JP2020119030A - Information processing apparatus control program, information processing apparatus control method, and information processing apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a control program or the like of an information processing device capable of detecting that a road sign or the like is difficult to be visually recognized by a driver. SOLUTION: A control program of an information processing apparatus has a first image detection function for detecting one or more objects included in an image with the first accuracy, and one or more objects included in the image. , A second image detection function that detects with a second accuracy different from the first accuracy, an image acquisition function that acquires one image, and a first detection result by the first image detection function in one image. Realizes an extraction function that extracts the difference from the second detection result by the second image detection function, and an output function that outputs information about the difference in association with one image when the difference is extracted by the extraction function. Let me. [Selection diagram] Fig. 1

Description

The present invention relates to a control program for an information processing apparatus, a method for controlling the information processing apparatus, and an information processing apparatus, and in particular, a control program for an information processing apparatus used in image detection for detecting one or more objects included in an image. Etc.

The development of technology that supports safe driving of vehicles is remarkable. For example, Patent Document 1 discloses a technique of recognizing a road sign included in an image captured from an image captured by a drive recorder, a smartphone, or the like mounted on a vehicle, and transmitting the recognized content to a driver. ..

Also, in recent years, the accuracy of image recognition and image detection has dramatically improved due to the development of artificial intelligence (AI) and machine learning. Therefore, if high-accuracy image detection is applied to recognition of a road sign like the technique described in Patent Document 1, even if the road sign is difficult to see, the road sign is appropriately recognized and driving is performed. It is possible to tell the person.

JP, 2017-068351, A

As described above, using recent image recognition and image detection technologies, even when the driver cannot see the road sign while driving, such as when the road sign is covered with leaves or facing an angle that is difficult for the driver to see. , A road sign can be detected from an image captured by a drive recorder or the like. Therefore, a problem may occur that the road sign is left in a state where it is difficult for the driver to visually recognize it. However, it is not appropriate from the safety point of view to leave the road sign in such a state that the driver cannot easily see the road sign.

Therefore, the present invention solves the above-mentioned problems, and can detect that an object, such as a road sign, that the user needs to properly visually recognize is in a state in which it is difficult to visually recognize, and the like. I will provide a.

A control program for an information processing apparatus according to an embodiment of the present invention includes a first image detection function for detecting, with a first accuracy, one or more objects included in an image in the information processing apparatus, and a 1 A second image detection function for detecting the above objects with a second accuracy different from the first accuracy, an image acquisition function for acquiring one image, and a first image detection function for one image based on the first image detection function. An extraction function for extracting a difference between the detection result and the second detection result by the second image detection function, and an output function for outputting information regarding the difference in association with one image when the difference is extracted by the extraction function And realize.

In the control program according to the embodiment of the present invention, the first accuracy is higher than a predetermined threshold value indicating a human detection accuracy when the image detection is executed by a human under a predetermined condition, and a second accuracy is set. May be less than or equal to a predetermined threshold.

A control program according to an embodiment of the present invention causes an information processing apparatus to further realize a location information acquisition function of acquiring location information that is information regarding a shooting location of one image, and an output function includes information regarding a difference, The location information of one image may be output.

A control program according to an embodiment of the present invention further causes an information processing device to realize a difference function extracted by an extraction function and a determination function of determining a relationship between a shooting location of one image and an output function. May output information regarding the difference according to the relevance determined by the determination function.

In the control program according to the embodiment of the present invention, the determination function is based on at least one or more characteristics related to a shooting location of one image, which is stored in a predetermined storage unit, and is related to each other. May be determined.

A control program according to an embodiment of the present invention includes a reception function of receiving from a user selection information as to whether or not it is necessary to output information regarding a difference output by an output function to an information processing device, a difference, and selection information. Based on the above, a learning function of learning a feature relating to a shooting location of one image may be further realized.

