9(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 9(b) are images shot with a narrower angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 9(a).
- step S207 the zoom control parameters of the PTZ camera 10 are adjusted to narrow the imaging range, that is, the image Executes the process of narrowing the corners.
- Step S208 After the processing in steps S206 and S207, the process advances to step S208, and in step S208, it is determined whether or not the photographing process has ended.
- step S201 If the photographing process has not been completed, the process returns to step S201 and the process for the next photographed image frame is executed. When the photographing process is finished, the process is finished.
- Example 1-3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest
- Example 2 Example of changing the imaging ratio according to the communication delay time between the camera and the external device
- Example 3 An example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device. Explain the sequence.
- Step S301 the image processing device of the present disclosure calculates the velocity (v) and acceleration ( ⁇ ) of the subject of interest 21 in step S301.
- the image processing device that is, the external device 30 shown in FIG. 2 receives a photographed image (moving image) from the PTZ camera 10, and analyzes changes in the position of the object of interest 21 in each image frame constituting the moving image to identify the object of interest. Calculate the velocity (v) and acceleration ( ⁇ ) of .
- Step S302 the image processing device of the present disclosure calculates, based on the speed-imaging ratio correspondence data, the speed-corresponding optimal Calculate the imaging ratio.
- This process is the process previously described with reference to FIG. 14 (process A).
- the speed-imaging ratio correspondence data is a graph shown in FIG. 14 (processing A).
- the imaging ratio corresponding to the current speed of the subject of interest 21 is calculated as the speed-based optimal imaging ratio.
- the optimal imaging ratio corresponding to the current speed (vt) of the subject of interest 21 is the speed-corresponding optimal imaging ratio (r1) shown in FIG. 14 (processing A).
- step S303 the image processing device of the present disclosure calculates the acceleration corresponding optimum image capturing ratio, which is the optimum image capturing ratio corresponding to the acceleration ( ⁇ ) of the current subject of interest calculated in step S301, based on the acceleration-imaging ratio corresponding data. Calculate the imaging ratio.
- This process is the process previously described with reference to FIG. 14 (process B).
- the acceleration-imaging ratio correspondence data is a graph shown in FIG. 14 (processing B).
- the imaging ratio corresponding to the current acceleration of the subject of interest 21 is calculated as the acceleration-compatible optimal imaging ratio.
- the optimal imaging ratio corresponding to the current acceleration ( ⁇ t) of the subject of interest 21 is the acceleration-compatible optimal imaging ratio (r2) shown in FIG. 14 (processing B).
- step S304 the image processing device determines the optimal imaging ratio corresponding to the speed (v) of the object of interest (optimum imaging ratio vx corresponding to speed) and the optimal imaging ratio corresponding to the acceleration ( ⁇ ) of the object of interest (optimum imaging ratio corresponding to acceleration). Compare the ratio ⁇ x).
- This process corresponds to the process in FIG. 14 (process C) described above.
- step S305 If it is determined in step S305 that the velocity-based optimal imaging ratio vx of the subject of interest is equal to or greater than the acceleration-based optimal imaging ratio ⁇ x, the process advances to step S306. On the other hand, if it is determined that the velocity-compatible optimal imaging ratio vx of the subject of interest is less than the acceleration-compatible optimal imaging ratio ⁇ x, the process advances to step S307.
- Step S306 If it is determined in step S305 that the velocity-based optimal imaging ratio vx of the subject of interest is equal to or greater than the acceleration-based optimal imaging ratio ⁇ x, the process advances to step S306.
- the image processing device selects the larger value, the optimal imaging ratio vx corresponding to the speed of the object of interest, as the optimal imaging ratio corresponding to the subject movement.
- Step S307 On the other hand, if it is determined in step S305 that the velocity-compatible optimal imaging ratio vx of the subject of interest is less than the acceleration-compatible optimal imaging ratio ⁇ x, the process advances to step S307.
- the image processing device selects the acceleration-compatible optimal imaging ratio ⁇ x of the subject of interest, which is a larger value, as the optimal imaging ratio compatible with subject movement.
- Step S311) the image processing device of the present disclosure calculates the communication delay time (dt) between the PTZ camera 10 and the external device 30 in step S311.
- the image processing device that is, the external device 30 shown in FIG. 2 calculates the communication delay time (dt) between the PTZ camera 10 and the external device 30 at each timing of receiving a captured image (moving image) from the PTZ camera 10.
- the frame rate of images (moving images) captured by the PTZ camera 10 is predefined, and the communication delay time (dt) between the PTZ camera 10 and the external device 30 is calculated by analyzing the reception timing of each image frame. be able to.
- Step S312 the image processing device of the present disclosure adjusts the communication delay time (dt) between the PTZ camera 10 and the external device 30 calculated in step S311 based on the communication delay time-imaging ratio correction coefficient correspondence data. Calculate the corresponding imaging ratio correction coefficient.
- the communication delay time-imaging ratio correction coefficient correspondence data calculates the imaging ratio correction coefficient as follows according to the communication delay time (dt) between the PTZ camera 10 and the external device 30. This is a prescribed graph.
- the imaging ratio correction coefficient is changed from 1.0 to the maximum allowable correction coefficient value kMAX according to the communication delay time.
- the imaging ratio correction coefficient is set to the maximum allowable correction coefficient value kMAX.
- step S313 the image processing device uses the optimal imaging ratio corresponding to the subject movement determined in step S306 or step S307 and the imaging ratio correction coefficient calculated in step S312 to adjust the subject movement, the PTZ camera 10, and the external environment.
- the optimum imaging ratio is calculated according to the communication delay time (dt) between the devices 30.
- Optimal imaging ratio (optimal imaging ratio corresponding to subject movement) x (imaging ratio correction coefficient)
- step S314 the image processing device determines whether the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is less than a specified threshold value.
- step S314 If the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is less than the specified threshold, the determination in step S314 is Yes, and in step S318 it is determined whether or not imaging is finished. If the camera (PTZ camera 10) is not zoomed, the process moves to the next processing frame without performing zoom control of the camera (PTZ camera 10).
- step S314 if the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is smaller than the specified threshold value, no control is performed and a stable image is obtained. This is done in order to continue shooting.
- step S314 determines whether the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is greater than or equal to the specified threshold. If the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is greater than or equal to the specified threshold, the determination in step S314 is No, and the process proceeds to step S315.
- the prescribed threshold value a value predefined in the image processing apparatus is used. For example, it is possible to perform a process in which the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is determined using a value of about 5% of the current imaging ratio. That is, it is determined whether or not to perform zoom control based on whether the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is smaller than a specified threshold (for example, 5%). This process will be performed.
- a specified threshold for example, 5%
- Step S315) In step S314, if the difference (ratio) between the optimal imaging ratio calculated in step S313 and the current imaging ratio is equal to or greater than the specified threshold, the process advances to step S315.
- the image processing device determines in step S315 whether the optimal imaging ratio calculated in step S313 is larger or smaller than the current imaging ratio.
- step S316 If the optimal imaging ratio is larger than the current imaging ratio, the process advances to step S316. On the other hand, if the optimal imaging ratio is smaller than the current imaging ratio, the process advances to step S317.
- Step S316 If it is determined in step S315 that the optimal imaging ratio calculated in step S313 is larger than the current imaging ratio, the process advances to step S316 and the following processing is executed.
- step S316 the image processing device executes processing to widen the angle of view by adjusting the zoom (angle of view) of the camera in order to increase the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to increase the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before the imaging ratio change shown in FIG. 8(a) to the zoom (angle of view) state after the imaging ratio change shown in FIG. 8(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 8(b) are images shot with a wider angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 8(a).
- step S316 the zoom control parameters of the PTZ camera 10 are adjusted to make settings to widen the imaging range, that is, the image Executes the process of widening the corners.
- Step S317) On the other hand, if it is determined in step S315 that the optimal imaging ratio calculated in step S313 is smaller than the current imaging ratio, the process advances to step S317 and the following processing is executed.
- step S317 the image processing device adjusts the zoom (angle of view) of the camera to narrow the angle of view in order to reduce the current imaging ratio to the optimum imaging ratio.
- the external device 30 adjusts the zoom (angle of view) of the PTZ camera 10 in order to reduce the current imaging ratio to the optimal imaging ratio.
- This process corresponds to, for example, the process previously described with reference to FIG. That is, this corresponds to the process of changing the zoom (angle of view) state before changing the imaging ratio shown in FIG. 9(a) to the zoom (angle of view) state after changing the imaging ratio shown in FIG. 9(b).
- the photographed image b and the photographing area 20b after the imaging ratio change in FIG. 9(b) are images shot with a narrower angle of view than the photographic image a and the photographing area 20a before the imaging ratio change in FIG. 9(a).
- step S313 if it is determined that the optimal imaging ratio calculated in step S313 is smaller than the current imaging ratio, the zoom of the PTZ camera 10 is adjusted in step S317 to narrow the imaging range, that is, to adjust the angle of view. Execute the narrowing process.
- Step S318 After the processing in steps S316 and S317, the process advances to step S318, and in step S318, it is determined whether or not the photographing process has ended.
- step S311 the process returns to step S311 to execute the process for the next photographed image frame.
- the process is finished.
- Examples 1 to 3 described above namely: (Example 1) Example of changing the imaging ratio according to at least one of the speed or acceleration of the object of interest (Example 2) Example of changing the imaging ratio according to the communication delay time between the camera and the external device (Example 3) Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and an external device
- Example 1 Example of changing the imaging ratio according to at least one of the speed or acceleration of the object of interest
- Example 2 Example of changing the imaging ratio according to the communication delay time between the camera and the external device
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and an external device
- the processing according to these examples mainly focuses on the image shown in FIG. 2, for example. It is also possible to execute it in the external device 30 that constitutes the processing system, and it is also possible to configure it to be executed by the PTZ camera 10 alone without using the external device 30.
- FIG. 23 is a diagram illustrating a processing sequence when the PTZ camera 100 performs all of the following: image capturing, image cutting, distribution of the cut out image, and camera control processing.
- the PTZ camera 100 shown in FIG. 23 corresponds to the PTZ camera 10 shown in FIG. 2 and elsewhere.
- Step S501 image shooting process
- Step S502 image analysis processing
- Step S503 image cutting processing
- Step S504 Camera control processing
- Step S505 Cutout image output processing
- the PTZ camera 100 is a camera that shoots moving images (videos), and repeatedly executes the processes of steps S501 to S505 for each frame or multiple frames that the PTZ camera 100 shoots.
- the image photographing process in step S501 is a process of photographing an image (moving image) using the PTZ camera 100.
- the image analysis process in step S502 is an image analysis process for the photographed image taken by the PTZ camera 100. For example, detection of a person to be cut out, face area detection processing, etc. are performed.
- the process of detecting the image area of the subject of interest, which is a candidate for cropping, from the photographed image can be performed by applying existing processes such as pattern matching, face detection process, skeleton detection process, segmentation process, etc.
- aspects of the person detection processing include head and face region detection processing, upper body detection processing, and whole body detection processing.
- the manner in which the person detection process is performed is determined, for example, according to a predetermined subject tracking algorithm.
- the image cutting process in step S503 is a process of cutting out a part of the image area of the captured image captured by the PTZ camera 100 based on the result of the image analysis process in step S502.
- step S503 may be performed using AI analysis using at least one of a machine learning model such as the above-mentioned deep neural network or a rule-based model to detect and track a specific person. Processing such as cutting out an image with a predetermined angle of view is performed according to the following algorithm.
- a machine learning model such as the above-mentioned deep neural network or a rule-based model to detect and track a specific person.
- the camera control process in step S504 includes camera control parameters, specifically zoom (angle of view) settings, in order to set a cropping area that includes the subject of interest in the image cropping process in step S503 and to obtain a high-quality cropped image.
- camera control parameters specifically zoom (angle of view) settings
- This is the process of calculating values, etc. That is, the optimum camera control parameters for image capturing of the region of the cut-out image are calculated, and the calculated camera control parameters are set in the PTZ camera 100 to execute image capturing.
- Example 1 Example of changing the imaging ratio according to at least one of the speed or acceleration of the object of interest (Example 2)
- Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device The processing according to these examples includes the following steps shown in FIG. It will be executed as a process.
- Step S502 image analysis processing
- Step S503 image cutting processing
- Step S504 Camera control processing
- the cutout image output process of step S505 is a process of distributing the cutout image 25 including the subject of interest cut out in the image cutout process of step S503 to the outside or storing it in the storage unit.
- a cutout image 25 is distributed (displayed) to a user terminal 80 such as a smartphone.
- steps S501 to S505 are repeatedly executed for each processed image frame captured by the PTZ camera 100.
