WO2020094088A1 - Image capturing method, monitoring camera, and monitoring system - Google Patents

Abstract

An image capturing method, a monitoring camera, and a monitoring system. The image capturing method comprises: acquiring a current video frame (S201); determining a face target image in a current video frame during face target detection on the current video frame (S202); analyzing the quality of the face target image to obtain the image quality of the face target image (S203); determining whether the image quality satisfies a preset quality condition (S204); and if yes, uploading the face target image as a captured image to a comparison system (S205). The method can ensure that a comparison result of the comparison system has high accuracy.

Description

Image capturing method, monitoring camera and monitoring system

This application requires the priority of the Chinese patent application submitted to the Chinese Patent Office on November 7, 2018, with the application number 201811321514.1 and the invention titled "An Image Capture Method, Surveillance Camera, and Surveillance System", the entire contents of which are incorporated by reference in In this application.

Technical field

The present application relates to the technical field of video surveillance, in particular to an image capture method, surveillance camera and surveillance system.

Background technique

In order to reduce the social crime rate, a large number of surveillance cameras are installed in all corners of the city. The surveillance camera captures the face object appearing in the scene, and uploads the captured image to the comparison system. The comparison system extracts the face features from the captured image, and extracts the extracted face features and the black list face features Perform a comparison, and if the similarity of the comparison is greater than a certain threshold, an alarm is generated.

In the corresponding video surveillance system, once the surveillance camera detects the face target, it will capture the face target and upload the captured image to the comparison system. However, since the face target is moving, the captured image is likely to appear The face target in occlusion, blur, etc. affects the similarity of the comparison, causing false alarms or false negatives, and the accuracy of the comparison results is low.

Summary of the invention

The purpose of the embodiments of the present application is to provide an image capture method, a monitoring camera, and a monitoring system, so as to ensure that the comparison result of the comparison system has high accuracy. The specific technical solutions are as follows:

In a first aspect, an embodiment of the present application provides an image capture method, which includes:

Collect the current video frame;

Perform face target detection on the current video frame to determine the face target image in the current video frame;

Perform quality analysis on the face target image to obtain the image quality of the face target image;

Determine whether the image quality meets the preset quality conditions;

If satisfied, the face target image is uploaded to the comparison system as a captured image.

Optionally, after the step of determining whether the image quality meets the preset quality condition, the method further includes:

For any face target image, if the image quality of the face target image does not meet the preset quality conditions, the next video frame is obtained as the current video frame in the order of first to last video frames;

Determine the face target image of the same face target in the current video frame and the previous video frame;

Perform a quality analysis on the face target image in the current video frame to obtain the image quality of the face target image;

Return to the step of judging whether the image quality meets the preset quality condition, until the image quality of the face target image in the current video frame meets the preset quality condition, upload the face target image as a captured image to the comparison system.

Optionally, the step of determining the face target image of the same face target in the current video frame and the previous video frame includes:

Perform face target detection on the current video frame to determine the face target frame in the current video frame;

Match the face target frame in the current video frame with each face target frame in the previous video frame;

If the matching degree reaches the preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;

It is determined that the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.

Optionally, after the step of uploading the face target image as a captured image to the comparison system, the method further includes:

For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;

If it is better, the face target image and image quality of the face target in the current video frame are cached;

After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image.

Optionally, the steps of performing quality analysis on the face target image to obtain the image quality of the face target image include:

Obtain the face target quality parameters of the face target image, where the face target quality parameters include at least one or more of the degree of face occlusion, face clarity, and posture;

According to the face target quality parameter, the image quality of the face target image is determined.

Optionally, the image quality includes an image quality score value;

The steps of performing quality analysis on the face target image to obtain the image quality of the face target image include:

Perform a quality score on the face target image to obtain the image quality score value of the face target image;

The steps to determine whether the image quality meets the preset quality conditions include:

Determine whether the image quality score is greater than the preset quality threshold;

If it is greater, it is determined that the image quality meets the preset quality conditions;

If it is not greater, it is determined that the image quality does not satisfy the preset quality condition.