A control method for an information processing apparatus according to an embodiment of the present invention includes a first image detection unit that detects one or more objects included in an image with a first accuracy, and one or more objects included in the image. An information processing apparatus including a second image detection unit that detects a second accuracy different from the first accuracy includes an image acquisition step of acquiring one image, and a first image detection unit for the first image in the one image. 1) performing an extraction step of extracting a difference between the detection result and the second detection result of the second image detection section, and an output step of outputting information on the difference when the difference is extracted in the extraction step ..

An information processing apparatus according to an embodiment of the present invention includes a first image detection unit that detects one or more objects included in an image with a first accuracy, and one or more objects included in the image as a first image detection unit. A second image detection unit that detects with a second accuracy different from the accuracy, an image acquisition unit that acquires one image, a first detection result by the first image detection unit in one image, and a second image detection An extraction unit that extracts a difference from the second detection result by the unit, and an output unit that outputs information about the difference when the extraction unit extracts the difference.

ADVANTAGE OF THE INVENTION According to this invention, the control program of an information processing apparatus etc. which can detect that the object which a user needs to recognize appropriately are in a state where it is difficult to recognize visually.

1 is a schematic diagram of an image detection system configuration according to an embodiment of the present invention. 1 is an example of a hardware configuration of a server (information processing device) according to an embodiment of the present invention. (A) And (b) is a figure explaining the outline of the image detection system which concerns on one Embodiment of this invention. Both (a) and (b) are examples of screens that display the output result of the image detection system according to the embodiment of the present invention. It is a flowchart of the control method of the server which concerns on one Embodiment of this invention. (A) is an example of an image to be image-detected, and (b) is a table used in the image detection system according to the embodiment of the present invention. 6 is an example of a screen displaying an output result by the image detection system according to the embodiment of the present invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

<System configuration>
FIG. 1 is a diagram showing a configuration example of an image detection system according to an embodiment of the present invention. As shown in FIG. 1, the image detection system 400 includes a server (information processing device) 100 and a communication terminal 200 (200A, 200B) connected to each other via a network 300.

The communication terminal 200 is a communication terminal that includes an image capturing unit and can transmit a captured moving image or still image to the server 100. The image capturing unit may be of any type, such as a camera, a video, a sensor, and a lidar (LiDER), as long as it can capture an image of an object. As an example of the communication terminal 200, FIG. 1 illustrates a smartphone 200A and a drive recorder 200B mounted on a vehicle and recording a moving image captured by the camera 210B, but the communication terminal 200 is not limited to these. Absent. Although only two communication terminals 200 are shown in FIG. 1, more or less communication terminals 200 may be used. In the following description, the smartphone 200A and the drive recorder 200B will be referred to as the communication terminal 200, unless otherwise required to be distinguished.

The server 100 executes image detection for detecting one or more objects from the image captured by the communication terminal 200 (details will be described later). The server 100 may be typically realized on the cloud.

The network 300 plays a role of connecting the server 100 and each communication terminal 200. The network 300 means a communication network that provides a connection path so that data can be transmitted and received between them. The network 300 may include a wireless network or a wired network. Specifically, the network 300 includes a wireless LAN (WLAN), a wide area network (WAN), ISDNs (integrated service digital networks), wireless LANs, LTE (long term evolution), LTE-Advanced, The fourth generation (4G), the fifth generation (5G), CDMA (code division multiple access), and the like. The network 300 is not limited to these examples. For example, the public switched telephone network (PSTN), Bluetooth (registered trademark), optical line, ADSL (Asymmetric Digital Subscriber LINE) line, satellite. It may be a communication network or the like. Further, the network 300 may be a combination of these.

Note that the server 100 and the communication terminal 200 may be any information processing device as long as it is an information processing device that can implement the functions and/or methods described in the present disclosure. For example, examples of these information processing devices include smartphones, mobile phones (feature phones), computers (for example, desktops, laptops, tablets, etc.), server devices, media computer platforms (for example, cables, satellite set-top boxes, digital video). A recorder, etc.), a handheld computing device (eg PDA (Personal Digital Assistant), email client, etc.), a wearable terminal (eg glasses-type device, watch-type device, etc.), another type of computer, or a communication platform. ..