- the example shown in FIG. 23 is a configuration example in which the image processing of the present disclosure is executed within the PTZ camera 100.
- a configuration in which part of the image processing of the present disclosure is executed in an external device other than the PTZ camera 100 is also possible. An example of such a configuration will be described with reference to FIG. 24.
- FIG. 24 shows the PTZ camera 100 and the external device 120.
- the external device 120 corresponds to the external device 30 described above with reference to FIG. 2 and others.
- the PTZ camera 100 and the external device 120 have a configuration that allows them to communicate.
- the external device 120 is configured by at least one device connected to the PTZ camera 100 wirelessly or by wire, such as a PC, a server (cloud), a switcher, or another image processing device.
- the PTZ camera 100 captures images (moving images) and transmits captured image data to the external device 120.
- the external device 120 performs image analysis processing, image cutout processing, camera control parameter calculation processing, cutout image output processing, etc. on the captured image received from the PTZ camera 100.
- the external device 120 calculates camera control parameters generated by the above processing, that is, control parameters such as zoom control parameters that are optimal for generating a cutout image, and transmits them to the PTZ camera 100.
- the PTZ camera 100 sets camera control parameters received from the external device 120 and executes image capturing.
- the external device 120 executes recording processing, display processing, and distribution processing of cutout images.
- the external device 120 stores and records the cutout image generated by the external device 120 on the recording medium 121. Further, the external device 120 executes a process of distributing the generated cutout image to a user terminal 130 such as a smartphone or a television owned by the user.
- FIG. 25 shows an example of a processing sequence using the PTZ camera 100 shown in FIG. 24 and the external device 120.
- Step S521 Image shooting process
- Step S522 Shooting image output process
- Step S528 Camera control process
- an external device 120 such as a PC, a server (cloud), a switcher, or another image processing device executes the following process.
- Step S523 Photographed image input processing
- Step S524 Image analysis processing
- Step S525 Image cutting processing
- Step S526 Camera control parameter generation and transmission processing
- Step S527 Cutout image output processing
- the PTZ camera 100 is a camera that shoots moving images (videos), and the PTZ camera 100 and the external device 120 repeatedly execute the processing of steps S521 to S527 for each frame or multiple frames that the PTZ camera 100 shoots. .
- the image photographing process in step S521 is a process of photographing an image (moving image) using the PTZ camera 100.
- the PTZ camera 100 transmits the captured image to the external device 120 in step S522.
- the external device 120 inputs the captured image from the PTZ camera 100 in step S523.
- the image analysis process in step S524 executed by the external device 120 is an image analysis process for the captured image captured by the PTZ camera 100. For example, detection of a person to be cut out, face area detection processing, etc. are performed.
- the process of detecting the image area of the subject of interest, which is a cropping candidate, from the photographed image can be performed by applying existing processes such as pattern matching, face detection process, skeleton detection process, and segmentation process.
- aspects of the person detection processing include head and face region detection processing, upper body detection processing, and whole body detection processing.
- the manner in which the person detection process is performed is determined, for example, according to a predetermined subject tracking algorithm.
- the image cutting process of step S525 is a process of cutting out a part of the image area of the photographed image taken by the PTZ camera 100 based on the result of the image analysis process of step S524.
- step S525 is performed, for example, by detecting and tracking a specific person using AI analysis using at least one of a machine learning model such as the aforementioned deep neural network or a rule-based model. Processing such as cutting out an image with a predetermined angle of view is performed according to the following algorithm.
- the camera control parameter calculation and transmission process in step S526 includes camera control parameters for setting a cropping area including the subject of interest in the image cropping process in step S524 and obtaining a high-quality cropped image. This is the process of calculating and transmitting the setting values (angle of view), etc. That is, the optimum camera control parameters for image capturing of the cut-out image area are calculated, and the calculated camera control parameters are transmitted to the PTZ camera 100.
- Example 1 Example of changing the imaging ratio according to at least one of the speed or acceleration of the object of interest (Example 2)
- Example of changing the imaging ratio according to the communication delay time between the camera and the external device Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device
- Example 3 Example of changing the imaging ratio according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device
- the processing according to these examples includes the following steps shown in FIG. It will be executed as a process.
- Step S524 image analysis processing
- Step S525 image cutting process
- Step S526 Camera control parameter calculation, transmission processing
- the cut-out image output process in step S527 is a process in which the cut-out image 25 including the subject of interest cut out in the image cut-out process in step S525 is distributed to the outside or stored in the storage unit.
- a cutout image 25 is distributed (displayed) to a user terminal 80 such as a smartphone.
- steps S521 to S528 are repeatedly executed for each processed image frame captured by the PTZ camera 100.
- the image processing of the present disclosure can be performed by the camera alone, or can be performed as collaborative processing between the camera and other external devices. It is possible.
- the image processing of the present disclosure can be performed by a single camera, or can be performed as collaborative processing between the camera and other external devices.
- a configuration example of an image processing apparatus that is, a PTZ camera 100, in which the image processing of the present disclosure is executed by a single camera will be described.
- the PTZ camera 100 which is an example of the image processing device of the present disclosure, includes an imaging unit 201, an image analysis unit 202, a cutting area calculation unit 203, a target subject movement (velocity, acceleration) analysis unit 204, an optimal imaging unit It includes a ratio calculation section 205, a cutout execution section 206, an output section 207, a recording processing section 208, a recording medium 209, an optimal imaging area determination section 211, a camera control parameter calculation section 212, and a camera control section 213.
- the imaging unit 201 executes image capturing processing.
- a subject of interest such as a tracking target
- a moving image is captured to capture a tracking image of the subject of interest.
- a machine learning model such as a deep neural network or a rule-based model
- the process of detecting and following a specific person from a captured image can be performed with high precision. It is now possible to do so.
- the PTZ camera is automatically controlled (pan, tilt, and zoom controls) to capture a tracking image of the subject of interest.
- the image analysis unit 202 executes image analysis processing on the captured image captured by the imaging unit 201. For example, detection of a person to be cut out, face area detection processing, tracking processing, etc. are performed.
- the image analysis unit 202 performs person detection processing by applying processing such as pattern matching, face detection processing, skeleton detection processing, and segmentation processing.
- the cropping area calculation unit 203 executes a process of calculating the position and size of an image cropping area, such as a cropping rectangle, in the photographed image that includes a predetermined subject of interest.
- the cropping area calculation unit 203 calculates a cropping area including the subject of interest from the image according to a predefined algorithm.
- extraction area setting algorithms there are various types of extraction area setting algorithms. Specifically, there are, for example, a cropping area setting algorithm that includes the whole body area of the subject of interest, a cropping area setting algorithm that includes only the upper body area of the subject of interest, or a cropping area setting algorithm that includes only the face area of the subject of interest.
- the object of interest movement (velocity, acceleration) analysis unit 204 calculates the movement of the object of interest, specifically, at least one of speed and acceleration.
- the target subject movement (velocity, acceleration) analysis unit 204 analyzes changes in the position of the target subject in each image frame constituting the moving image captured by the imaging unit 201, thereby determining the velocity (v) or acceleration ( ⁇ ) of the target subject. Calculate at least one of the following. These calculated values are input to the optimal imaging ratio calculation unit 205.
- the optimal imaging ratio calculation unit 205 calculates at least one of the clipping area information calculated by the clipping area calculation unit 203 and the velocity (v) or acceleration ( ⁇ ) of the target subject analyzed by the target subject movement (velocity, acceleration) analysis unit 204. is input, and an optimal imaging ratio corresponding to at least one of the velocity (v) and acceleration ( ⁇ ) of the subject of interest, that is, the "imaging ratio for generating a cutout image" is calculated.
- Example 1-1 Example of changing the imaging ratio according to the speed of the object of interest (Example 1-2)
- Attention Example of changing the imaging ratio according to the speed and acceleration of the object Execute the processing according to any of these examples to change the imaging ratio according to at least one of the speed (v) or acceleration ( ⁇ ) of the object of interest. Calculate the optimal imaging ratio.
- the optimal imaging ratio calculated by the optimal imaging ratio calculation unit 205 according to at least one of the velocity (v) or acceleration ( ⁇ ) of the subject of interest is the optimal imaging area together with the extraction area information calculated by the extraction area calculation unit 203. It is output to the determining section 211.
- the optimal imaging area determining unit 211 applies the clipping area information calculated by the clipping area calculation unit 203 and the optimal imaging ratio calculated by the optimal imaging ratio calculation unit 205 to determine the imaging area of the image captured by the imaging unit 201. Determine the size.
- the aspect ratio of the imaging area is defined in advance, and once the height H of the imaging area is calculated, the width L of the imaging area can also be calculated.
- the size of the imaging area calculated by the optimal imaging area determination unit 211 is input to the camera control parameter calculation unit 212.
- the camera control parameter calculation unit 212 uses zoom control parameters necessary to capture an image with an angle of view of the size of the imaging area (height x width (H x L) of the imaging area) calculated by the optimal imaging area determination unit 211. Calculate.
- the zoom control parameters calculated by the camera control parameter calculation section 212 are output to the camera control section 213.
- the camera control unit 213 sets the zoom control parameters calculated by the camera control parameter calculation unit 212 in the PTZ camera 100, and causes the PTZ camera 100 to perform image capturing using the zoom control parameters.
- the cropping execution unit 206 executes image cropping processing from the photographed image based on the image cropping area calculated by the cropping area calculation unit 203.
- the cutout area calculation unit 203 calculates the cutout area including the subject of interest according to a predefined algorithm as described above with reference to FIG. 3.
- the cropping execution unit 206 executes image cropping processing according to the cropping area determined according to this predefined algorithm.
- the output unit 207 outputs the cutout image cut out by the cutout execution unit 206 to at least one of various user terminals such as an external device, a smartphone, and a television.
- the recording processing unit 208 records the cutout image cut out by the cutout execution unit 206 on the recording medium 209.
- FIG. 27 is a diagram showing an example of the configuration of the PTZ camera 100 and the external device 120.
- the external device 120 is configured by, for example, at least one of a PC, a server (cloud), a switcher, a broadcasting device, another image processing device, and the like.
- the PTZ camera 100 and the external device 120 are connected by at least one of wired and wireless means and have a configuration in which they can communicate with each other.
- the PTZ camera 100 shown in FIG. 27 includes an imaging section 221, an output section 222, a recording processing section 223, a recording medium 224, and a camera control section 225.
- the external device 120 also includes an input unit 301, an image analysis unit 302, a cropping area calculation unit 303, a target subject movement (velocity, acceleration) analysis unit 304, an optimal imaging ratio calculation unit 305, a cropping execution unit 306, an output unit 307, It includes a recording processing section 308, a recording medium 309, an optimal imaging area determining section 311, and a camera control parameter calculating section 312.
- the imaging unit 221 of the PTZ camera 100 executes image capturing processing.
- a subject of interest such as a tracking target
- a moving image is captured to capture a tracking image of the subject of interest.
- a machine learning model such as a deep neural network or a rule-based model
- the process of detecting and following a specific person from a captured image can be performed with high precision. It is now possible to do so.
- the PTZ camera is automatically controlled (pan, tilt, and zoom controls) to capture a tracking image of the subject of interest.
- the image taken by the imaging unit 221 is output to the external device 120 via the output unit 222 and is recorded on the recording medium 224 via the recording processing unit 223.
- the camera control unit 225 applies camera control parameters input from the camera control parameter calculation unit 312 of the external device 120 to cause the imaging unit 221 to execute image capturing.
- the PTZ camera 100 can perform image shooting by applying optimal camera control parameters, specifically zoom setting parameters, etc. to the cutout image determined by the external device 120.
- the input unit 301 of the external device 120 inputs the image captured by the imaging unit 221 of the PTZ camera 100 from the output unit 222 of the PTZ camera 100 and outputs it to the image analysis unit 302.
- the processing of the image analysis unit 302 to camera control parameter calculation unit 312 of the external device 120 is similar to the processing of the image analysis unit 202 to camera control parameter calculation unit 212 of the PTZ camera 100, which was previously explained with reference to FIG. It is.
- the external device 120 executes image analysis processing, that is, detection of a person to be cut out, and also executes image cutting processing.
- the optimal imaging ratio calculation unit 305 of the external device 120 executes optimal imaging ratio calculation processing. That is, the following embodiments described above, (Example 1-1) Example of changing the imaging ratio according to the speed of the object of interest (Example 1-2) Example of changing the imaging ratio according to the acceleration of the object of interest (Example 1-3) Attention Example of changing the imaging ratio according to the speed and acceleration of the object Execute the processing according to any of these examples to change the imaging ratio according to at least one of the speed (v) or acceleration ( ⁇ ) of the object of interest. Calculate the optimal imaging ratio.