In a second aspect, an embodiment of the present application provides a surveillance camera, including a surveillance camera, a processor, and a memory, where,

Surveillance camera, used to collect the current video frame;

Memory, used to store computer programs;

The processor, when used to execute the computer program stored on the memory, implements the following steps:

Perform face target detection on the current video frame to determine the face target image in the current video frame;

Perform quality analysis on the face target image to obtain the image quality of the face target image;

Determine whether the image quality meets the preset quality conditions;

If satisfied, the face target image is uploaded to the comparison system as a captured image.

Optionally, when the processor executes the computer program stored on the memory, the following steps are also implemented:

For any face target image, if the image quality of the face target image does not meet the preset quality conditions, the next video frame is obtained as the current video frame in the order of first to last video frames;

Determine the face target image of the same face target in the current video frame and the previous video frame;

Perform a quality analysis on the face target image in the current video frame to obtain the image quality of the face target image;

Return to the step of judging whether the image quality meets the preset quality condition, until the image quality of the face target image in the current video frame meets the preset quality condition, upload the face target image as a captured image to the comparison system.

Optionally, when the processor implements the step of determining the face target image of the same face target in the current video frame and the previous video frame, the specific steps are as follows:

Perform face target detection on the current video frame to determine the face target frame in the current video frame;

Match the face target frame in the current video frame with each face target frame in the previous video frame;

If the matching degree reaches the preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;

It is determined that the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.

Optionally, when the processor executes the computer program stored on the memory, the following steps are also implemented:

For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;

If it is better, the face target image and image quality of the face target in the current video frame are cached;

After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image.

Optionally, when the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it specifically implements the following steps:

Obtain the face target quality parameters of the face target image, where the face target quality parameters include at least one or more of the degree of face occlusion, face clarity, and posture;

According to the face target quality parameter, the image quality of the face target image is determined.

Optionally, the image quality includes an image quality score value;

When the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it specifically implements the following steps:

Perform a quality score on the face target image to obtain the image quality score value of the face target image;

When the processor implements the step of judging whether the image quality meets the preset quality condition, it specifically implements the following steps:

Determine whether the image quality score is greater than the preset quality threshold;

If it is greater, it is determined that the image quality meets the preset quality conditions;

If it is not greater, it is determined that the image quality does not satisfy the preset quality condition.

In a third aspect, an embodiment of the present application provides a machine-readable storage medium in which a computer program is stored. When the computer program is executed by a processor, the image capture method provided in the first aspect of the embodiment of the present application is implemented .

According to a fourth aspect, an embodiment of the present application provides an application program for execution at runtime: the image capturing method provided in the first aspect of the embodiment of the present application.

In a fifth aspect, an embodiment of the present application provides a monitoring system, including a monitoring camera and a comparison system;

Surveillance camera, used to collect the current video frame; perform face target detection on the current video frame to determine the face target image in the current video frame; perform quality analysis on the face target image to obtain the image quality of the face target image; Whether the image quality meets the preset quality conditions; if it meets, upload the face target image as a captured image to the comparison system;

The comparison system is used to compare and alarm the captured images.

An image capturing method, a monitoring camera and a monitoring system provided by the embodiments of the present application, the monitoring camera collects the current video frame, performs face target detection on the current video frame, and determines the face target image in the current video frame. The target image is subjected to quality analysis to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

BRIEF DESCRIPTION

In order to more clearly explain the embodiments of the present application and the technical solutions of the prior art, the following briefly introduces the drawings required in the embodiments and the prior art. Obviously, the drawings in the following description are only For some embodiments of the application, for those of ordinary skill in the art, without paying any creative labor, other drawings may be obtained based on these drawings.

FIG. 1 is a schematic diagram of an operation process of a monitoring system according to an embodiment of this application;

2 is a schematic flowchart of an image capture method according to an embodiment of the present application;

3 is an example diagram of capturing a face target image according to an embodiment of the present application;

4 is a schematic structural diagram of a surveillance camera according to an embodiment of this application;

5 is a schematic structural diagram of a monitoring system according to an embodiment of this application.

detailed description

In order to make the purpose, technical solutions and advantages of the present application more clear, the following describes the present application in further detail with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

In practical applications, the monitoring system mainly captures, compares and alarms face targets. The monitoring system includes a surveillance camera and a comparison system. The comparison system can be a background server, which is mainly used to realize feature extraction, face comparison and alarm.