<Hardware configuration>
Prior to the description of FIG. 1, the hardware configuration of the server 100 will be described with reference to FIG. Although shown as the server 100 in FIG. 2, the communication terminal 200 has the same hardware configuration.

The server 100 realizes the functions and methods described in the present embodiment by the cooperation of the processor 101, the memory 102, the storage 103, the input/output interface (I/F) 104, and the communication I/F 105. .. For example, the function or method of the present disclosure is realized by the processor 101 executing an instruction included in a program read into the memory 102.

The processor 101 executes a function and/or a method realized by a code or an instruction included in a program stored in the storage 103. The processor 101 is, for example, a central processing unit (CPU), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), microprocessor (microprocessor), processor core (processor core), multiprocessor (multiprocessor), ASIC (Application- Specific integrated circuit), FPGA (Field Programmable Gate Array), etc., and implemented by a logic circuit (hardware) or dedicated circuit formed in an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)) or the like. Each process disclosed in the embodiment may be realized. Further, these circuits may be realized by one or a plurality of integrated circuits, and the plurality of processes shown in each embodiment may be realized by a single integrated circuit. Further, the LSI may be referred to as VLSI, super LSI, ultra LSI, or the like depending on the degree of integration.

The memory 102 temporarily stores the program loaded from the storage 103 and provides a work area to the processor 101. The memory 102 also temporarily stores various data generated while the processor 101 is executing the program. The memory 102 includes, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), and the like.

The storage 103 stores the program. The storage 103 includes, for example, a HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, and the like.

The communication I/F 105 is implemented as hardware such as a network adapter, communication software, or a combination thereof, and transmits and receives various data via the network 300. The communication may be performed by wire or wireless, and any communication protocol may be used as long as mutual communication can be performed. The communication I/F 105 executes communication with the communication terminal 200, which is another information processing apparatus, via the network 300. The communication I/F 105 transmits various data to another information processing device according to an instruction from the processor 101. Further, the communication I/F 105 receives various data transmitted from another information processing device and transfers the data to the processor 101.

The input/output I/F 104 includes an input device that inputs various operations on the server 100 and an output device that outputs a processing result processed by the server 100. In the input/output I/F 104, an input device and an output device may be integrated, or an input device and an output device may be separated. The input device is realized by any of all types of devices that can receive an input from a user and transmit information related to the input to the processor 101, or a combination thereof. The input device includes, for example, a hardware key such as a touch panel, a touch display, and a keyboard, a pointing device such as a mouse, a camera (operation input via an image), and a microphone (operation input by voice). The output device outputs the processing result processed by the processor 101. The output device includes, for example, a touch panel, a speaker, and the like.

<Functional configuration>
Returning to FIG. 1, the functional configurations of the server 100 and the communication terminal 200 will be described. As illustrated in FIG. 1, the server 100 includes a communication control unit 110, a first image detection unit 121, a second image detection unit 122, an input/output control unit 130, an extraction unit 140, an output unit 150, a determination unit 160, a reception unit. 170, a learning unit 180, and a storage unit 190. Note that the functional units illustrated in FIG. 1 are not essential, and in the embodiments described below, the non-essential functional units may be omitted. Further, the function or processing of each functional unit may be realized by machine learning or AI (Artificial Intelligence) in a feasible range.

The communication control unit 110 controls communication with an external device via the communication I/F 105. That is, the communication control unit 110 transmits the data acquired by the communication with the communication terminal 200 to the first image detection unit 121, the second image detection unit 122, and the storage unit 190, or the data from the functional units. Is transmitted to the communication terminal 200. Therefore, the communication control unit 110 functions as an image acquisition unit that acquires one image captured by the communication terminal 200.

The input/output control unit 130 controls transmission of various types of information with an external device via the input/output I/F 104. For example, the input/output control unit 130 transmits information to each functional unit according to an input instruction from a user (not shown) such as a touch panel, a keyboard, a microphone or the like, and outputs (not shown) such as a touch panel, a monitor or a speaker. Information from each functional unit is transmitted to the device. In addition, one image captured by the communication terminal 200 may be stored in, for example, a memory that can be carried by a user, and the image may be input to the server 100 using the memory as an input device. In such a case, the input/output control unit 130 functions as an image acquisition unit that acquires one image.