- the optimal imaging ratio calculated by the optimal imaging ratio calculation unit 305 according to at least one of the velocity (v) or acceleration ( ⁇ ) of the subject of interest is based on the extraction area information calculated by the extraction area calculation unit 303 of the external device 120. It is also output to the optimum imaging area determination unit 311.
- the optimum imaging area determination unit 311 applies the cutting area information calculated by the cutting area calculation unit 303 and the optimum imaging ratio calculated by the optimum imaging ratio calculation unit 305 to determine the imaging area of the image captured by the PTZ camera 100. Determine the size.
- the camera control parameter calculation unit 312 uses zoom control parameters necessary to capture an image with an angle of view of the size of the imaging area (height x width (H x L) of the imaging area) calculated by the optimal imaging area determination unit 211. Calculate.
- the zoom control parameters calculated by the camera control parameter calculation unit 312 are output to the camera control unit 225 of the PTZ camera 100.
- the camera control unit 225 of the PTZ camera 100 sets the zoom control parameters calculated by the camera control parameter calculation unit 312 of the external device 120 in the PTZ camera 100, and causes the PTZ camera 100 to perform image capturing using the zoom control parameters.
- FIG. 28 shows Example 2 and Example 3 described above, that is, (Example 2) An example of changing the imaging ratio according to the communication delay time between the camera and an external device (Example 3) Imaging according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device Embodiment of changing the ratio It is a diagram showing an example of the configuration of a PTZ camera 100 and an external device 120 that make it possible to execute these embodiments.
- the PTZ camera 100 shown in FIG. 28 has the same configuration as the PTZ camera 100 shown in FIG. 27.
- the external device 120 shown in FIG. 28 has a configuration in which a communication delay time calculation section 313 is added to the external device 120 shown in FIG. 27.
- Other configurations are similar to the configuration shown in FIG. 27.
- the external device 120 shown in FIG. 28 has a configuration that prevents the occurrence of such a situation, and has a configuration that allows the imaging ratio to be changed according to the communication delay time between the PTZ camera 100 and the external device 120. be.
- the communication delay time calculation unit 313 of the external device 120 calculates the communication delay time between the PTZ camera 100 and the external device 120.
- the frame rate of the captured image (moving image) of the PTZ camera 100 is predefined, and the communication delay time calculation unit 313 of the external device 120 analyzes the reception timing of the image frame that the input unit 301 receives from the PTZ camera 100, for example. Then, the communication delay time between the PTZ camera 100 and the external device 120 is calculated.
- Information indicating the communication delay time between the PTZ camera 100 and the external device 120 calculated by the communication delay time calculation unit 313 is output to the optimal imaging ratio calculation unit 305.
- the optimal imaging ratio calculation unit 305 calculates the imaging ratio correction coefficient described above with reference to FIG. 19, and further calculates the optimal imaging ratio by executing processing according to one of the following embodiments.
- Example 2 An example of changing the imaging ratio according to the communication delay time between the camera and an external device (Example 3) Imaging according to the speed and acceleration of the object of interest and the communication delay time between the camera and the external device Example of changing the ratio
- the process according to the flowchart shown in FIG. 20 is executed to calculate the optimum imaging ratio. Furthermore, when executing the process according to the above (Embodiment 3), the optimum imaging ratio is calculated by executing the process according to the flowcharts shown in FIGS. 21 and 22.
- the optimal imaging ratio calculated by the optimal imaging ratio calculation unit 305 is output to the optimal imaging area determination unit 311 together with the extraction area information calculated by the extraction area calculation unit 303.
- the subsequent processing is similar to the processing described with reference to FIG.
- FIG. 29 is an example of the hardware configuration of, for example, the camera or external device described above with reference to FIGS. 20 to 23.
- the hardware configuration shown in FIG. 29 will be explained.
- a CPU (Central Processing Unit) 701 functions as a data processing unit that executes various processes according to programs stored in a ROM (Read Only Memory) 702 or a storage unit 708. For example, processing according to the sequence described in the embodiment described above is executed.
- a RAM (Random Access Memory) 703 stores programs executed by the CPU 701, data, and the like. These CPU 701, ROM 702, and RAM 703 are interconnected by a bus 704.
- the CPU 701 is connected to an input/output interface 705 via a bus 704, and the input/output interface 705 includes an input section 706 consisting of various sensors, cameras, switches, keyboards, mice, microphones, etc., and an output section 707 consisting of a display, speakers, etc. is connected.
- an input section 706 consisting of various sensors, cameras, switches, keyboards, mice, microphones, etc.
- an output section 707 consisting of a display, speakers, etc. is connected.
- a storage unit 708 connected to the input/output interface 705 is made up of, for example, a hard disk, and stores programs executed by the CPU 701 and various data.
- the communication unit 709 functions as a transmitting/receiving unit for data communication via a network such as the Internet or a local area network, and communicates with an external device.
- a drive 710 connected to the input/output interface 705 drives a removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory such as a memory card, and records or reads data.
- a removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory such as a memory card
- the technology disclosed in this specification can have the following configuration.
- a cropping area calculation unit that calculates an image area including the subject of interest from an image captured by the camera as an image cropping area;
- a cropping execution unit that generates a cropped image by cropping the image of the image cropping area calculated by the cropping area calculation unit;
- the cutout image generation is a size ratio between the size of the cutout image and the size of an imaging area corresponding to the entire image area of the image taken by the camera.
- an imaging ratio calculation unit that calculates an imaging ratio for a camera control parameter calculation unit that calculates a camera control parameter for causing the camera to take an image according to an imaging area size determined based on the calculated imaging ratio for generating a cutout image;
- An image processing device that causes the camera to perform image capturing using camera control parameters calculated by the camera control parameter calculation unit.
- the camera is: It is a PTZ camera capable of panning, tilting, and zooming processing
- the camera control parameter calculation unit includes: The image processing device according to (1), which calculates a zoom control parameter for photographing an image according to an imaging area size of the camera calculated from the imaging ratio for generating a cutout image.
- the image processing device includes: comprising a subject of interest movement analysis unit that analyzes the movement of the subject of interest;
- the imaging ratio calculation unit includes: Inputting the analysis results of the noted subject movement analysis section, The image processing device according to (1) or (2), which calculates an imaging ratio for generating a cutout image according to at least one of the speed and acceleration of the object of interest.
- the imaging ratio calculation unit includes: The faster the speed of the object of interest is, the larger the imaging ratio for generating the cropped image is calculated;
- the camera control parameter calculation unit includes: The image processing device according to (3), wherein the image processing device calculates a zoom control parameter that increases the imaging area of the camera as the speed of the object of interest increases.
- the imaging ratio calculation unit includes: The larger the acceleration of the object of interest, the larger the imaging ratio for generating the cutout image.
- the camera control parameter calculation unit includes: The image processing device according to (3) or (4), wherein the image processing device calculates a zoom control parameter that increases the imaging area of the camera as the acceleration of the subject of interest increases.
- the imaging ratio calculation unit includes: Calculating an imaging ratio for generating a cutout image according to at least one of the velocity or acceleration of the object of interest as a value between a predefined minimum allowable imaging ratio and a predefined maximum allowable imaging ratio (3) to (5).
- An image processing device according to claim 1.
- the maximum allowable imaging ratio is: The image processing device according to (6), wherein the imaging ratio is determined according to the minimum allowable number of pixels included in the cutout image.
- the imaging ratio calculation unit includes: The image processing device according to any one of (3) to (7), which calculates the imaging ratio for generating the cutout image using correspondence data between the speed of the object of interest and the imaging ratio for generating the cutout image.
- the imaging ratio calculation unit The image processing device according to any one of (3) to (8), which calculates the imaging ratio for generating the cutout image using correspondence data between the acceleration of the subject of interest and the imaging ratio for generating the cutout image.
- the imaging ratio calculation unit includes: a speed-compatible imaging ratio calculated from the speed of the object of interest; Comparing acceleration-compatible imaging ratios calculated from the acceleration of the object of interest, The image processing device according to any one of (3) to (9), wherein the imaging ratio having a larger value is determined as the final imaging ratio for generating the cutout image.
- the image processing device is an external device capable of communicating with the camera,
- the image processing device includes: comprising a communication delay time calculation unit that calculates communication delay time between the camera and the image processing device;
- the imaging ratio calculation unit includes: The image processing device according to any one of (1) to (10), wherein an imaging ratio for generating a cutout image is calculated according to a communication delay time between the camera and the image processing device calculated by the communication delay time calculation unit.
- the imaging ratio calculation unit includes: The larger the communication delay time between the camera and the image processing device, the larger the imaging ratio for generating the cropped image is calculated;
- the camera control parameter calculation unit includes: The image processing device according to (11), wherein the larger the communication delay time between the camera and the image processing device, the larger the zoom control parameter that increases the imaging area of the camera.
- the imaging ratio calculation unit includes: In (11) or (12), an imaging ratio for generating a cutout image according to a communication delay time between the camera and the image processing device is calculated as a value between a predefined minimum allowable imaging ratio and a predefined maximum allowable imaging ratio.
- the imaging ratio calculation unit includes: The image processing device according to any one of (11) to (13), wherein the imaging ratio for generating the cutout image is calculated using correspondence data between a communication delay time between the camera and the image processing device and an imaging ratio correction coefficient.
- the imaging ratio correction coefficient is a multiplication coefficient for calculating an imaging ratio for generating a cutout image by multiplying a predefined minimum allowable imaging ratio.
- the imaging ratio correction coefficient is a multiplication coefficient for calculating the final cropped image generation imaging ratio by multiplying the imaging ratio corresponding to the subject movement, which is calculated according to the movement of the subject of interest. ) or the image processing device according to (15).
- the image processing device is an external device capable of communicating with the camera,
- the image processing device includes: a subject of interest movement analysis unit that analyzes the movement of the subject of interest; comprising a communication delay time calculation unit that calculates communication delay time between the camera and the image processing device;
- the imaging ratio calculation unit includes: the analysis results of the noted subject movement analysis unit; inputting the communication delay time between the camera and the image processing device calculated by the communication delay time calculation unit;
- the image processing device according to any one of (1) to (16), which calculates an imaging ratio for generating a cutout image according to a speed and acceleration of the object of interest and a communication delay time between the camera and the image processing device.
- An image processing method executed in an image processing device a cropping area calculating step in which the cropping area calculating unit calculates an image area including the subject of interest from an image taken by the camera as an image cropping area; a cropping execution step in which the cropping execution unit generates a cropped image by cropping the image of the image cropping area calculated in the cropping area calculating step;
- the imaging ratio calculation unit uses the size of the cutout image and the size of the imaging area corresponding to the entire image area of the captured image of the camera as an index value for executing the cutout image generation process including the subject of interest.
- the camera control parameter calculation unit executes a camera control parameter calculation step of calculating a camera control parameter for causing the camera to take an image according to the imaging area size determined based on the calculated imaging ratio for generating the cutout image. death, An image processing method that causes the camera to perform image capturing using camera control parameters calculated by the camera control parameter calculation unit.
- a program that causes an image processing device to perform image processing, a cropping area calculation step of causing a cropping area calculating unit to calculate an image area including the subject of interest from an image taken by the camera as an image cropping area; a cropping execution step in which a cropping execution unit generates a cropped image by cropping the image of the image cropping area calculated in the cropping area calculating step;
- the size of the size of the cut-out image and the size of the image-capturing area corresponding to the entire image area of the captured image of the camera is used as an index value for causing the imaging ratio calculation unit to execute a cut-out image generation process that includes the subject of interest.
- a step of calculating an imaging ratio for generating a cropped image which is a ratio
- Execute a camera control parameter calculation step of causing the camera control parameter calculation unit to calculate a camera control parameter for causing the camera to take an image according to the imaging area size determined based on the calculated imaging ratio for generating the cutout image.
- a program that records the processing sequence can be installed and executed in the memory of a computer built into dedicated hardware, or the program can be installed on a general-purpose computer that can execute various types of processing. It is possible to install and run it.
- the program can be recorded in advance on a recording medium.
- the program can be received via a network such as a LAN (Local Area Network) or the Internet, and installed on a recording medium such as a built-in hard disk.
- a system is a logical collective configuration of a plurality of devices, and the devices of each configuration are not limited to being in the same housing.
- the optimal imaging ratio (cutout A device and a method for calculating an imaging ratio for image generation are realized. Specifically, for example, in a configuration in which an image cropping area including the subject of interest is calculated from an image taken by a PTZ camera, and an image of the calculated area is cropped to generate a cropped image, the process of generating a cropped image including the subject of interest is further performed. As an index value for ensuring execution, an optimum imaging ratio (imaging ratio for generating a cutout image), which is the size ratio of the camera's imaging area to the cutout image, is calculated.