The operation process of the monitoring system is shown in Figure 1. The monitoring camera collects video data, captures the face target image from the video data through the face capture algorithm, and the monitoring camera transmits the captured face target image to the comparison system. The system extracts the face features of the face target image, compares the extracted face features with the face features of all the people in the database, and if the similarity is higher than the preset threshold, an alarm is generated.

In the surveillance camera and the comparison system, the captured face target image is mainly transmitted. Therefore, the quality and real-time performance of the face target image seriously affect the performance and real-time performance of the comparison system, that is, monitoring The image capture method performed by the camera is the key to ensuring the performance and real-time performance of the comparison system.

Therefore, in order to ensure that the comparison result of the comparison system has high accuracy, the embodiments of the present application provide an image capture method, a monitoring camera, a machine-readable storage medium, and a monitoring system.

In the following, the image capture method provided by the embodiments of the present application is first introduced.

The execution subject of the image capture method provided in the embodiments of the present application may be a surveillance camera (for example, a smart camera, a network camera, etc.) in the surveillance system, and the surveillance camera may include at least a surveillance camera and a processor equipped with a core processing chip . The method for implementing the image capturing method provided by the embodiments of the present application may be at least one method of software, hardware circuits, and logic circuits provided in the monitoring camera.

As shown in FIG. 2, an image capture method provided by an embodiment of the present application may include the following steps:

S201: Collect the current video frame.

Surveillance cameras can be installed in all corners of the city, for example, community entrances, intersections, parks, stadiums, etc. Here, there is no specific requirement for the specific location, angle and resolution of the surveillance camera, which can meet the coverage. As long as possible, the requirements for capturing the face target clearly.

The surveillance camera can shoot the surveillance scene in real time to obtain the video data of the surveillance scene, and the video data includes the video frames of each frame and the time stamp of each video frame collected. In order to ensure the real-time nature of the face target image, the current video frame collected needs to be processed.

S202: Perform face target detection on the current video frame to determine the face target image in the current video frame.

You can use the preset target detection algorithm to detect the face of the current video frame. The preset target detection algorithm can be a traditional feature matching algorithm, which can determine the current video frame by face features such as eyes, nose, mouth, ears, etc. Whether the target in is a face target, if it is a face target, a certain area around the face target is divided into a face target frame, and the image in the face target frame or the image within a certain range of the face target frame is a person Face target image; the preset target detection algorithm can also be a more popular intelligent detection algorithm, such as deep neural network. The network model of deep neural network can be obtained by training a large number of face images, by inputting the current video frame into the depth The neural network can obtain the interest area of the face target in the current video frame, and the image in the interest area of the face target or the image within a certain range of the interest area of the face target is the face target image. Of course, other methods that can detect the face target in the video frame also belong to the protection scope of the embodiments of the present application, and details are not repeated here.

S203. Perform quality analysis on the face target image to obtain the image quality of the face target image.

There are many factors that affect the image quality of the face target image, such as the degree to which the face target is blocked in the face target image, the imaging clarity of the face target in the face target image, and the pose of the face target in the face target image and many more. The less the face target is occluded in the face target image, the higher the image quality, the clearer the face target is imaged in the face target image, the higher the image quality, and the more positive the face target in the face target image More often the image quality is higher and so on. Of course, there are many factors that affect the image quality of the face target image, such as contrast, brightness, and so on, which are not listed here.

You can consider the above factors comprehensively and assign a certain image quality score value to the face target image by weighting; you can also consider only one or some of the factors set by the analysis algorithm to assign a certain image quality score to the face target image value. The preset quality analysis algorithm can also assign, for example, good, good, medium, and poor evaluation results to the face target image.