The first image detection unit 121 has a first accuracy in image detection for detecting one or more objects included in the image. The second image detection unit 122 detects one or more objects included in the image with a second accuracy different from the first accuracy. The image detection in this embodiment refers to a process of detecting an object included in an image and outputting information about the object. The information about the object may be the category, name, color of the object, the position (coordinates, etc.) of the detected object in the image, and the like. The information about the object may include the meaning of the detected object. For example, when the object is a road sign, the meanings of the road sign may be output such as “no parking” and “pause”. A known image detection technique (image recognition technique) can be used for image detection by the first image detection unit 121 and the second image detection unit 122, and detailed description of algorithms and the like will be omitted.

The first image detection unit 121 and the second image detection unit 122 have different detection accuracy as described above. Here, the detection accuracy is an index according to the correct answer rate as a result of performing image detection on a plurality of images under the same condition. The first image detection unit 121 and the second image detection unit 122 may have different image detection algorithms as long as the detection accuracy is different. When the same algorithm is used in image detection, in order to realize different detection accuracy between the first image detection unit 121 and the second image detection unit 122, the parameters used in the image detection algorithm are set to the first A change may be made between the image detection unit 121 and the second image detection unit 122, or a different version may be used in known application software relating to image detection. In general, the new version has a higher detection accuracy than the old version.

The extraction unit 140 extracts the difference between the first detection result by the first image detection unit 121 and the second detection result by the second image detection unit 122 in one image. When the difference is extracted by the extraction unit 140, the output unit 150 outputs information regarding the difference in association with one image.

Prior to description of other functional units of the server 100, the functional configuration of the communication terminal 200 will be described. As shown in FIG. 1, the communication terminal 200 includes a communication control unit 210, an imaging control unit 220, a position information acquisition unit 230, and a storage unit 240. Note that the function or processing of each functional unit may be realized by machine learning or AI within a feasible range.

The communication control unit 210 executes transmission/reception of various information between the communication terminal 200 and an external device (for example, the server 100) via the network 300. The imaging control unit 220 controls imaging by the imaging unit according to an instruction from the user of the communication terminal 200. The position information acquisition unit 230 has a function of measuring position information of the current position of the communication terminal 200. The position information acquisition unit 230 measures the latitude and longitude of the communication terminal 200 as position information of the current position of the communication terminal 200 by using, for example, GPS (Global Positioning System). In addition, the measurement of the position information is not limited to GPS, and the communication method such as public wireless LAN such as Wi-Fi, IMES (Indoor MEssaging System), RFID (Radio Frequency Identifier), BLE (Bluetooth Low Energy), or the like is used. Alternatively, the position information of the communication terminal 200 may be measured. The position information of the communication terminal 200 may be measured using a mobile communication system such as LTE or CDMA. The storage unit 240 has a function of storing various programs and various data necessary for the communication terminal 200 to operate in a storage or the like.

<Image detection processing>
The above-described image detection processing according to the embodiment of the present invention will be described with reference to FIG. The image 10 is an image captured by the communication terminal 200. The image 10 includes a tree 11 and a road sign 12, but a part of the road sign 12 is covered with the tree 11. The image 10 is transmitted to the first image detection unit 121 and the second image detection unit 122 in the server 100, respectively. Then, it is assumed that the first detection result shown in the table TB11 is obtained as a result of the image detection by the first image detection unit 121. Similarly, it is assumed that the second detection result shown in the table TB12 is obtained as a result of the image detection by the second image detection unit 122.

In the example of FIG. 3, as the detection result, the information of the object included in the image 10 is output as text information as a tag. Here, in the first detection result and the second detection result, the first detection result has the tags "parking prohibited" and "40", whereas the second detection result does not detect them. In the second detection result, the tag "0" is output, which indicates that the number "40" on the road sign 12 cannot be detected.

