JP2021131623A - Traffic risk reduction program, information processing device, and method - Google Patents

Abstract

To suitably identify a mobile body which satisfies a predetermined condition.SOLUTION: An information processing device includes an estimation section and an identification section. The estimation section estimates an image captured by a monitoring camera or to be captured by an on-vehicle camera mounted on an automobile existing in the neighborhood of the monitoring camera based on a monitoring camera image captured by the monitoring camera. The identification section identifies an automobile mounting the on-vehicle camera which has captured an on-vehicle camera image corresponding to an estimation image among a plurality of automobiles mounting an on-vehicle camera.SELECTED DRAWING: Figure 3

Description

The present invention relates to traffic risk reduction programs, information processing devices and methods.

In recent years, with the development of autonomous driving technology, autonomous vehicles are becoming widespread. For example, it is common to each blind spot area based on the first blind spot information indicating the blind spot area generated by the object when viewed from the infrastructure sensor and the second blind spot information indicating the blind spot area generated by the object when viewed from the in-vehicle sensor. A technique for outputting common blind spot information indicating a first common blind spot region to an external device is known.

JP-A-2018-195289

However, in the above-mentioned conventional technique, it is not always possible to preferably specify a moving body that satisfies a predetermined condition. For example, in the above-mentioned prior art, only the common blind spot information indicating the first common blind spot area common to each blind spot area is output to an external device, and the moving body having a high possibility of being involved in a traffic accident It is not always possible to identify such a moving object when providing information for avoiding a traffic accident.

The present application has been made in view of the above, and an object of the present application is to provide a traffic risk reduction program, an information processing device, and a method capable of preferably identifying a moving body satisfying a predetermined condition.

The information processing apparatus according to the present application estimates an image taken by the surveillance camera or taken by an in-vehicle camera mounted on an automobile existing in the vicinity of the surveillance camera based on the surveillance camera image taken by the surveillance camera. It is characterized in that it is provided with an estimation unit for identifying a vehicle equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to the estimated image among a plurality of vehicles equipped with an in-vehicle camera. ..

According to one aspect of the embodiment, there is an effect that a moving body satisfying a predetermined condition can be preferably specified.

FIG. 1 is a diagram showing an example of a specific process executed by the information processing apparatus according to the embodiment. FIG. 2 is a diagram showing a specific example of specific processing executed by the information processing apparatus according to the embodiment. FIG. 3 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 4 is a diagram showing an example of the surveillance camera image storage unit according to the embodiment. FIG. 5 is a diagram showing an example of an in-vehicle camera image storage unit according to the embodiment. FIG. 6 is a diagram showing an example of an estimated image storage unit according to the embodiment. FIG. 7 is a diagram showing an example of a destination storage unit according to the embodiment. FIG. 8 is a flowchart showing an example of a flow of specific processing executed by the information processing apparatus according to the embodiment. FIG. 9 is a diagram showing a specific example of the specific processing executed by the information processing apparatus according to the modified example. FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, modes for implementing the traffic risk reduction program, information processing device, and method according to the present application (hereinafter, referred to as “implements”) will be described in detail with reference to the drawings. The traffic risk reduction program, information processing device, and method according to the present application are not limited by this embodiment. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Idea background]
With the development of autonomous driving technology in recent years, autonomous vehicles are becoming widespread, but there is a point that the maintenance of the transportation system is not sufficient. For example, in the process in which autonomous vehicles are becoming widespread, there is a process in which autonomous vehicles and manual vehicles, which are vehicles driven by drivers, coexist. In this case, it is difficult to prevent a traffic accident caused by a manual vehicle even if only the autonomous vehicle travels according to the traffic rules. Therefore, it is necessary to control the self-driving car with high accuracy in consideration of the running of the manual car.

However, the driving technology of autonomous vehicles is not always sufficient. For example, an autonomous vehicle has a photographing device such as a camera, and by photographing the surroundings of the autonomous vehicle, the traveling is controlled based on the surrounding environment and the situation. In this case, the self-driving car may not be able to recognize the side environment and the situation when traveling at a predetermined speed or higher. For example, when the self-driving car travels at a high speed, the image of the camera that captures the side surface may flow, and other vehicles or objects may not be recognized. In this case, it becomes difficult for the self-driving car to acquire information from the side surface, so that the risk of a traffic accident from the side surface increases. In this way, the issue was how to obtain information from the side regarding the driving technology of the autonomous driving vehicle.