Optionally, S203 may specifically be:

Obtain the face target quality parameters of the face target image, where the face target quality parameters include at least one or more of the degree of face occlusion, face clarity, and posture; according to the face target quality parameters, determine the person The image quality of the face target image.

The face target quality parameter refers to the parameter that affects the image quality of the face target image, mainly including the face target's posture, degree of occlusion, and imaging clarity. When performing image quality analysis on the face target image, you can obtain the person The facial target quality parameters such as the posture information, degree of occlusion and sharpness of the facial target are based on the comprehensive consideration of the effects of different facial target quality parameters on the image quality to obtain the image quality of the facial target image. For example, in the face target image in the face target frame in the current video frame, the face target A is completely frontal, the face is occluded by 1/10, and the sharpness is very high, it can be determined that the image quality of the face target image is excellent Or, quantify the image quality and assign an image quality score of 9.

Optionally, the image quality may include an image quality score value.

Correspondingly, S203 can specifically be:

The quality score of the face target image is obtained to obtain the image quality score value of the face target image.

In order to facilitate the processing of the monitoring camera, the image quality can be expressed by a quantized image quality score value. The quality score algorithm is used to score the face target image to obtain a quantized image quality score value. Of course, the image quality can also be expressed as the evaluation results of excellent, good, medium, and poor.

S204: Determine whether the image quality meets the preset quality condition.

The preset quality condition is a condition set to determine whether the image quality of the face target image can meet the requirement of higher image quality. If the image quality can meet the preset quality condition, it means that the image quality of the face target image is higher. If it cannot be satisfied, it means that the image quality of the face target image in the current video frame cannot meet the requirements.

Optionally, for the case where the image quality includes an image quality score value, S204 may specifically be:

It is determined whether the image quality score value is greater than the preset quality threshold; if it is greater, it is determined that the image quality meets the preset quality condition; if not, it is determined that the image quality does not meet the preset quality condition.

For the quantized image quality, the preset quality condition may be greater than the preset quality threshold, for example, the preset quality threshold is 8 points, if the quantized image quality score value is greater than 8 points, it means that the face target image can achieve a better image quality High requirements, if the image quality score value is not greater than 8, it means that the face target image can not meet the requirements.

Of course, the preset quality condition may also be a preset degree of image quality evaluation. For example, the preset quality condition may be that the image quality is good. If the image quality of the face target image reaches good and above, it means that the face target image It can meet the requirement of high image quality. If the image quality of the face target image is not good, it means that the face target image cannot meet the requirements.

Optionally, after S204, the image capture method provided by the embodiment of the present application may further perform the following steps:

In the first step, for any face target image, if the image quality of the face target image does not meet the preset quality condition, the next video frame is obtained as the current video frame in the order of the video frames from first to last.

The current video frame may include multiple face targets. For a face target image of any face target, if the image quality does not meet the preset quality conditions, it means that the image quality of the face target image of the face target cannot meet the requirements In order to find the face target image with the image quality that meets the requirements as soon as possible, the next video frame can be obtained in sequence, and the next video frame is used as the current video frame to determine the face target image of the same face target in the video frame Whether the quality of the image can meet the requirements.

The second step is to determine the face target image of the same face target in the current video frame and the previous video frame.

The way to determine the face target image of the same face target in the current video frame and the previous video frame can be using an intelligent target tracking algorithm to track the same face target, or it can be used in the current video frame as in S202 The target detection algorithm performs face target detection, and then determines the target frame matching method.

The third step is to analyze the quality of the face target image in the current video frame to obtain the image quality of the face target image.

The fourth step is to return to S204 until the image quality of the face target image in the current video frame meets the preset quality condition, and upload the face target image as a captured image to the comparison system.

Perform quality analysis and judgment on the face target image in the new current video frame. If the image quality does not meet the preset quality conditions, obtain the next video frame to determine the face target image, image quality analysis, and judgment Processing, until the image quality of the face target image in a certain video frame can meet the preset quality conditions, immediately capture the face target to ensure that the first time when the face target image with the required image quality meets the requirements Upload the captured image to ensure the real-time nature of the facial feature comparison in the comparison system.