- a zoom parameter for photographing an image according to the camera imaging area size calculated from the optimum imaging ratio is calculated, and the PTZ camera is caused to perform image photographing using the calculated parameters.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
Description
また、例えば、サッカー等のスポーツ映像においても、特定の注目被写体、例えば特定の選手の画像領域を切り出した追従映像データを生成することが要求される場合がある。
PTZカメラはパン、チルト、ズーム処理が可能であり、カメラの撮影方向を注目被写体に向けることが可能である。注目被写体が移動しても、より長期間に渡って注目被写体を所定の大きさの画像サイズの撮影領域内に維持しながら撮影を行うことが可能となる。
カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出部と、
前記切り出し領域算出部が算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行部と、
前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出部と、
算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出部を有し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理装置にある。
画像処理装置において実行する画像処理方法であり、
切り出し領域算出部が、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出ステップと、
切り出し実行部が、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行ステップと、
撮像比率算出部が、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出ステップと、
カメラ制御パラメータ算出部が、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出ステップを実行し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理方法にある。
画像処理装置において画像処理を実行させるプログラムであり、
切り出し領域算出部に、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出させる切り出し領域算出ステップと、
切り出し実行部に、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成させる切り出し実行ステップと、
撮像比率算出部に、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出させる切り出し画像生成用撮像比率算出ステップと、
カメラ制御パラメータ算出部に、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出させるカメラ制御パラメータ算出ステップを実行させ、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させるプログラムにある。
具体的には、例えば、PTZカメラの撮影画像から注目被写体を含む画像切り出し領域を算出し、算出した領域の画像を切り出して切り出し画像を生成する構成において、注目被写体を含む切り出し画像生成処理をより確実に実行させるための指標値として、切り出し画像に対するカメラの撮像領域のサイズ比率である最適撮像比率(切り出し画像生成用撮像比率)を算出する。さらに最適撮像比率から算出されるカメラの撮像領域サイズに従った画像を撮影させるためのズームパラメータを算出して、算出パラメータを適用した画像撮影をPTZカメラに実行させる。
本構成により、PTZカメラの撮影画像から注目被写体を含む切り出し画像生成処理をより確実に実行させるための指標値である最適撮像比率(切り出し画像生成用撮像比率)を算出する装置、方法が実現される。
なお、本明細書に記載された効果はあくまで例示であって限定されるものではなく、また付加的な効果があってもよい。
1.PTZカメラを用いた画像切り出しを伴う注目被写体の追従画像生成処理の概要について
2.本開示の画像処理装置の実行する処理について
3.(実施例1)(実施例1)注目被写体の速度、または加速度の少なくともいずれかに応じて撮像比率を変更する実施例
3-1.(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
3-2.(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
3-3.(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
4.実施例1の画像処理装置が実行する処理のシーケンスについて
5.(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
6.(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
7.本開示の画像処理装置の構成例について
8.本開示の画像処理装置の詳細構成について
9.画像処理装置のハードウェア構成例について
10.本開示の構成のまとめ
まず、図1以下を参照してPTZカメラを用いた画像切り出しを伴う注目被写体の追従画像生成処理の概要について説明する。
カメラの撮影方向を水平方向に回動させるパン処理、
カメラの撮影方向を垂直方向に回動させるチルト処理、
カメラの撮影画角を変更(=撮影領域の拡大、縮小)するズーム処理、
これらの処理を行うことが可能なカメラである。
このようなAI解析を利用することで、PTZカメラを自動制御(パン、チルト、ズームの各制御)して注目被写体の追従映像を撮影することが可能である。
なお、以下の説明において、「画像」は動画像である映像、および映像を構成する画像フレームを含むものとして説明する。
以下、各処理ステップについて説明する。
まず、ステップS01において、PTZカメラ10が画像撮影を行う。画像は動画像(映像)である。
図に示す撮影画像20は、PTZカメラ10が撮影した動画像(映像)の1つの画像フレームの例である。
撮影画像20には、例えば追従対象である注目被写体21が撮影されている。
次に、ステップS02において、PTZカメラ10は撮影画像を画像解析処理や画像切り出し処理の実行装置である外部装置30に送信する。
外部装置30は、PTZカメラ10から受信した撮影画像20から、注目被写体21の検出を実行するとともに、検出した注目被写体21の画像領域を切り出す画像切り出し処理を実行する。
図に示すように、撮影画像20全体の領域である撮像領域22から一部の画像領域を切り出し領域23として切り出す処理を行う。
例えば注目被写体21の全身領域が含まれる画像領域を切り出し領域23として設定して画像切り出しを実行する。
図3に示す「(1)全身ショット」は、注目被写体21の全身領域を含む切り出し領域設定アルゴリズムの一例を示している。切り出し領域23のほぼ中央位置に注目被写体21の全身領域の位置を設定し、注目被写体21の上下左右に予め規定した長さ、例えば注目被写体21の上下に注目被写体の高さの10%程度のマージン領域、注目被写体21の左右に注目被写体の横幅の50%程度のマージン領域を設定した矩形領域を切り出し領域23とする。
外部装置30は、ステップS03において、PTZカメラ10が撮影する撮影画像20の各画像フレームに切り出し領域23設定して、各画像フレーム対応の切り出し画像を生成する。各画像フレーム対応のこれらの切り出し画像を再生することで、注目被写体21が大きく映し出された注目被写体を中心とした映像を生成することができる。
外部装置30は、さらに、ステップS03における画像切り出し処理を実行する際に画像解析も実行する。外部装置30は、撮影画像20から検出した注目被写体21の移動方向や移動速度を推定し、ステップS04において、これらの推定結果に基づいてPTZカメラ10にカメラ駆動指示を送信する。
PTZカメラ10は、外部装置30からのカメラ駆動指示データを受信すると、ステップS05において、受信したカメラ駆動指示データに基づいてカメラの向き(パン、チルト)やズーム設定を変更、更新する。
なお、切り出し画像から構成される映像は、注目被写体21が切り出し前の撮影画像における注目被写体21よりも大きく撮影された映像となる。
図4を参照して、この問題点の具体例について説明する。
PTZカメラ10は、時間(t0)~(t2)において注目被写体21を含む撮影画像20a~cを撮影して外部装置30に送信する。
外部装置30は、PTZカメラ10から受信した撮影画像20から注目被写体21を検出し、撮影画像20の全体領域に相当する撮像領域22から注目被写体21の全身領域を含む切り出し領域23を設定して切り出す処理を行う。
すなわち、図4に示す(処理b)の処理を実行する。
撮影画像20cの注目被写体21は、一部がPTZカメラ10の撮影範囲の端部付近または撮像範囲外となってしまっている。
これは、撮影方向を右方向に移動させるパン動作がPTZカメラ10の歯車機構等のメカ駆動により実行されるため時間を要するためである。
すなわち、図5に示す(処理x)の処理を実行する。
外部装置30からPTZカメラ10に対するカメラ駆動(PTZ駆動)指示の送信タイミングは時間(t1+dt2)である。
撮影画像の撮影タイミング(t1)から、すでに時間td2が経過している。
このデータ通信にも通信遅延が発生している。(dt3-dt2)は、外部装置30からPTZカメラ10へカメラ駆動(PTZ駆動)指示を送信する通信処理に要した時間(=通信遅延時間)に相当する。
このように、PTZカメラ10のメカ駆動による遅延に、外部装置30との間の通信遅延が加わると、さらに、注目被写体の追従エラーや画像切り出しエラーの発生可能性が高まることになる。
以下、本開示の画像処理装置の構成と処理の詳細について説明する。
以下、本開示の画像処理装置の実行する処理について説明する。
図6は、本開示の画像処理装置が実行する処理の具体例について説明する図である。
図6に示すように、本開示の画像処理装置は、例えば追従対象である注目被写体の移動する速度、または加速度、または通信遅延を含む処理遅延時間等の少なくともいずれかに応じて撮像比率を変更する制御を実行する。
(a)撮像比率変更前の画像撮影例
(b)撮像比率変更後の画像撮影例
具体的には、(b)撮像比率変更後の画像撮影例における撮像領域22bのサイズが、(a)撮像比率変更前の画像撮影例における撮像領域22aのサイズより大きくなっている。
撮像比率=(撮像領域サイズ/切り出し領域サイズ)
である。
図7には、(a)撮影画像例と、(b)撮像比率説明図を示している。
撮像比率=(撮像領域サイズ/切り出し領域サイズ)
=H/h
である。
なお、撮像領域22の縦横比と、切り出し領域23の縦横比は同じである。
図8に示すように、
(a)撮像比率変更前の画像撮影例における撮像比率は、
撮像比率=Ha/ha
である。
また、(b)撮像比率変更後の画像撮影例における撮像比率は、
撮像比率=Hb/hb
である。
(Ha/ha)<(Hb/hb)
となる。すなわち、(b)撮像比率変更後の画像撮影例における撮像比率(Hb/hb)は、(a)撮像比率変更後の画像撮影例における撮像比率(Ha/ha)より大きな値(大きな比率)に変更されている。
この処理によりPTZカメラ10の撮影可能範囲が広げられ、注目被写体21を見失うことなく追従撮影を継続することが可能となる。
図9には、図8と同様、PTZカメラ10による以下の2つの画像撮影例を示している。
(a)撮像比率変更前の画像撮影例
(b)撮像比率変更後の画像撮影例
(a)撮像比率変更前の画像撮影例における撮像比率は、
撮像比率=Ha/ha
である。
また、(b)撮像比率変更後の画像撮影例における撮像比率は、
撮像比率=Hb/hb
である。
(Ha/ha)>(Hb/hb)
となる。すなわち、(b)撮像比率変更後の画像撮影例における撮像比率(Hb/hb)は、(a)撮像比率変更後の画像撮影例における撮像比率(Ha/ha)より小さな値(小さな比率)に変更されている。
この処理によりPTZカメラ10の撮影可能範囲が狭められ、撮像領域22における切り出し領域23の割合を大きくすることが可能となる。すなわち注目被写体21を含む切り出し領域23の割合が大きくなり、結果として、切り出し画像23の画像領域の画素数が増加することとなり、切り出し画像23の画質を向上させることができる。
次に、本開示の画像処理装置が実行する処理の具体例について説明する。
(実施例1)注目被写体の速度、または加速度の少なくともいずれかに応じて撮像比率を変更する実施例
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
まず、注目被写体の速度に応じて撮像比率を変更する実施例について説明する。
図10に示すグラフは、横軸に注目被写体速度(v)、縦軸に撮像比率を設定したグラフである。
縦軸の撮像比率は、先に図7他を参照して説明したように、撮影画像20の全体領域に相当する撮像領域22の高さHと、切り出し領域23の高さhとの比率、
撮像比率=(撮像領域サイズ/切り出し領域サイズ)
=H/h
である。
(a)注目被写体の速度(v)=0~v1では、撮像比率=rMIN(許容最小撮像比率)
(b)注目被写体の速度(v)=v1~v2では、撮像比率を、rMIN(許容最小撮像比率)からrMAX(許容最大撮像比率)まで注目被写体の速度(v)に応じて変化させる
(c)注目被写体の速度(v)=v2~では、撮像比率=rMAX(許容最大撮像比率)
この処理により、切り出し領域23の画素数をより多く設定することができ、切り出し画像の画質の低下を軽減させることができる。
これにより、注目被写体の移動が速い場合でも、注目被写体が撮影範囲から外に出てしまう可能性を低減でき、注目被写体の確実な追従処理が可能となる。
rMIN(許容最小撮像比率)と、rMAX(許容最大撮像比率)は予め規定した固定値としてもよいが、撮影画像のシーンの状態や切り出し領域の設定、あるいは切り出し領域23の許容最小画素数(予め設定された許容される最小の画素数)などに応じて決定してもよい。
rMIN(許容最小撮像比率)は、切り出し領域23に対して、どこまで撮像領域を小さく設定できるかの下限比率を示す値である。
なお、注目被写体に対する切り出し領域の設定も画像撮影開始前に予め決定しておく。
rMIN(許容最小撮像比率)=Ha1/ha1
であり、比較的(注目被写体の一部だけを含めるショットの設定の場合よりも)、rMIN(許容最小撮像比率)の値(比率)が小さく設定される。
rMIN(許容最小撮像比率)=Ha2/ha2
であり、比較的(注目被写体の上半身より大きい領域を含めるショットの設定の場合よりも)、rMIN(許容最小撮像比率)の値(比率)が大きく設定される。
例えば、図11の(b1)は、注目被写体の動きが激しい(動きが多い、移動量が多い)シーンである。
この場合は、rMIN(許容最小撮像比率)は、撮像領域22の高さHb1と、切り出し領域23の高さhb1との比率、
rMIN(許容最小撮像比率)=Hb1/hb1
であり、比較的(注目被写体の動きがより少ないシーンの場合よりも)、rMIN(許容最小撮像比率)の値(比率)が大きく設定される。
rMIN(許容最小撮像比率)=Hb2/hb2
であり、比較的(注目被写体の動きがより多いシーンの場合よりも)、rMIN(許容最小撮像比率)の値(比率)が小さく設定される。
rMAX(許容最大撮像比率)=(撮像領域22の高さ画素数)/(切り出し領域23の高さ画素数)
=2160/720
=3
rMAX(許容最大撮像比率)は、3となる。
(a)注目被写体の速度(v)=0~v1では、撮像比率=rMIN(許容最小撮像比率)
(b)注目被写体の速度(v)=v1~v2では、撮像比率を、rMIN(許容最小撮像比率)からrMAX(許容最大撮像比率)まで変化させる