Therefore, in the present embodiment, a technique for supporting the running of an autonomous vehicle is provided. In the present embodiment, the information from the side of the autonomous driving vehicle is complemented by utilizing the information acquired from an external device such as a sensor. As a result, the present embodiment makes it possible to control the autonomous driving vehicle with high accuracy.

[2. An example of specific processing indicated by an information processing device]
An example of the specific processing executed by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a specific process executed by the information processing apparatus 100 according to the embodiment.

As shown in FIG. 1, the information processing system 1 includes an automobile 10, a surveillance camera 20, a surveillance camera image providing device FIS, an in-vehicle camera image providing device SIS, and an information processing device 100. The automobile 10, the surveillance camera 20, the surveillance camera image providing device FIS, the in-vehicle camera image providing device SIS, and the information processing device 100 are connected via a wireless network (not shown). The information processing system 1 shown in FIG. 1 includes a plurality of automobiles 10, a plurality of surveillance cameras 20, a plurality of surveillance camera image providing devices FIS, a plurality of in-vehicle camera image providing devices SIS, and the like. A plurality of information processing devices 100 may be included.

The automobile 10 according to the embodiment is a connected vehicle that communicates with various other devices via a wireless network. For example, the automobile 10 executes communication by an in-vehicle device such as a communication module incorporated in the automobile 10.

Further, the automobile 10 has an in-vehicle device having a camera function. For example, the in-vehicle device includes a drive recorder, a car navigation system, a car navigation system having a drive recorder function, and the like. For example, the in-vehicle device incorporated in each automobile 10 distinguishes between an image including a landscape taken from a predetermined angle (hereinafter, may be referred to as an in-vehicle camera image) and the automobile 10 in which the in-vehicle device is mounted. The vehicle ID (Identifier) for this purpose is always transmitted to the vehicle-mounted camera image providing device SIS.

The surveillance camera 20 according to the embodiment is a surveillance camera having a function of being able to communicate with various other devices via a wireless network. For example, the surveillance camera 20 is fixedly installed on a traffic signal or a pillar to which the traffic signal is attached. The surveillance camera 20 acquires an image including a landscape or the like taken from a predetermined angle (hereinafter, may be referred to as a surveillance camera image). In the following, each of the different surveillance cameras will be referred to as a surveillance camera 2N, and when the surveillance camera 2N is not particularly distinguished, it will be referred to as a surveillance camera 20.

The surveillance camera image providing device FIS according to the embodiment is realized by, for example, a server device or a cloud system. Specifically, the surveillance camera image providing device FIS constantly acquires the surveillance camera image captured by the surveillance camera 20. Then, the surveillance camera image providing device FIS provides the surveillance camera image to the information processing device 100 in response to the request from the information processing device 100.

The vehicle-mounted camera image providing device SIS according to the embodiment is realized by, for example, a server device or a cloud system. Specifically, the vehicle-mounted camera image providing device SIS acquires an image taken by the vehicle-mounted device of the vehicle 10 and a vehicle ID at all times or at predetermined intervals (for example, 30 times per second). Then, the vehicle-mounted camera image providing device SIS provides the vehicle-mounted camera image and the vehicle ID to the information processing device 100 in response to a request from the information processing device 100. Further, the information processing device 100 stores the automobile ID that identifies the automobile 10 and the contact information in a predetermined storage unit in association with each other.

The information processing device 100 according to the embodiment is realized by, for example, a server device or a cloud system. Specifically, the information processing device 100 estimates an image taken by an in-vehicle camera mounted on an automobile based on a surveillance camera image taken by the surveillance camera. Then, the information processing device 100 identifies the vehicle equipped with the vehicle-mounted camera that captures the vehicle-mounted camera image corresponding to the estimated image estimated from the surveillance camera image among the plurality of vehicles equipped with the vehicle-mounted camera.

Hereinafter, an example of the specific processing by the information processing apparatus 100 will be described along the flow with reference to FIG.