Optionally, the step of determining the face target image of the same face target in the current video frame and the previous video frame may specifically be:

Perform face target detection on the current video frame to determine the face target frame in the current video frame;

Match the face target frame in the current video frame with each face target frame in the previous video frame;

If the matching degree reaches the preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;

It is determined that the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.

The method of determining the face target image of the same face target in the current video frame and the previous video frame may be to use the target detection algorithm as in S202 for the current video frame to detect the face target, and then match through the face target frame The way is determined.

Comprehensively consider the matching conditions, such as whether the size of the face target frame is the same, whether the position offset is less than a certain threshold, whether the motion trajectory meets a certain smoothness, etc. Based on these matching conditions, a certain amount can be allocated between the two face target frames Matching degree, when the matching degree reaches the preset matching degree threshold, it means that the two face target frames are the same as the face target frame of the same face target. The greater the matching degree, the two face target frames are the same The possibility of the face target frame of the face target is greater. Therefore, the face target frame in the current video frame can be assigned the same target frame identifier as the face target frame with the highest matching degree in the previous video. If the target frame identification is the same, it means that the face targets in the face target image are the same target, and different face target frames have different target frame identifications, which are used to distinguish different face targets.

S205: If the image quality meets the preset quality condition, upload the face target image as a captured image to the comparison system.

If the image quality of the face target image satisfies the preset quality condition, it means that the image quality of the face target image is high. At this time, the face target can be captured immediately, and the face target image can be uploaded to the comparison system as a captured image , The captured image compared by the comparison system has a higher image quality, and the captured image received by the comparison system with the higher image quality is uploaded immediately after being captured by the surveillance camera, and has a better quality real-time.

Optionally, after S205, the image capturing method provided by the embodiment of the present application may further perform the following steps:

For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;

If it is better, the face target image and image quality of the face target in the current video frame are cached;

After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image.

In order to ensure that the comparison system can have a more accurate comparison result when performing the comparison, the surveillance camera sequentially analyzes the quality of the face target image of the face target in each video frame. First, the first video frame and The image quality of the face target image of the face target in the first video frame is cached. If the image quality of the face target image of the face target in the subsequent video frame is better than the cached image quality, the better Image quality and face target image buffering, overwriting the face target image and image quality of the face target that have been cached. After the face target disappears, the face target image with the best image quality of the face target is cached, and the face target image can be uploaded as a captured image.

The way to determine the end of the tracking of the face target may be that the matching degree of the continuous multiple frames to the face target is very low, then the tracking of the face target may be determined to end, or, through the target tracking algorithm, the tracking of the face target may be determined If it is lost, that is, a certain face target cannot be tracked in multiple consecutive frames, then it can be determined that the tracking of the face target ends.

The comparison system can finally calibrate the alarm with the comparison result of the captured image with the best image quality, so as to ensure that the final alarm has high accuracy. In the whole process, the surveillance camera only needs to transmit a small number of captured images (up to two), which can not only ensure high real-time performance, but also ensure the accuracy of the comparison results, and save bandwidth resources.

Taking a certain face target as an example, as shown in FIG. 3, the surveillance camera first collects the first frame, detects the face target image of the face target in the first frame, and performs quality analysis on the face target image. If the quality score value is less than the preset quality threshold, the surveillance camera next collects the second frame, detects the face target image of the face target in the second frame again, and performs image quality analysis on the face target image to obtain the image quality The score value is still less than the preset quality threshold. Continue to collect frames 3, 4, and 5 in sequence. The image quality of the obtained face target image is less than the preset quality threshold. Until frame 6, the obtained person If the image quality of the face target image is greater than the preset quality threshold, the face target image as a captured image will be uploaded to the comparison system for processing. When the target tracking ends, for example, at the 50th frame, it is determined that the target tracking ends. The frame with the best cached image quality is not the 6th frame, but the 30th frame, then the face target in the 30th frame is determined. The face target image is uploaded to the comparison system as a captured image.