(c)注目被写体の速度(v)=v2~では、撮像比率=rMAX(許容最大撮像比率)
なお、「最適撮像比率(切り出し画像生成用撮像比率)」は注目被写体を含む切り出し画像生成処理を従来より確実に実行させるための指標値であり、また、注目被写体を含む切り出し画像の画質を所定以上の画質とするための指標値である。
図10に示すグラフを用いて、この注目被写体21の現在速度(vt)に対応する撮像比率を最適撮像比率として算出する。注目被写体21の現在速度(vt)に対応する最適撮像比率は、図10に示す最適撮像比率(r1)となる。
具体的には、撮像領域22(=撮影画像20の画像全体領域)の高さHを、
H=r1×hとした設定での画像撮影処理をPTZカメラ10に実行させる。
なお、hは切り出し領域23の高さである。
この処理により、切り出し領域23の画素数をより多く設定することができ、切り出し画像の画質の低下を軽減させることができる。
これにより、注目被写体の移動が速い場合でも、注目被写体が撮影範囲から外に出てしまう可能性を低減でき、注目被写体の確実な追従処理が可能となる。
次に、注目被写体の加速度に応じて撮像比率を変更する実施例について説明する。
図13に示すグラフは、横軸に注目被写体加速度(α)、縦軸に撮像比率を設定したグラフである。
縦軸の撮像比率は、先に図7他を参照して説明したように、撮影画像20の全体領域に相当する撮像領域22の高さHと、切り出し領域23の高さhとの比率、
撮像比率=(撮像領域サイズ/切り出し領域サイズ)
=H/h
である。
(a)注目被写体の加速度(α)=0~α1では、撮像比率=rMIN(許容最小撮像比率)
(b)注目被写体の加速度(α)=α1~α2では、撮像比率を、rMIN(許容最小撮像比率)からrMAX(許容最大撮像比率)まで注目被写体の加速度(α)に応じて変化させる
(c)注目被写体の加速度(α)=α2~では、撮像比率=rMAX(許容最大撮像比率)
図13に示すグラフを用いて、この注目被写体21の現在加速度(αt)に対応する撮像比率を最適撮像比率として算出する。注目被写体21の現在加速度(αt)に対応する最適撮像比率は、図13に示す最適撮像比率(r2)となる。
具体的には、撮像領域22(=撮影画像20の画像全体領域)の高さHを、
H=r2×hとした設定での画像撮影処理をPTZカメラ10に実行させる。
なお、hは切り出し領域23の高さである。
この処理により、切り出し領域23の画素数をより多く設定することができ、切り出し画像の画質の低下を軽減させることができる。
これにより、注目被写体の移動速度が急激に速くなった場合でも、注目被写体が撮影範囲から外に出てしまう可能性を低減でき、注目被写体の確実な追従処理が可能となる。
例えば、rMIN(許容最小撮像比率)と、rMAX(許容最大撮像比率)は予め規定した固定値としてもよい。あるいは、先に図11、図12を参照して説明したように、撮影画像のシーンの状態や切り出し領域の設定、あるいは切り出し領域23の許容最小画素数などに応じて決定してもよい。
次に、注目被写体の速度と加速度に応じて撮像比率を変更する実施例について説明する。
現在の注目被写体21の速度(v)を図14(処理A)に示すグラフに示す現在速度(vt)とする。
図14(処理A)に示すグラフを用いて、この注目被写体21の現在速度(vt)に対応する最適撮像比率を算出すると、注目被写体21の現在速度(vt)に対応する最適撮像比率は、図14(処理A)に示す最適撮像比率(r1)となる。
現在の注目被写体21の加速度(α)を図14(処理B)に示すグラフに示す現在加速度(αt)とする。
図14(処理B)に示すグラフを用いて、この注目被写体21の現在加速度(αt)に対応する最適撮像比率を算出すると、注目被写体21の現在加速度(αt)に対応する最適撮像比率は、図14(処理B)に示す最適撮像比率(r2)となる。
(処理C)では、速度対応最適撮像比率r1と加速度対応最適撮像比率r2を比較し、より大きな値を最終最適撮像比率として選択する処理を実行する。
図に示す例では、
r1>r2
であるので、より大きな値、すなわち、速度対応最適撮像比率r1を最終最適撮像比率として選択する。
すなわち、
最終最適撮像比率=r1とする。
具体的には、撮像領域22(=撮影画像20の画像全体領域)の高さHを、
H=r1×hとして画像撮影処理を実行させる。
なお、hは切り出し領域23の高さである。
次に、上述した本開示の実施例1の画像処理装置が実行する処理のシーケンスについて説明する。
(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
後段において説明するが、本開示の処理は、PTZカメラ10単体で実行することも可能であり、PTZカメラ10と外部装置30の組み合わせを利用して実行する構成も可能である。
図15以下のフローチャートにおいて説明する画像処理装置の処理は、外部装置30が実行するものとして説明する。ただし、上述したように、PTZカメラ10において実行することも可能である。
(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
この実施例1-1を、画像処理装置(外部装置30)が実行する処理のシーケンスについて説明する。
まず、本開示の画像処理装置は、ステップS101において、注目被写体21の速度(v)を算出する。
次に、本開示の画像処理装置は、ステップS102において、速度-撮像比率対応データに基づいて、ステップS101で算出した現在の注目被写体の速度(v)に対応する最適撮像比率(切り出し画像生成用撮像比率)を算出する。
(a)注目被写体の速度(v)=0~v1では、最適撮像比率=rMIN(許容最小撮像比率)
(b)注目被写体の速度(v)=v1~v2では、最適撮像比率を、rMIN(許容最小撮像比率)からrMAX(許容最大撮像比率)まで注目被写体の速度(v)に応じて変化させる
(c)注目被写体の速度(v)=v2~では、最適撮像比率=rMAX(許容最大撮像比率)
次に、画像処理装置はステップS103において、ステップS102で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値未満であるか否かを判定する。
言い換えれば、次の(式1)が成り立つ場合にはズーム制御を行わない。
現在の撮像比率‐規定しきい値 < 算出した最適撮像比率 < 現在の撮像比率+規定しきい値…(式1)
一方で、以下の(式2)または(式3)が成り立つ場合にはズーム制御を行う。
算出した最適撮像比率 ≧ 現在の撮像比率+規定しきい値…(式2)
算出した最適撮像比率 ≦ 現在の撮像比率―規定しきい値…(式3)
ステップS103において、ステップS102で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値以上である場合は、ステップS104に進む。
一方、最適撮像比率が現在の撮像比率より小さい場合は、ステップS106に進む。
ステップS104で、ステップS102で算出した最適撮像比率が現在の撮像比率より大きいと判定した場合は、ステップS105に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで大きくするため、カメラのズーム(画角)を調整して画角を広げさせるカメラ駆動指示を出力する。
すなわち、図8(a)に示す撮像比率変更前のズーム(画角)状態を、図8(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図8(b)撮像比率変更後の撮影画像b,撮影領域20bは、図8(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が広い設定で撮影される画像となる。
一方、ステップS104で、ステップS102で算出した最適撮像比率が現在の撮像比率より小さいと判定した場合は、ステップS106に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで小さくするため、カメラのズーム(画角)を調整して画角を狭めさせるカメラ駆動指示を出力する。
すなわち、図9(a)に示す撮像比率変更前のズーム(画角)状態を、図9(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図9(b)撮像比率変更後の撮影画像b,撮影領域20bは、図9(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が狭い設定で撮影される画像となる。
ステップS105、ステップS106の処理の後、ステップS107に進み、ステップS107において、撮影処理終了か否かを判定する。
撮影処理が終了した場合は、処理を終了する。
(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
この実施例1-2を、画像処理装置(外部装置30)が実行する処理のシーケンスについて説明する。
まず、本開示の画像処理装置は、ステップS121において、注目被写体21の加速度(α)を算出する。
次に、本開示の画像処理装置は、ステップS122において、加速度-撮像比率対応データに基づいて、ステップS121で算出した現在の注目被写体の加速度(α)に対応する最適撮像比率(切り出し画像生成用撮像比率)を算出する。
(a)注目被写体の加速度(α)=0~α1では、最適撮像比率=rMIN(許容最小撮像比率)
(b)注目被写体の加速度(α)=α1~α2では、最適撮像比率を、rMIN(許容最小撮像比率)からrMAX(許容最大撮像比率)まで注目被写体の加速度(α)に応じて変化させる
(c)注目被写体の加速度(α)=α2~では、最適撮像比率=rMAX(許容最大撮像比率)
次に、画像処理装置はステップS123において、ステップS122で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値未満であるか否かを判定する。
すなわち、ステップS122で算出した最適撮像比率と、現在の撮像比率との差分(比率)が、規定しきい値(例えば5%)より小さいかどうかに基づいて、ズーム制御を行うか否かを判定する処理を行うことになる。
ステップS123において、ステップS122で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値以上である場合は、ステップS124に進む。
一方、最適撮像比率が現在の撮像比率より小さい場合は、ステップS126に進む。
ステップS124で、ステップS122で算出した最適撮像比率が現在の撮像比率より大きいと判定した場合は、ステップS125に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで大きくするため、カメラのズーム(画角)を調整して画角を広げさせるカメラ駆動指示を出力する。
すなわち、図8(a)に示す撮像比率変更前のズーム(画角)状態を、図8(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図8(b)撮像比率変更後の撮影画像b,撮影領域20bは、図8(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が広い設定で撮影される画像となる。
一方、ステップS124で、ステップS122で算出した最適撮像比率が現在の撮像比率より小さいと判定した場合は、ステップS126に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで小さくするため、カメラのズーム(画角)を調整して画角を狭めさせるカメラ駆動指示を出力する。
すなわち、図9(a)に示す撮像比率変更前のズーム(画角)状態を、図9(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図9(b)撮像比率変更後の撮影画像b,撮影領域20bは、図9(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が狭い設定で撮影される画像となる。
ステップS125、ステップS126の処理の後、ステップS127に進み、ステップS127において、撮影処理終了か否かを判定する。
撮影処理が終了した場合は、処理を終了する。
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
この実施例1-3を、画像処理装置(外部装置30)が実行する処理のシーケンスについて説明する。
まず、本開示の画像処理装置は、ステップS141において、注目被写体21の速度(v)と加速度(α)を算出する。
次に、本開示の画像処理装置は、ステップS142において、速度-撮像比率対応データに基づいて、ステップS141で算出した現在の注目被写体の速度(v)に対応する最適撮像比率である速度対応最適撮像比率を算出する。
次に、本開示の画像処理装置は、ステップS143において、加速度-撮像比率対応データに基づいて、ステップS141で算出した現在の注目被写体の加速度(α)に対応する最適撮像比率である加速度対応最適撮像比率を算出する。
次に、画像処理装置はステップS144において、注目被写体の速度(v)対応の最適撮像比率(速度対応最適撮像比率vx)と、注目被写体の加速度(α)対応の最適撮像比率(加速度対応最適撮像比率αx)を比較する。
一方、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx未満であると判定した場合は、ステップS147に進む。
ステップS145において、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx以上であると判定した場合は、ステップS146に進む。
一方、ステップS145において、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx未満であると判定した場合は、ステップS147に進む。
次に、画像処理装置はステップS148において、ステップS146、またはステップS147において選択した最終的な最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値未満であるか否かを判定する。
すなわち、ステップS146、またはステップS147において選択した最終的な最適撮像比率と、現在の撮像比率との差分(比率)が、規定しきい値(例えば5%)より小さいかどうかに基づいて、ズーム制御を行うか否かを判定する処理を行うことになる。
ステップS148において、ステップS146、またはステップS147において選択した最終的な最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値以上である場合は、ステップS149に進む。
一方、最適撮像比率が現在の撮像比率より小さい場合は、ステップS152に進む。
ステップS146、またはステップS147において選択した最終的な最適撮像比率が現在の撮像比率より大きいと判定した場合は、ステップS151に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで大きくするため、カメラのズーム(画角)を調整して画角を広げさせるカメラ駆動指示を出力する。
すなわち、図8(a)に示す撮像比率変更前のズーム(画角)状態を、図8(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図8(b)撮像比率変更後の撮影画像b,撮影領域20bは、図8(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が広い設定で撮影される画像となる。
一方、ステップS146、またはステップS147において選択した最終的な最適撮像比率が現在の撮像比率より小さいと判定した場合は、ステップS152に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで小さくするため、カメラのズーム(画角)を調整して画角を狭めさせるカメラ駆動指示を出力する。
すなわち、図9(a)に示す撮像比率変更前のズーム(画角)状態を、図9(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図9(b)撮像比率変更後の撮影画像b,撮影領域20bは、図9(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が狭い設定で撮影される画像となる。