In the example of FIG. 1, an example in which a vehicle CA1 which is not a connected vehicle performing dangerous driving (hereinafter, may be referred to as a non-connected vehicle CA1) and a vehicle 10 which is a connected vehicle are approaching an intersection. show.

Here, as a result of analyzing the image taken by the surveillance camera 20, the unconnected vehicle CA1 is about to enter the intersection by traveling significantly exceeding the legal speed, and the unconnected vehicle CA1 and the automobile 10 collide with each other. It is presumed that the possibility is high. That is, in the example shown in FIG. 1, it is assumed that the surveillance camera 20 has detected that the automobile 10 is likely to have a traffic accident.

In this case, the surveillance camera 20 wants to alert the automobile 10 regarding a traffic accident, but the image taken by the surveillance camera 20 alone cannot identify the communication destination of the automobile 10, and the notification is given. Is difficult to do. In response to this problem, in the present embodiment, the destination of the automobile 10 photographed by the surveillance camera 20 is specified by the following procedure.

First, as shown in FIG. 1, the information processing device 100 acquires the surveillance camera images captured by the surveillance cameras 21 and 22 from the surveillance camera image providing device FIS (step S1).

For example, in the example of FIG. 1, the information processing apparatus 100 acquires a surveillance camera image including the unconnected vehicle CA1 taken by the surveillance camera 21. Further, in the example of FIG. 1, the information processing device 100 acquires a surveillance camera image including the automobile 10 taken by the surveillance camera 22. In this case, in the example of FIG. 1, it is assumed that the surveillance camera image taken by the surveillance camera 21 captures the non-connected vehicle CA1 traveling at a speed significantly exceeding the legal speed. Further, it is assumed that the surveillance camera image taken by the surveillance camera 22 includes the surveillance camera image including the automobile 10. The information processing device 100 may acquire a surveillance camera image in advance from the surveillance camera image providing device FIS and acquire an in-vehicle camera image in advance from the in-vehicle camera image providing device SIS. At this time, the information processing device 100 uses the in-vehicle camera images and the like in any order. You may acquire the surveillance camera image.

Here, the information processing device 100 identifies a vehicle that is likely to be involved in a traffic accident as a target vehicle based on a surveillance camera image (step S2). For example, the information processing device 100 determines whether or not the vehicle photographed in the surveillance camera image is a dangerous vehicle having a high possibility of causing a traffic accident. To give a specific example, it is assumed that the surveillance camera image taken by the surveillance camera 21 captures the non-connected vehicle CA1 traveling at a speed significantly exceeding the legal speed. In this case, the information processing device 100 determines that the unconnected vehicle CA1 is a dangerous vehicle with a high possibility of causing a traffic accident.

Then, when a dangerous vehicle is photographed, the information processing device 100 identifies a vehicle that is likely to be involved in a traffic accident as a target vehicle from a surveillance camera image. For example, it is assumed that the non-connected vehicle CA1 traveling in the blind spot of the automobile 10 is a dangerous automobile. In this case, the information processing device 100 identifies the automobile 10 as the target automobile based on the positional relationship between the surveillance camera 21 and the surveillance camera 22.

The information processing device 100 is provided with the orientation of the automobile 10 estimated from the surveillance camera image, the orientation of the unconnected vehicle CA1 which is a dangerous vehicle, the speeds of the automobile 10 and the unconnected vehicle CA1, and the surveillance camera 20. The target vehicle may be specified in consideration of the positional relationship between the buildings and roads existing on the road. For the identification of such a target vehicle, various known techniques for estimating the occurrence of a traffic accident by image analysis can be adopted.

Here, even if the automobile 10 is specified as the target automobile from the surveillance camera image, it is difficult to identify the destination of the automobile 10 from the surveillance camera image. Therefore, the information processing device 100 estimates an in-vehicle camera image predicted to be taken by the in-vehicle device of the automobile 10 which is the target vehicle, based on the surveillance camera image taken by the surveillance camera 20 (step S3).