Applying this example, the surveillance camera collects the current video frame, performs face target detection on the current video frame, determines the face target image in the current video frame, and performs quality analysis on the face target image to obtain the image of the face target image Quality, if the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

Corresponding to the above method embodiment, an embodiment of the present application provides a surveillance camera. As shown in FIG. 4, it includes a surveillance camera 401, a processor 402, and a memory 403, where,

Surveillance camera 401, used to collect the current video frame;

Memory 403, used to store computer programs;

The processor 402 is configured to execute the following steps when executing the computer program stored on the memory 403:

Perform face target detection on the current video frame to determine the face target image in the current video frame;

Perform quality analysis on the face target image to obtain the image quality of the face target image;

Determine whether the image quality meets the preset quality conditions;

If satisfied, the face target image is uploaded to the comparison system as a captured image.

Optionally, when the processor 402 executes the computer program stored in the memory 403, the following steps may also be implemented:

For any face target image, if the image quality of the face target image does not meet the preset quality conditions, the next video frame is obtained as the current video frame in the order of first to last video frames;

Determine the face target image of the same face target in the current video frame and the previous video frame;

Perform a quality analysis on the face target image in the current video frame to obtain the image quality of the face target image;

Return to the step of judging whether the image quality meets the preset quality condition until the image quality of the face target image in the current video frame meets the preset quality condition, upload the face target image as a captured image to the comparison system.

Optionally, when the processor 402 implements the step of determining the face target image of the same face target in the current video frame and the previous video frame, it may specifically implement the following steps:

Perform face target detection on the current video frame to determine the face target frame in the current video frame;

Match the face target frame in the current video frame with each face target frame in the previous video frame;

If the matching degree reaches the preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;

It is determined that the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.

Optionally, when the processor 402 executes the computer program stored on the memory 403, the following steps may also be implemented:

For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;

If it is better, the face target image and image quality of the face target in the current video frame are cached;

After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image.

Optionally, when the processor 402 implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it may specifically implement the following steps:

Obtain the face target quality parameters of the face target image, where the face target quality parameters include at least one or more of the degree of face occlusion, face clarity, and posture;

According to the face target quality parameter, the image quality of the face target image is determined.

Optionally, the image quality includes an image quality score value;

When the processor 402 implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it may specifically implement the following steps:

Perform a quality score on the face target image to obtain the image quality score of the face target image;

When the processor 402 implements the step of judging whether the image quality meets the preset quality condition, it specifically implements the following steps:

Determine whether the image quality score is greater than the preset quality threshold;

If it is greater, it is determined that the image quality meets the preset quality conditions;

If it is not greater, it is determined that the image quality does not satisfy the preset quality condition.

The above memory may include RAM (Random Access Memory, random access memory), or may include NVM (Non-Volatile Memory, non-volatile memory), for example, at least one disk memory. Optionally, the memory may also be at least one storage device located away from the processor.

The above processor may be a general-purpose processor, including CPU (Central Processing Unit), NP (Network Processor), etc .; it may also be DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

Data can be transmitted between the surveillance camera 401, the processor 402, and the memory 403 through a wired connection or a wireless connection, and the surveillance camera can communicate with the comparison system through a wired communication interface or a wireless communication interface. 4 is only an example of data transmission between the surveillance camera 401, the processor 402, and the memory 403 through the bus, and is not intended as a limitation of a specific connection method.

In this embodiment, the processor of the surveillance camera can read the computer program stored in the memory and run the computer program to realize that the surveillance camera collects the current video frame and performs face target detection on the current video frame to determine Face target image in the current video frame, perform quality analysis on the face target image to obtain the image quality of the face target image, if the image quality meets the preset quality conditions, the face target image is uploaded as a captured image to the comparison To the system. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

In addition, embodiments of the present application also provide a machine-readable storage medium, and the machine-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the image capturing method provided by the embodiment of the present application All steps.