The extraction unit 140 extracts the difference between the first detection result and the second detection result. In the example of FIG. 3, “parking prohibited” and “40” are included in the first detection result, not included in the second detection result, and “0” is included in the second detection result. What is not included in is extracted as a difference.

The storage unit 190 stores the information regarding the difference extracted by the extraction unit 140 in association with the image 10. For example, as shown in FIG. 3B, a detection difference (“no parking” “40”) may be associated with the image ID (image_10) of the image 10 and stored as the detection result table TB13. Further, the storage unit 190 may store location information that is information regarding the shooting location of the image 10. In the example of FIG. 3B, position information is stored as location information in the detection result table TB13. The location information can be acquired by the position information acquisition unit 230 when the image 10 is captured by the communication terminal 200. Further, the location information may specify the shooting location of the image 10 by, for example, crawling a website by the server 100.

The output unit 150 outputs the information regarding the difference extracted by the extraction unit 140 in association with the image 10. 4A and 4B show examples of display screens of the communication terminal 200A on which the output result of the output unit 150 is displayed. That is, the output unit 150 outputs the information for displaying the information regarding the difference on a predetermined display unit of the communication terminal 200. The output result by the output unit 150 is not limited to the form output to the communication terminal 200A, and may be output to another monitor connected to the server 100, or the communication in which the image 10 is captured, for example. The information may be output from an information processing device (for example, the terminal of the administrator of the road sign 12) different from the terminal 200A. Here, the case of the communication terminal 200A will be described as an example. The output result is not limited to an image, and may be text information or audio information.

In the example of FIG. 4A, the mark 22 indicating the shooting location of the image of which the difference is extracted by the extraction unit 140 is output on the map 21. Therefore, the user can promptly grasp the place where the image was captured. When the user selects the mark 22, the output unit 150, as shown in FIG. 4B, the image 23 captured by the mark 22 and the extracted difference information 24 (“parking prohibited” in the example of the figure). , “40”) is displayed.

A control method of the server 100 according to the embodiment of the present invention will be described with reference to the flowchart of FIG. Note that the flowchart of FIG. 5 shows processing for one image. First, the server 100 acquires an image from the input/output control unit 130 or the communication control unit 110 (step S11). Then, the first image detection unit 121 and the second image detection unit 122 perform image detection for one image (step S12). The extraction unit 140 determines whether a difference is detected between the first detection result by the first image detection unit 121 and the second detection result by the second image detection unit 122 (step S13). If there is a detection difference (YES in step S13), the output unit 150 outputs information regarding the detection difference (step S14). If there is no detection difference (NO in step S13), the process ends.

As described above, according to the embodiment of the present invention, when there is a difference in the detection result as a result of image detection of the same image by two image detection units having different detection accuracy, information regarding the difference is output. It The difference in the detection result in the image detection with different detection accuracy means that the image includes a state that causes the difference. Therefore, it is possible to detect a place having a safety problem, for example, a road sign cannot be visually recognized.

The first accuracy may be higher than a predetermined threshold value indicating the detection accuracy by the human when the image detection is performed by the human under the predetermined condition, and the second accuracy may be equal to or lower than the predetermined threshold value. .. The human detection accuracy can be set by performing image detection in advance by one or more users under the same conditions as when obtaining the first accuracy and the second accuracy. For example, image detection is performed on a plurality of images under the condition of "extracting an object shown in one image within 2 seconds", and the detection accuracy by humans is determined from the number of extracted objects, the error rate, and the like. You may set it.

According to one embodiment of the present invention, the first accuracy is set higher than the human detection accuracy and the second accuracy is set lower than the human detection accuracy. Therefore, an object detected by the first image detection unit 121 and not detected by the second image detection unit 122 is an object that is highly likely not to be detected by the user. That is, according to an embodiment of the present invention, it is possible to detect an object that is difficult for the user to visually recognize, and for example, when the present invention is applied to an image of a road sign such as the image 10, the user can be sure. It is possible to detect that the object to be visually recognized is in a state in which it is difficult to visually recognize.