ステップS151、ステップS152の処理の後、ステップS153に進み、ステップS153において、撮影処理終了か否かを判定する。
撮影処理が終了した場合は、処理を終了する。
次に、(実施例2)として、カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例について説明する。
図19に示すグラフは、横軸にカメラと外部装置間の通信遅延時間(dt)、縦軸に撮像比率補正係数を設定したグラフである。
縦軸の撮像比率補正係数は、例えば先に図11を参照して説明した「最小許容撮像比率rMIN」に乗算して最適撮像比率を算出するために用いる乗算値としての補正係数である。
ただし、最大値は、補正係数許容最大値kMAXである。
補正係数許容最大値kMAX=(許容最大撮像比率rMAX)/(許容最小撮像比率rMIN)
(a)カメラと外部装置間の通信遅延時間(dt)=0~t1では、撮像比率補正係数を1.0から、補正係数許容最大値kMAXまで通信遅延時間に応じて変化させる。
(b)カメラと外部装置間の通信遅延時間(dt)=t1~では、撮像比率補正係数を補正係数許容最大値kMAXとする。
最適撮像比率=(最小許容撮像比率rMIN)×(撮像比率補正係数)
上記式に従って算出される値を最適撮像比率として、算出した最適撮像比率に基づいて決定される撮像領域サイズに従った画像撮影をPTZカメラ10に実行させる。
図19に示すグラフを用いて、現在のカメラと外部装置間の通信遅延時間(dt)=taに対応する撮像比率補正係数=1.2を算出する。
さらに、算出した撮像比率補正係数=1.2を適用して、以下の式に従って、最適撮像比率を算出する。
最適撮像比率=(最小許容撮像比率rMIN)×(撮像比率補正係数)
=(最小許容撮像比率rMIN)×(1.2)
すなわち、現在のカメラと外部装置間の通信遅延時間(dt)=taの場合、最適撮像比率は、(最小許容撮像比率rMIN)の1.2倍の撮像比率となる。
具体的には、撮像領域22(=撮影画像20の画像全体領域)の高さHを、
H=(1.2(rMIN))×hとした設定での画像撮影処理をPTZカメラ10に実行させる。
なお、hは切り出し領域23の高さである。
この結果、撮像比率は、rMIN(許容最小撮像比率)から、遅延時間に応じて、順次増加する設定とされる。遅延時間が少ないほど、切り出し領域23のサイズに対する撮像領域22のサイズの差分(比率)が小さく設定される。
この処理により、切り出し領域23の画素数をより多く設定することができ、切り出し画像の画質の低下を軽減上させることができる。
これにより、通信遅延時間が所定値より大きい場合でも、注目被写体が撮影範囲から外に出てしまう可能性を低減でき、注目被写体の確実な追従処理が可能となる。
例えば、rMIN(許容最小撮像比率)と、rMAX(許容最大撮像比率)は予め規定した固定値としてもよい。あるいは、先に図11、図12を参照して説明したように、撮影画像のシーンの状態や切り出し領域の設定、あるいは切り出し領域23の許容最小画素数などに応じて決定してもよい。
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
この実施例2を、画像処理装置(外部装置30)が実行する処理のシーケンスについて説明する。
まず、本開示の画像処理装置は、ステップS201において、PTZカメラ10と外部装置30間の通信遅延時間(dt)を算出する。
PTZカメラ10の撮影画像(動画像)のフレームレートは予め規定されており、各画像フレームの受信タイミングを解析することで、PTZカメラ10と外部装置30間の通信遅延時間(dt)を算出することができる。
次に、本開示の画像処理装置は、ステップS202において、通信遅延時間-撮像比率補正係数対応データに基づいて、ステップS201で算出したPTZカメラ10と外部装置30間の通信遅延時間(dt)に対応する撮像比率補正係数を算出する。
通信遅延時間-撮像比率補正係数対応データは、図19を参照して説明したように、PTZカメラ10と外部装置30間の通信遅延時間(dt)に応じて以下のように撮像比率補正係数を規定したグラフである。
(a)カメラと外部装置間の通信遅延時間(dt)=0~t1では、撮像比率補正係数を1.0から、補正係数許容最大値kMAXまで通信遅延時間に応じて変化させる。
(b)カメラと外部装置間の通信遅延時間(dt)=t1~では、撮像比率補正係数を補正係数許容最大値kMAXとする。
例えば図19に示す例では、PTZカメラ10と外部装置30間の通信遅延時間(dt)=taの場合、撮像比率補正係数=1.2となる。
次に、画像処理装置はステップS203において、ステップS202で算出した撮像比率補正係数を用いてPTZカメラ10と外部装置30間の通信遅延時間(dt)に応じた最適撮像比率(切り出し画像生成用撮像比率)を算出する。
最適撮像比率=(最小許容撮像比率rMIN)×(撮像比率補正係数)
次に、画像処理装置はステップS204において、ステップS203で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値未満であるか否かを判定する。
すなわち、ステップS203で算出した最適撮像比率と、現在の撮像比率との差分(比率)が、規定しきい値(例えば5%)より小さいかどうかに基づいて、ズーム制御を行うか否かを判定する処理を行うことになる。
ステップS204において、ステップS203で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値以上である場合は、ステップS205に進む。
一方、最適撮像比率が現在の撮像比率より小さい場合は、ステップS207に進む。
ステップS205で、ステップS203で算出した最適撮像比率が現在の撮像比率より大きいと判定した場合は、ステップS206に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで大きくするため、カメラのズーム(画角)を調整して画角を広げさせるカメラ駆動指示を出力する。
すなわち、図8(a)に示す撮像比率変更前のズーム(画角)状態を、図8(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図8(b)撮像比率変更後の撮影画像b,撮影領域20bは、図8(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が広い設定で撮影される画像となる。
一方、ステップS205で、ステップS203で算出した最適撮像比率が現在の撮像比率より小さいと判定した場合は、ステップS207に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで小さくするため、カメラのズーム(画角)を調整して画角を狭めさせるカメラ駆動指示を出力する。
すなわち、図9(a)に示す撮像比率変更前のズーム(画角)状態を、図9(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図9(b)撮像比率変更後の撮影画像b,撮影領域20bは、図9(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が狭い設定で撮影される画像となる。
ステップS206、ステップS207の処理の後、ステップS208に進み、ステップS208において、撮影処理終了か否かを判定する。
撮影処理が終了した場合は、処理を終了する。
次に、(実施例3)として、注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例について説明する。
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
これら2つの実施例を併せて実行する実施例に相当する。
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
この実施例3を画像処理装置(外部装置30)が実行する処理のシーケンスについて説明する。
まず、本開示の画像処理装置は、ステップS301において、注目被写体21の速度(v)と加速度(α)を算出する。
次に、本開示の画像処理装置は、ステップS302において、速度-撮像比率対応データに基づいて、ステップS301で算出した現在の注目被写体の速度(v)に対応する最適撮像比率である速度対応最適撮像比率を算出する。
次に、本開示の画像処理装置は、ステップS303において、加速度-撮像比率対応データに基づいて、ステップS301で算出した現在の注目被写体の加速度(α)に対応する最適撮像比率である加速度対応最適撮像比率を算出する。
次に、画像処理装置はステップS304において、注目被写体の速度(v)対応の最適撮像比率(速度対応最適撮像比率vx)と、注目被写体の加速度(α)対応の最適撮像比率(加速度対応最適撮像比率αx)を比較する。
一方、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx未満であると判定した場合は、ステップS307に進む。
ステップS305において、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx以上であると判定した場合は、ステップS306に進む。
一方、ステップS305において、注目被写体の速度対応最適撮像比率vxが、加速度対応最適撮像比率αx未満であると判定した場合は、ステップS307に進む。
次に、本開示の画像処理装置は、ステップS311において、PTZカメラ10と外部装置30間の通信遅延時間(dt)を算出する。
PTZカメラ10の撮影画像(動画像)のフレームレートは予め規定されており、各画像フレームの受信タイミングを解析することで、PTZカメラ10と外部装置30間の通信遅延時間(dt)を算出することができる。
次に、本開示の画像処理装置は、ステップS312において、通信遅延時間-撮像比率補正係数対応データに基づいて、ステップS311で算出したPTZカメラ10と外部装置30間の通信遅延時間(dt)に対応する撮像比率補正係数を算出する。
通信遅延時間-撮像比率補正係数対応データは、図19を参照して説明したように、PTZカメラ10と外部装置30間の通信遅延時間(dt)に応じて以下のように撮像比率補正係数を規定したグラフである。
(a)カメラと外部装置間の通信遅延時間(dt)=0~t1では、撮像比率補正係数を1.0から、補正係数許容最大値kMAXまで通信遅延時間に応じて変化させる。
(b)カメラと外部装置間の通信遅延時間(dt)=t1~では、撮像比率補正係数を補正係数許容最大値kMAXとする。
例えば図19に示す例では、PTZカメラ10と外部装置30間の通信遅延時間(dt)=taの場合、撮像比率補正係数=1.2となる。
次に、画像処理装置はステップS313において、ステップS306、またはステップS307で決定した被写体動き対応最適撮像比率と、ステップS312で算出した撮像比率補正係数を用いて、被写体動きと、PTZカメラ10と外部装置30間の通信遅延時間(dt)に応じた最適撮像比率を算出する。
最適撮像比率=(被写体動き対応最適撮像比率)×(撮像比率補正係数)
次に、画像処理装置はステップS314において、ステップS313で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値未満であるか否かを判定する。
すなわち、ステップS313で算出した最適撮像比率と、現在の撮像比率との差分(比率)が、規定しきい値(例えば5%)より小さいかどうかに基づいて、ズーム制御を行うか否かを判定する処理を行うことになる。
ステップS314において、ステップS313で算出した最適撮像比率と、現在の撮像比率との差分(比率)が規定しきい値以上である場合は、ステップS315に進む。
一方、最適撮像比率が現在の撮像比率より小さい場合は、ステップS317に進む。
ステップS315で、ステップS313で算出した最適撮像比率が現在の撮像比率より大きいと判定した場合は、ステップS316に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで大きくするため、カメラのズーム(画角)を調整して画角を広げさせるカメラ駆動指示を出力する。
すなわち、図8(a)に示す撮像比率変更前のズーム(画角)状態を、図8(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図8(b)撮像比率変更後の撮影画像b,撮影領域20bは、図8(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が広い設定で撮影される画像となる。
一方、ステップS315で、ステップS313で算出した最適撮像比率が現在の撮像比率より小さいと判定した場合は、ステップS317に進み、以下の処理を実行する。
具体的には、例えば図2に示すシステム構成において、外部装置30が、PTZカメラ10に対して、現在の撮像比率を最適撮像比率まで小さくするため、カメラのズーム(画角)を調整して画角を狭めさせるカメラ駆動指示を出力する。
すなわち、図9(a)に示す撮像比率変更前のズーム(画角)状態を、図9(b)に示す撮像比率変更後のズーム(画角)状態に変更する処理に相当する。
図9(b)撮像比率変更後の撮影画像b,撮影領域20bは、図9(a)撮像比率変更前の撮影画像a,撮影領域20aより画角が狭い設定で撮影される画像となる。
ステップS316、ステップS317の処理の後、ステップS318に進み、ステップS318において、撮影処理終了か否かを判定する。
撮影処理が終了した場合は、処理を終了する。
次に、本開示の画像処理装置の構成例について説明する。
(実施例1)注目被写体の速度、または加速度の少なくともいずれかに応じて撮像比率を変更する実施例
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
これらの実施例に従った処理は、主に例えば図2に示す画像処理システムを構成する外部装置30において実行することも可能であり、外部装置30を用いることなくPTZカメラ10単独で実行する構成とすることもできる。
図23に示すPTZカメラ100は、図2他に示すPTZカメラ10に相当する。
ステップS501=画像撮影処理、
ステップS502=画像解析処理、
ステップS503=画像切り出し処理、
ステップS504=カメラ制御処理
ステップS505=切り出し画像出力処理
(実施例1)注目被写体の速度、または加速度の少なくともいずれかに応じて撮像比率を変更する実施例
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
これらの実施例に従った処理は、図23に示す以下の各ステップの処理として実行されることになる。
ステップS502=画像解析処理、
ステップS503=画像切り出し処理、
ステップS504=カメラ制御処理
例えば図に示すようにスマホ等のユーザ端末80に切り出し画像25が配信(表示)される。
このような構成例の他、本開示の画像処理の一部をPTZカメラ100以外の外部装置において実行する構成も可能である。
このような構成例の一例について図24を参照して説明する。
PTZカメラ100と外部装置120は通信可能な構成を有する。
外部装置120は、PTZカメラ100と無線または有線で接続された装置、例えばPC、サーバ(クラウド)、スイッチャー、その他の画像処理装置などの少なくともいずれかによって構成される。
外部装置120は、PTZカメラ100から受信する撮影画像に対して、画像解析処理、画像切り出し処理、カメラ制御パラメータ算出処理、切り出し画像出力処理などを実行する。
外部装置120は、外部装置120が生成した切り出し画像を記録メディア121に格納して記録する。
さらに、外部装置120は、生成した切り出し画像を、ユーザが所有するスマホやテレビ等のユーザ端末130に配信する処理を実行する。
ステップS521=画像撮影処理
ステップS522=撮影画像出力処理
ステップS528=カメラ制御処理
ステップS523=撮影画像入力処理
ステップS524=画像解析処理
ステップS525=画像切り出し処理
ステップS526=カメラ制御パラメータ生成、送信処理
ステップS527=切り出し画像出力処理
PTZカメラ100は、ステップS522において、撮影画像を外部装置120に送信する。