In this embodiment, the machine-readable storage medium stores a computer program that executes the image capture method provided by the embodiments of the present application at runtime, so it can be achieved that the surveillance camera collects the current video frame and performs face target detection on the current video frame , Determine the face target image in the current video frame, and perform quality analysis on the face target image to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, use the face target image as the captured image Upload to the comparison system. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

An embodiment of the present application also provides an application program for executing at run time: all steps of the image capturing method provided by the embodiment of the present application.

In the embodiment of the present application, the application program executes the image capturing method provided in the embodiment of the present application when it is running, so that it can realize that: the monitoring camera collects the current video frame, performs face target detection on the current video frame, and determines The face target image is subjected to quality analysis to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

An embodiment of the present application also provides a monitoring system. As shown in FIG. 5, the monitoring system may include a monitoring camera 510 and a comparison system 520;

The surveillance camera 510 is used to collect the current video frame; perform face target detection on the current video frame to determine the face target image in the current video frame; perform quality analysis on the face target image to obtain the image quality of the face target image; Determine whether the image quality meets the preset quality conditions; if it meets, upload the face target image as a captured image to the comparison system 520;

The comparison system 520 is used for comparing and alarming the captured images.

The monitoring camera 510 can also be used to implement all the steps provided in the above method embodiments, and no more details are provided here.

The comparison system 520 compares and alarms the captured images, which may specifically include: extracting the captured images, and comparing the extracted facial features with the facial features in the blacklist, if the similarity of the comparison is greater than a certain Threshold, then alarm.

Applying this embodiment, the monitoring camera collects the current video frame, performs face target detection on the current video frame, determines the face target image in the current video frame, and performs quality analysis on the face target image to obtain the image of the face target image Quality, if the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison alarm. The image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system The results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

For the embodiments of the surveillance camera, the machine-readable storage medium, and the surveillance system, since the content of the methods involved is basically similar to the foregoing method embodiments, the description is relatively simple. For the related parts, refer to the partial description of the method embodiments. can.

For the surveillance camera, machine-readable storage medium, and application program embodiments, because the content of the methods involved is basically similar to the foregoing method embodiments, the description is relatively simple. For the related parts, refer to the section of the method embodiments. can.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations There is any such actual relationship or order. Moreover, the terms "include", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also those not explicitly listed Or other elements that are inherent to this process, method, article, or equipment. Without more restrictions, the element defined by the sentence "include one ..." does not exclude that there are other identical elements in the process, method, article or equipment that includes the element.

The embodiments in this specification are described in a related manner. The same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, monitoring camera, machine-readable storage medium, application program, and monitoring system embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the related parts, refer to the section of the method embodiments. can.

The above are only the preferred embodiments of this application and are not intended to limit this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application should be included in this application Within the scope of protection.

Claims (14)