According to the embodiment of the present invention, the server 100 further includes a determination unit 160 that determines the relationship between the difference extracted by the extraction unit 140 and the shooting location of one image. The output unit 150 may output information regarding the difference according to the relevance determined by the determination unit 160. The relationship between the extracted difference and the shooting location of one image is an index indicating the importance of the extracted difference with respect to the shooting location, and refers to, for example, information indicating characteristics associated with the shooting location. .. This embodiment will be described with reference to FIG.

FIG. 6A is a diagram showing an image 30 obtained by capturing the same place as the image 10. Unlike the image 10, the image 31 shows the person 31 behind the tree 11. Here, as a result of image detection by the first image detection unit 121 and the second image detection unit 122, the person 31 may be extracted as a difference, but the person 31 is an object that the user should definitely recognize. It can be said that the information does not need to be output and does not need to be output. In such a case, the determination unit 160 determines that there is no relevance between the shooting location of the image 30 and the difference extracted by the extraction unit 140. Note that the determination by the determination unit 160 can be performed, for example, based on at least one or more features related to the shooting location of one image, which is stored in the storage unit 190. FIG. 6B shows an example of the features stored in the storage unit 190. As shown in FIG. 6B, a plurality of keywords are stored in association with the category of the shooting location. In the example of the figure, keywords such as “sign”, “signal”, “object on road”, “street parking”, and “crack” are associated with the category “road” as features. The determination unit 160 sets an image category based on the image detection result, and determines that the difference extracted by the extraction unit 140 is relevant when the difference is associated with the category.

With such a configuration, it is possible to prevent information about unnecessary differences from being output.

It should be noted that, according to an embodiment of the present invention, the server 100 may further include a receiving unit 170 that receives, from a user, selection information as to whether or not it is necessary to output the information regarding the difference output by the output unit 150. Good. In addition, the learning unit 180 may be provided to learn the feature regarding the shooting location of one image based on the output difference and the selection information by the user. This embodiment will be described with reference to FIG. 7.

FIG. 7 is an example of a screen of the communication terminal 200A in which the detection difference of the image 30 by the first image detection unit 121 and the second image detection unit 122 is output. In the example of FIG. 7, the keyword “person” is output as the information regarding the difference in addition to “road sign” and “40”. The user can select either the OK button 34 or the selection button 33 for the output result of FIG. 7. When the selection button 33 is selected, a screen for selecting unnecessary keywords is displayed, and the user can input that the keyword “person” is unnecessary. The learning unit 180 learns that the keyword “person” is not necessary for the image 30 and can update the table of the characteristics regarding the shooting location shown in FIG. 6B, for example.

With such a configuration, the difference to be output for one image is appropriately learned, and it is possible to provide a more convenient image detection system.

Although the present invention has been described based on the drawings and the embodiments, it should be noted that those skilled in the art can easily make various variations and modifications based on the present disclosure. Therefore, it should be noted that these variations and modifications are included in the scope of the present invention. For example, the functions and the like included in each constituent unit and each step can be rearranged so as not to logically contradict, and a plurality of constituent units and steps can be combined or divided into one. Is. In addition, the configurations described in the above embodiments may be combined as appropriate. For example, each component described as being included in the server 100 may be distributed and realized by a plurality of servers. Further, each component may be provided by an API (Application Programming Interface).

In addition, the example of the road sign has been described above. However, the present invention is not limited to the example of the road sign, and can be applied to all objects that detect that the object or information that the user should appropriately visually recognize is in the invisible state. For example, the present invention can be applied also when designing a user interface of a device such as a layout of a dashboard of a car.

The program of each embodiment of the present disclosure may be provided in a state of being stored in a storage medium readable by the information processing device. The storage medium can store the program in a “non-transitory tangible medium”. The programs include, for example, software programs and information processing device programs.