次に外部装置120が実行するステップS524の画像解析処理は、PTZカメラ100が撮影した撮影画像に対する画像解析処理である。例えば切り出し対象となる人物の検出、顔領域の検出処理などが行われる。
(実施例1)注目被写体の速度、または加速度の少なくともいずれかに応じて撮像比率を変更する実施例
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
これらの実施例に従った処理は、図25に示す以下の各ステップの処理として実行されることになる。
ステップS524=画像解析処理、
ステップS525=画像切り出し処理、
ステップS526=カメラ制御パラメータ算出、送信処理
例えば図に示すようにスマホ等のユーザ端末80に切り出し画像25が配信(表示)される。
次に、本開示の画像処理装置の詳細構成について説明する。
まず、図26を参照して、本開示の画像処理をカメラ単体で実行する構成とした場合の画像処理装置、すなわちPTZカメラ100の構成例について説明する。
なお、予め追従対象等の注目被写体を決定し、この注目被写体の追従画像を撮影する動画像の撮影を行う。
前述したようにディープニューラルネットワーク等の機械学習モデルまたはルールベースのモデルのうち少なくとも一つを利用したAI解析を行うことで、撮影画像から特定の人物を検出して追従する処理を高精度に実行することが可能となっている。
このようなAI解析を利用することで、PTZカメラを自動制御(パン、チルト、ズームの各制御)して注目被写体の追従映像を撮影する。
画像解析部202は、例えばパターンマッチングや顔検出処理、骨格検出処理、セグメンテーション処理等の処理を適用して人物検出処理を実行する。
切り出し領域算出部203は、予め規定したアルゴリズムに従って画像から注目被写体を含む切り出し領域を算出する。
注目被写体動き(速度、加速度)解析部204は、撮像部201が撮影した動画像を構成する各画像フレームの注目被写体の位置変化を解析することで注目被写体の速度(v)または加速度(α)の少なくともいずれかを算出する。
これらの算出値は、最適撮像比率算出部205に入力される。
(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
これらいずれかの実施例に従った処理を実行して、注目被写体の速度(v)または加速度(α)の少なくともいずれか一つに応じた最適撮像比率を算出する。
H=(最適撮像比率)×h
上記算出式に従って算出する。
なお、hは切り出し領域23の高さである。
カメラ制御パラメータ算出部212は、最適撮像領域決定部211が算出した撮像領域のサイズ(撮像領域の高さ×幅(H×L))の画角の画像を撮影するために必要なズーム制御パラメータを算出する。
カメラ制御部213は、カメラ制御パラメータ算出部212が算出したズーム制御パラメータをPTZカメラ100に設定し、このズーム制御パラメータを適用した画像撮影を実行させる。
記録処理部208は、切り出し実行部206が切り出した切り出し画像を記録メディア209に記録する。
なお、外部装置120は、例えばPC、サーバ(クラウド)、スイッチャー、放送機器、その他の画像処理装置などの少なくともいずれかによって構成される。
また、PTZカメラ100と外部装置120は有線または無線の少なくともいずれかで接続されており相互に通信可能な構成を有する。
また、外部装置120は、入力部301、画像解析部302、切り出し領域算出部303、注目被写体動き(速度、加速度)解析部304、最適撮像比率算出部305、切り出し実行部306、出力部307、記録処理部308、記録メディア309、最適撮像領域決定部311、カメラ制御パラメータ算出部312を有する。
なお、予め追従対象等の注目被写体を決定し、この注目被写体の追従画像を撮影する動画像の撮影を行う。
前述したようにディープニューラルネットワーク等の機械学習モデルまたはルールベースのモデルのうち少なくとも一つを利用したAI解析を行うことで、撮影画像から特定の人物を検出して追従する処理を高精度に実行することが可能となっている。
このようなAI解析を利用することで、PTZカメラを自動制御(パン、チルト、ズームの各制御)して注目被写体の追従映像を撮影する。
この処理により、PTZカメラ100は、外部装置120が決定した切り出し画像に最適なカメラ制御パラメータ、具体的にはズーム設定パラメータ等を適用した画像撮影を実行することができる。
すなわち、先に説明した以下の実施例、
(実施例1-1)注目被写体の速度に応じて撮像比率を変更する実施例
(実施例1-2)注目被写体の加速度に応じて撮像比率を変更する実施例
(実施例1-3)注目被写体の速度と加速度に応じて撮像比率を変更する実施例
これらいずれかの実施例に従った処理を実行して、注目被写体の速度(v)または加速度(α)の少なくともいずれか一つに応じた最適撮像比率を算出する。
H=(最適撮像比率)×h
上記算出式に従って算出する。
なお、hは切り出し領域23の高さである。
カメラ制御パラメータ算出部312は、最適撮像領域決定部211が算出した撮像領域のサイズ(撮像領域の高さ×幅(H×L))の画角の画像を撮影するために必要なズーム制御パラメータを算出する。
PTZカメラ100のカメラ制御部225は、外部装置120のカメラ制御パラメータ算出部312が算出したズーム制御パラメータをPTZカメラ100に設定し、このズーム制御パラメータを適用した画像撮影を実行させる。
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
これらの実施例を実行可能としたPTZカメラ100と外部装置120の構成例を示す図である。
その他の構成は、図27に示す構成と同様である。
図28に示す外部装置120は、このような事態の発生を防止する構成を有し、PTZカメラ100と外部装置120間の通信遅延時間に応じて撮像比率を変更することを可能とした構成である。
PTZカメラ100の撮影画像(動画像)のフレームレートは予め規定されており、外部装置120の通信遅延時間算出部313は、例えば入力部301がPTZカメラ100から受信する画像フレームの受信タイミングを解析してPTZカメラ100と外部装置120間の通信遅延時間を算出する。
(実施例2)カメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
(実施例3)注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じて撮像比率を変更する実施例
また、上記(実施例3)に従った処理を実行する場合は、図21、図22に示すフローチャートに従った処理を実行して最適撮像比率を算出する。
その後の処理は、図27を参照して説明した処理と同様である。
すなわち、(実施例2)において説明したように、PTZカメラ100と外部装置120間の通信遅延時間に応じた最適撮像比率を算出し、算出した最適撮像比率での画像撮影を行うことが可能となる。
また、(実施例3)において説明したように、注目被写体の速度と加速度、およびカメラと外部装置間の通信遅延時間に応じた最適撮像比率を算出し、算出した最適撮像比率での画像撮影を行うことが可能となる。
次に、上述した実施例に従った処理を実行する画像処理装置のハードウェア構成例について、図29を参照して説明する。
図29に示すハードウェアは、例えば先に図20~図23を参照して説明したカメラや外部装置のハードウェア構成の一例である。
図29に示すハードウェア構成について説明する。
以上、特定の実施例を参照しながら、本開示の実施例について詳解してきた。しかしながら、本開示の要旨を逸脱しない範囲で当業者が実施例の修正や代用を成し得ることは自明である。すなわち、例示という形態で本発明を開示してきたのであり、限定的に解釈されるべきではない。本開示の要旨を判断するためには、特許請求の範囲の欄を参酌すべきである。
(1) カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出部と、
前記切り出し領域算出部が算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行部と、
前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出部と、
算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出部を有し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理装置。
パン、および、チルト、およびズーム処理が可能なPTZカメラであり、
前記カメラ制御パラメータ算出部は、
前記切り出し画像生成用撮像比率から算出される前記カメラの撮像領域サイズに従った画像を撮影させるためのズーム制御パラメータを算出する(1)に記載の画像処理装置。
前記注目被写体の動きを解析する注目被写体動き解析部を有し、
前記撮像比率算出部は、
前記注目被写体動き解析部の解析結果を入力し、
前記注目被写体の速度、または加速度の少なくともいずれかに応じた切り出し画像生成用撮像比率を算出する(1)または(2)に記載の画像処理装置。
前記注目被写体の速度が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記注目被写体の速度が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する(3)に記載の画像処理装置。
前記注目被写体の加速度が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記注目被写体の加速度が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する(3)または(4)に記載の画像処理装置。
前記注目被写体の速度、または加速度の少なくともいずれかに応じた切り出し画像生成用撮像比率を、予め規定した許容最小撮像比率と許容最大撮像比率の間の値として算出する(3)~(5)いずれかに記載の画像処理装置。
前記切り出し画像に含まれる許容最小画素数に応じて決定する撮像比率である(6)に記載の画像処理装置。
注目被写体速度と切り出し画像生成用撮像比率との対応データを用いて、前記切り出し画像生成用撮像比率を算出する(3)~(7)いずれかに記載の画像処理装置。
注目被写体加速度と切り出し画像生成用撮像比率との対応データを用いて、前記切り出し画像生成用撮像比率を算出する(3)~(8)いずれかに記載の画像処理装置。
前記注目被写体の速度から算出した速度対応撮像比率と、
前記注目被写体の加速度から算出した加速度対応撮像比率を比較し、
より大きな値を持つ撮像比率を最終的な切り出し画像生成用撮像比率として決定する(3)~(9)いずれかに記載の画像処理装置。
前記画像処理装置は、
前記カメラと前記画像処理装置間の通信遅延時間を算出する通信遅延時間算出部を有し、
前記撮像比率算出部は、
前記通信遅延時間算出部が算出した前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を算出する(1)~(10)いずれかに記載の画像処理装置。
前記カメラと前記画像処理装置間の通信遅延時間が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記カメラと前記画像処理装置間の通信遅延時間が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する(11)に記載の画像処理装置。
前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を、予め規定した許容最小撮像比率と許容最大撮像比率の間の値として算出する(11)または(12)に記載の画像処理装置。
前記カメラと前記画像処理装置間の通信遅延時間と撮像比率補正係数との対応データを用いて前記切り出し画像生成用撮像比率を算出する(11)~(13)いずれかに記載の画像処理装置。
前記画像処理装置は、
前記注目被写体の動きを解析する注目被写体動き解析部と、
前記カメラと前記画像処理装置間の通信遅延時間を算出する通信遅延時間算出部を有し、
前記撮像比率算出部は、
前記注目被写体動き解析部の解析結果と、
前記通信遅延時間算出部が算出した前記カメラと前記画像処理装置間の通信遅延時間を入力し、
前記注目被写体の速度と加速度、および前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を算出する(1)~(16)いずれかに記載の画像処理装置。
切り出し領域算出部が、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出ステップと、
切り出し実行部が、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行ステップと、
撮像比率算出部が、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出ステップと、
カメラ制御パラメータ算出部が、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出ステップを実行し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理方法。
切り出し領域算出部に、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出させる切り出し領域算出ステップと、
切り出し実行部に、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成させる切り出し実行ステップと、
撮像比率算出部に、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出させる切り出し画像生成用撮像比率算出ステップと、
カメラ制御パラメータ算出部に、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出させるカメラ制御パラメータ算出ステップを実行させ、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させるプログラム。
具体的には、例えば、PTZカメラの撮影画像から注目被写体を含む画像切り出し領域を算出し、算出した領域の画像を切り出して切り出し画像を生成する構成において、注目被写体を含む切り出し画像生成処理をより確実に実行させるための指標値として、切り出し画像に対するカメラの撮像領域のサイズ比率である最適撮像比率(切り出し画像生成用撮像比率)を算出する。さらに最適撮像比率から算出されるカメラの撮像領域サイズに従った画像を撮影させるためのズームパラメータを算出して、算出パラメータを適用した画像撮影をPTZカメラに実行させる。
本構成により、PTZカメラの撮影画像から注目被写体を含む切り出し画像生成処理をより確実に実行させるための指標値である最適撮像比率(切り出し画像生成用撮像比率)を算出する装置、方法が実現される。
20 撮影画像
21 注目被写体
22 撮像領域
23 切り出し領域
30 外部装置
100 PTZカメラ
201 撮像部
202 画像解析部
203 切り出し領域算出部
204 注目被写体動き(速度、加速度)解析部
205 最適撮像比率算出部
206 切り出し実行部
207 出力部
208 記録処理部
209 記録メディア
211 最適撮像領域決定部
212 カメラ制御パラメータ算出部
213 カメラ制御部
221 撮像部
222 出力部
223 記録処理部
224 記録メディア
225 カメラ制御部
301 入力部
302 画像解析部
303 切り出し領域算出部
304 注目被写体動き(速度、加速度)解析部
305 最適撮像比率算出部
306 切り出し実行部
307 出力部
308 記録処理部
309 記録メディア
311 最適撮像領域決定部
312 カメラ制御パラメータ算出部
313 通信遅延時間算出部
701 CPU
702 ROM
703 RAM
704 バス
705 入出力インタフェース
706 入力部
707 出力部
708 記憶部
709 通信部
710 ドライブ
711 リムーバブルメディア
Claims (19)
- カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出部と、