An image capture method, characterized in that the method includes: Collect the current video frame; Performing face target detection on the current video frame to determine the face target image in the current video frame; Performing quality analysis on the face target image to obtain the image quality of the face target image; Determine whether the image quality meets the preset quality conditions; If satisfied, the face target image is uploaded to the comparison system as a captured image. The method according to claim 1, wherein after the judging whether the image quality satisfies a preset quality condition, the method further comprises: For any face target image, if the image quality of the face target image does not meet the preset quality condition, the next video frame is obtained as the current video frame in the order of first to last video frames; Determining a face target image of the same face target in the current video frame and the previous video frame; Performing quality analysis on the face target image in the current video frame to obtain the image quality of the face target image; Return to performing the step of determining whether the image quality meets the preset quality condition until the image quality of the face target image in the current video frame meets the preset quality condition, upload the face target image as a captured image to Compare systems. The method according to claim 2, wherein the determining the face target image of the same face target in the current video frame and the previous video frame includes: Performing face target detection on the current video frame to determine the face target frame in the current video frame; Matching the face target frames in the current video frame with each face target frame in the previous video frame; If the matching degree reaches a preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree; It is determined that the face target image in the face target frame with the same target frame identifier in the current video frame and the previous video frame is the face target image of the same face target. The method according to claim 1 or 2, wherein after the uploading of the face target image as a captured image to a comparison system, the method further comprises: For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is superior to the cached image quality of the face target image of the face target; If it is better, cache the face target image and image quality of the face target in the current video frame; After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image. The method according to claim 1, wherein the quality analysis of the face target image to obtain the image quality of the face target image includes: Acquiring a face target quality parameter of the face target image, the face target quality parameter includes at least one or more of a degree of face occlusion, face clarity, and posture; The image quality of the face target image is determined according to the face target quality parameter. The method according to claim 1 or 5, wherein the image quality includes an image quality score value; The quality analysis of the face target image to obtain the image quality of the face target image includes: Performing a quality score on the face target image to obtain an image quality score value of the face target image; The judging whether the image quality satisfies the preset quality condition includes: Determine whether the image quality score value is greater than a preset quality threshold; If it is greater, it is determined that the image quality meets the preset quality condition; If it is not greater, it is determined that the image quality does not satisfy the preset quality condition. A surveillance camera is characterized by comprising a surveillance camera, a processor and a memory, wherein, The monitoring camera is used to collect the current video frame; The memory is used to store computer programs; When the processor is used to execute the computer program stored on the memory, the following steps are implemented: Performing face target detection on the current video frame to determine the face target image in the current video frame; Performing quality analysis on the face target image to obtain the image quality of the face target image; Determine whether the image quality meets the preset quality conditions; If satisfied, the face target image is uploaded to the comparison system as a captured image. The surveillance camera according to claim 7, wherein when the processor executes the computer program stored on the memory, the following steps are further implemented: For any face target image, if the image quality of the face target image does not meet the preset quality condition, the next video frame is obtained as the current video frame in the order of first to last video frames; Determining a face target image of the same face target in the current video frame and the previous video frame; Performing quality analysis on the face target image in the current video frame to obtain the image quality of the face target image; Return to the step of determining whether the image quality meets the preset quality condition until the image quality of the face target image in the current video frame meets the preset quality condition, upload the face target image as a captured image to Compare systems. The surveillance camera according to claim 8, characterized in that, when the processor implements the step of determining the face target image of the same face target in the current video frame and the previous video frame, the specific implementation is as follows step: Performing face target detection on the current video frame to determine the face target frame in the current video frame; Matching the face target frames in the current video frame with each face target frame in the previous video frame; If the matching degree reaches a preset matching degree threshold, the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree; It is determined that the face target image in the face target frame with the same target frame identifier in the current video frame and the previous video frame is the face target image of the same face target. The surveillance camera according to claim 7 or 8, wherein when the processor executes the computer program stored on the memory, the following steps are further implemented: For the same face target, determine whether the image quality of the face target image of the face target in the current video frame is superior to the cached image quality of the face target image of the face target; If it is better, cache the face target image and image quality of the face target in the current video frame; After determining that the tracking of the face target ends, the cached face target image of the face target is uploaded to the comparison system as a captured image. The surveillance camera according to claim 7, characterized in that, when the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, the specific implementation is as follows step: Acquiring a face target quality parameter of the face target image, the face target quality parameter includes at least one or more of a degree of face occlusion, face clarity, and posture; The image quality of the face target image is determined according to the face target quality parameter. The surveillance camera according to claim 7 or 11, wherein the image quality includes an image quality score value; When the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it specifically implements the following steps: Performing a quality score on the face target image to obtain an image quality score value of the face target image; When the processor implements the step of judging whether the image quality satisfies the preset quality condition, it specifically implements the following steps: Determine whether the image quality score value is greater than a preset quality threshold; If it is greater, it is determined that the image quality meets the preset quality condition; If it is not greater, it is determined that the image quality does not satisfy the preset quality condition. An application program, which is used to execute at runtime: the method according to any one of claims 1-6. A monitoring system, characterized in that it includes a monitoring camera and a comparison system; The surveillance camera is used to collect the current video frame; perform face target detection on the current video frame to determine the face target image in the current video frame; perform quality analysis on the face target image to obtain all Describe the image quality of the face target image; determine whether the image quality meets the preset quality conditions; if satisfied, upload the face target image as a captured image to the comparison system; The comparison system is used for comparing and alarming the captured images.

Images