The storage medium is, where appropriate, one or more semiconductor-based or other integrated circuits (ICs) (eg, field programmable gate array (FPGA), application specific IC (ASIC), etc.), hard Disk drive (HDD), hybrid hard drive (HHD), optical disk, optical disk drive (ODD), magneto-optical disk, magneto-optical drive, floppy diskette, floppy disk drive (FDD), magnetic tape, solid-state drive (SSD), RAM drive, secure digital card or drive, any other suitable storage medium, or any suitable combination of two or more thereof. Storage media may be volatile, non-volatile, or a combination of volatile and non-volatile, where appropriate.

Further, the program of the present disclosure may be provided to the server 100 via any transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program.

Each embodiment of the present disclosure can also be realized in the form of a data signal embedded in a carrier wave in which a program is embodied by electronic transmission.

The program of the present disclosure is implemented using, for example, a script language such as Java Script (registered trademark), Python, C language, Go language, Swift, Koltin, Java (registered trademark), or the like.

400 image detection system 300 network 100 server (information processing device)
200 communication terminal 200A smartphone 210B camera 200B drive recorder 101 processor 102 memory 103 storage 110 communication control unit 121 first image detection unit 122 second image detection unit 130 input/output control unit 140 extraction unit 150 output unit 160 determination unit 170 reception unit 180 Learning part 190 Storage part 210 Communication control part 220 Imaging control part 230 Position information acquisition part 240 Storage part 10 Image 11 Tree 12 Road sign 21 Map 22 Mark 23 Image 24 Information 30 Image 31 Person 33 Selection button 34 Button

Claims (8)

In the information processing device,
A first image detection function of detecting at least one object included in the image with a first accuracy;
A second image detection function for detecting one or more objects included in the image with a second accuracy different from the first accuracy;
Image acquisition function to acquire one image,
An extraction function for extracting a difference between the first detection result of the first image detection function and the second detection result of the second image detection function in the one image;
When the difference is extracted by the extraction function, an output function of outputting information regarding the difference in association with the one image,
A control program of an information processing device for realizing the above. The first accuracy is higher than a predetermined threshold indicating the detection accuracy by the human when the image detection is performed by the human under predetermined conditions, and the second accuracy is equal to or lower than the predetermined threshold. is there,
The control program for the information processing apparatus according to claim 1, wherein In the information processing device,
A further realization of a location information acquisition function for obtaining location information which is information relating to the shooting location of the one image,
The output function outputs the location information of the one image together with the information about the difference,
The control program of the information processing device according to claim 1 or 2, characterized in that. In the information processing device,
A determination function of determining the relationship between the difference extracted by the extraction function and the shooting location of the one image;
Is further realized,
The output function outputs information regarding the difference according to the relevance determined by the determination function,
The control program of the information processing apparatus according to claim 3, wherein The determination function determines the relevance based on at least one or more features related to a shooting location of the one image, which is stored in a predetermined storage unit,
The control program for the information processing apparatus according to claim 4, wherein In the information processing device,
A reception function that receives selection information from the user as to whether or not it is necessary to output the information regarding the difference output by the output function,
A learning function of learning a feature related to a shooting location of the one image based on the difference and the selection information,
To further realize,
The control program of the information processing apparatus according to claim 5, wherein A first image detection unit that detects at least one object included in the image with a first accuracy, and a first image detection unit that detects at least one object included in the image with a second accuracy different from the first accuracy. The information processing device including the two-image detection unit,
An image acquisition step of acquiring one image,
An extraction step of extracting a difference between the first detection result by the first image detection unit and the second detection result by the second image detection unit in the one image;
When the difference is extracted in the extracting step, an output step of outputting information regarding the difference,
A method for controlling an information processing apparatus for executing the method. A first image detection unit that detects at least one object included in the image with a first accuracy;
A second image detection unit that detects one or more objects included in the image with a second accuracy different from the first accuracy;
An image acquisition unit that acquires one image,
An extraction unit that extracts a difference between the first detection result of the first image detection unit and the second detection result of the second image detection unit in the one image;
When the difference is extracted by the extraction unit, an output unit that outputs information regarding the difference,
An information processing apparatus including.

Images