前記切り出し領域算出部が算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行部と、
前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出部と、
算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出部を有し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理装置。 - 前記カメラは、
パン、および、チルト、およびズーム処理が可能なPTZカメラであり、
前記カメラ制御パラメータ算出部は、
前記切り出し画像生成用撮像比率から算出される前記カメラの撮像領域サイズに従った画像を撮影させるためのズーム制御パラメータを算出する請求項1に記載の画像処理装置。 - 前記画像処理装置は、
前記注目被写体の動きを解析する注目被写体動き解析部を有し、
前記撮像比率算出部は、
前記注目被写体動き解析部の解析結果を入力し、
前記注目被写体の速度、または加速度の少なくともいずれかに応じた切り出し画像生成用撮像比率を算出する請求項1に記載の画像処理装置。 - 前記撮像比率算出部は、
前記注目被写体の速度が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記注目被写体の速度が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する請求項3に記載の画像処理装置。 - 前記撮像比率算出部は、
前記注目被写体の加速度が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記注目被写体の加速度が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する請求項3に記載の画像処理装置。 - 前記撮像比率算出部は、
前記注目被写体の速度、または加速度の少なくともいずれかに応じた切り出し画像生成用撮像比率を、予め規定した許容最小撮像比率と許容最大撮像比率の間の値として算出する請求項3に記載の画像処理装置。 - 前記許容最大撮像比率は、
前記切り出し画像に含まれる許容最小画素数に応じて決定する撮像比率である請求項6に記載の画像処理装置。 - 前記撮像比率算出部は、
注目被写体速度と切り出し画像生成用撮像比率との対応データを用いて、前記切り出し画像生成用撮像比率を算出する請求項3に記載の画像処理装置。 - 前記撮像比率算出部は、
注目被写体加速度と切り出し画像生成用撮像比率との対応データを用いて、前記切り出し画像生成用撮像比率を算出する請求項3に記載の画像処理装置。 - 前記撮像比率算出部は、
前記注目被写体の速度から算出した速度対応撮像比率と、
前記注目被写体の加速度から算出した加速度対応撮像比率を比較し、
より大きな値を持つ撮像比率を最終的な切り出し画像生成用撮像比率として決定する請求項3に記載の画像処理装置。 - 前記画像処理装置は、前記カメラと通信可能な外部装置であり、
前記画像処理装置は、
前記カメラと前記画像処理装置間の通信遅延時間を算出する通信遅延時間算出部を有し、
前記撮像比率算出部は、
前記通信遅延時間算出部が算出した前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を算出する請求項1に記載の画像処理装置。 - 前記撮像比率算出部は、
前記カメラと前記画像処理装置間の通信遅延時間が大きいほど、前記切り出し画像生成用撮像比率を大きな値として算出し、
前記カメラ制御パラメータ算出部は、
前記カメラと前記画像処理装置間の通信遅延時間が大きいほど、前記カメラの撮像領域を大きくするズーム制御パラメータを算出する請求項11に記載の画像処理装置。 - 前記撮像比率算出部は、
前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を、予め規定した許容最小撮像比率と許容最大撮像比率の間の値として算出する請求項11に記載の画像処理装置。 - 前記撮像比率算出部は、
前記カメラと前記画像処理装置間の通信遅延時間と撮像比率補正係数との対応データを用いて前記切り出し画像生成用撮像比率を算出する請求項11に記載の画像処理装置。 - 前記撮像比率補正係数は、予め規定した許容最小撮像比率に乗算して切り出し画像生成用撮像比率を算出するための乗算係数である請求項14に記載の画像処理装置。
- 前記撮像比率補正係数は、前記注目被写体の動きに応じて算出される被写体動き対応撮像比率に乗算して最終的な切り出し画像生成用撮像比率を算出するための乗算係数である請求項14に記載の画像処理装置。
- 前記画像処理装置は、前記カメラと通信可能な外部装置であり、
前記画像処理装置は、
前記注目被写体の動きを解析する注目被写体動き解析部と、
前記カメラと前記画像処理装置間の通信遅延時間を算出する通信遅延時間算出部を有し、
前記撮像比率算出部は、
前記注目被写体動き解析部の解析結果と、
前記通信遅延時間算出部が算出した前記カメラと前記画像処理装置間の通信遅延時間を入力し、
前記注目被写体の速度と加速度、および前記カメラと前記画像処理装置間の通信遅延時間に応じた切り出し画像生成用撮像比率を算出する請求項1に記載の画像処理装置。 - 画像処理装置において実行する画像処理方法であり、
切り出し領域算出部が、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出する切り出し領域算出ステップと、
切り出し実行部が、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成する切り出し実行ステップと、
撮像比率算出部が、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出する撮像比率算出ステップと、
カメラ制御パラメータ算出部が、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出するカメラ制御パラメータ算出ステップを実行し、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させる画像処理方法。 - 画像処理装置において画像処理を実行させるプログラムであり、
切り出し領域算出部に、カメラの撮影画像から注目被写体を含む画像領域を画像切り出し領域として算出させる切り出し領域算出ステップと、
切り出し実行部に、前記切り出し領域算出ステップにおいて算出した画像切り出し領域の画像を切り出して、切り出し画像を生成させる切り出し実行ステップと、
撮像比率算出部に、前記注目被写体を含む切り出し画像生成処理を実行させるための指標値として、前記切り出し画像のサイズと、前記カメラの撮影画像の画像全体領域に相当する撮像領域のサイズとのサイズ比率である切り出し画像生成用撮像比率を算出させる切り出し画像生成用撮像比率算出ステップと、
カメラ制御パラメータ算出部に、算出した前記切り出し画像生成用撮像比率に基づいて決定される撮像領域サイズに従った画像を前記カメラに撮影させるためのカメラ制御パラメータを算出させるカメラ制御パラメータ算出ステップを実行させ、
前記カメラ制御パラメータ算出部が算出したカメラ制御パラメータを適用した画像撮影を前記カメラに実行させるプログラム。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202380029302.9A CN118985134A (zh) | 2022-03-31 | 2023-02-24 | 图像处理装置、图像处理方法和程序 |
| JP2024511491A JPWO2023189081A1 (ja) | 2022-03-31 | 2023-02-24 | |
| US18/848,932 US20250211857A1 (en) | 2022-03-31 | 2023-02-24 | Image processing apparatus, image processing method, and program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022-059634 | 2022-03-31 | ||
| JP2022059634 | 2022-03-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023189081A1 true WO2023189081A1 (ja) | 2023-10-05 |
Family
ID=88200560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/006809 Ceased WO2023189081A1 (ja) | 2022-03-31 | 2023-02-24 | 画像処理装置、および画像処理方法、並びにプログラム |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20250211857A1 (ja) |
| JP (1) | JPWO2023189081A1 (ja) |
| CN (1) | CN118985134A (ja) |
| WO (1) | WO2023189081A1 (ja) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016163311A (ja) * | 2015-03-05 | 2016-09-05 | ソニー株式会社 | ビデオ処理装置、ビデオ処理システムおよびビデオ処理方法 |
| JP2018057020A (ja) * | 2017-11-14 | 2018-04-05 | オリンパス株式会社 | 撮像装置、撮像方法およびプログラム |
| WO2018155159A1 (ja) * | 2017-02-24 | 2018-08-30 | パナソニックIpマネジメント株式会社 | 遠隔映像出力システム、及び遠隔映像出力装置 |
-
2023
- 2023-02-24 US US18/848,932 patent/US20250211857A1/en active Pending
- 2023-02-24 JP JP2024511491A patent/JPWO2023189081A1/ja active Pending
- 2023-02-24 WO PCT/JP2023/006809 patent/WO2023189081A1/ja not_active Ceased
- 2023-02-24 CN CN202380029302.9A patent/CN118985134A/zh active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016163311A (ja) * | 2015-03-05 | 2016-09-05 | ソニー株式会社 | ビデオ処理装置、ビデオ処理システムおよびビデオ処理方法 |
| WO2018155159A1 (ja) * | 2017-02-24 | 2018-08-30 | パナソニックIpマネジメント株式会社 | 遠隔映像出力システム、及び遠隔映像出力装置 |
| JP2018057020A (ja) * | 2017-11-14 | 2018-04-05 | オリンパス株式会社 | 撮像装置、撮像方法およびプログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118985134A (zh) | 2024-11-19 |
| JPWO2023189081A1 (ja) | 2023-10-05 |
| US20250211857A1 (en) | 2025-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12033082B2 (en) | Maintaining fixed sizes for target objects in frames | |
| JP4678603B2 (ja) | 撮像装置及び撮像方法 | |
| JP4429241B2 (ja) | 画像処理装置及び方法 | |
| JP5592006B2 (ja) | 三次元画像処理 | |
| US20100188511A1 (en) | Imaging apparatus, subject tracking method and storage medium | |
| US20110043639A1 (en) | Image Sensing Apparatus And Image Processing Apparatus | |
| KR20130010875A (ko) | 화상 조정 파라미터를 결정하기 위한 방법 및 카메라 | |
| CN108702456A (zh) | 一种对焦方法、设备及可读存储介质 | |
| JP2013172446A (ja) | 情報処理装置、端末装置、撮像装置、情報処理方法、及び撮像装置における情報提供方法 | |
| JP7324066B2 (ja) | 画像処理装置およびその制御方法、ならびに撮像装置 | |
| US9154693B2 (en) | Photographing control apparatus and photographing control method | |
| JP2019121278A (ja) | 情報処理装置およびその制御方法 | |
| JP2012257173A (ja) | 追尾装置、追尾方法及びプログラム | |
| CN114429191B (zh) | 基于深度学习的电子防抖方法、系统及存储介质 | |
| JP5118590B2 (ja) | 被写体追尾方法及び撮像装置 | |
| CN115037871B (zh) | 控制对焦的方法、装置、电子设备及计算机可读存储介质 | |
| WO2023189081A1 (ja) | 画像処理装置、および画像処理方法、並びにプログラム | |
| JP6261191B2 (ja) | 表示制御装置、表示制御方法、プログラム | |
| US20240070877A1 (en) | Image processing apparatus, method for controlling the same, imaging apparatus, and storage medium | |
| JP7625407B2 (ja) | 情報処理装置及びその制御方法、並びにプログラム | |
| US12141911B2 (en) | Generation apparatus, generation method, and storage medium | |
| JP2024139454A (ja) | 像ぶれ補正装置、撮像装置、及び像ぶれ補正装置の制御方法 | |
| JP4131113B2 (ja) | 画像処理装置と画像処理方法および画像処理プログラム | |
| JP2009181043A (ja) | 映像信号処理装置、画像信号処理方法、プログラム、記録媒体 | |
| Lee | Novel video stabilization for real-time optical character recognition applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23779111 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2024511491 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18848932 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202380029302.9 Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23779111 Country of ref document: EP Kind code of ref document: A1 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18848932 Country of ref document: US |