Further, the information processing apparatus 100 uses the estimated in-vehicle camera image (hereinafter, may be referred to as an estimated image) as a search query, and corresponds to the estimated image from the in-vehicle camera image acquired from the in-vehicle camera image providing device SIS. The vehicle-mounted camera image to be searched is searched (step S4). Then, the information processing device 100 identifies the vehicle equipped with the vehicle-mounted device that has captured the vehicle-mounted camera image corresponding to the estimated image as the target vehicle captured by the surveillance camera 20 (step S5). That is, the information processing apparatus 100 captures the connected vehicle in which the in-vehicle camera image corresponding to the estimated image is taken among the connected vehicles whose destinations are known based on the matching result between the estimated image and the in-vehicle camera image. Link to the target vehicle photographed in.

Here, a process of matching the estimated image and the vehicle-mounted camera image will be described with reference to FIG. FIG. 2 is a diagram showing a specific example of specific processing executed by the information processing apparatus according to the embodiment. The process shown in FIG. 2 corresponds to steps S1 to S5 shown in FIG.

In the example of FIG. 2, the information processing apparatus 100 acquires the image FIM1 indicated by the image including the automobile TC10 and the building TO1 from the surveillance camera 22 as the surveillance camera image (step S21). At this time, the information processing apparatus 100 identifies the automobile TC10 and the building TO1 by using a conventional technique such as image analysis.

In such a case, the information processing device 100 sets the automobile TC10 included in the surveillance camera image taken by the surveillance camera 22 as the target automobile TC10. Then, the information processing device 100 generates an estimated image PIM1 predicted to be captured by the in-vehicle device of the target vehicle TC10 from the image captured by the surveillance camera 22 (step S22). For example, the information processing apparatus 100 uses various surveillance camera images continuously captured by the surveillance camera 22 and various surveillance camera images captured by another surveillance camera 20 installed in the vicinity of the surveillance camera 22. Generate an estimated image PIM1. It should be noted that such an estimated image generation process can be realized by various estimation techniques for estimating an image taken from another viewpoint from an image taken from a certain viewpoint.

On the other hand, the information processing device 100 acquires the vehicle-mounted camera image SIM1 captured by the vehicle-mounted device of the automobile 10 (step S23). Here, when the automobile 10 is the target automobile TC10, the in-vehicle camera image SIM1 captured by the in-vehicle device of the automobile 10 is considered to be similar to the estimated image PIM1. Therefore, the information processing device 100 matches the in-vehicle camera image SIM1 with the estimated image PIM1 (step S24). For example, in the information processing apparatus 100, when the degree of similarity between the estimated image PIM1 and the in-vehicle camera image SIM1 indicating the similarity of the images is equal to or more than a predetermined threshold value, the in-vehicle camera image SIM1 and the estimated image PIM1 Judge that it corresponds.

In this case, when the in-vehicle camera image SIM1 and the estimated image PIM1 include the known building TO1, the information processing apparatus 100 includes the building TO1 included in the in-vehicle camera image SIM1 and the building TO1 included in the estimated image PIM1. The degree of similarity is calculated by comparing with.

For example, the information processing device 100 includes the outer shape of the building TO1 included in the in-vehicle camera image SIM1, the relative position of the building TO1 estimated from other objects and landscapes, and the construction included in the estimated image PIM1. The degree of similarity is calculated from the outer shape of the object TO1 and the relative position of the building TO1 estimated from other objects and landscapes. The calculation process for calculating such similarity can be realized by conventional techniques such as image analysis and image matching. Further, the information processing apparatus 100 may calculate the similarity by comparing the feature amount extracted from the vehicle-mounted camera image SIM1 with the feature amount extracted from the estimated image PIM1. Then, the information processing apparatus 100 determines that the in-vehicle camera image SIM1 and the estimated image PIM1 correspond to each other when the calculated similarity is equal to or higher than a predetermined threshold value.

Then, when the information processing device 100 determines that the in-vehicle camera image SIM1 and the estimated image PIM1 correspond to (similar to), the target vehicle TC10 and the vehicle 10 equipped with the in-vehicle device that captured the in-vehicle camera image SIM1 To tie. By performing such processing, the information processing device 100 is equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to the estimated image estimated from the surveillance camera image among a plurality of automobiles equipped with the in-vehicle camera. The vehicle 10 can be specified. As a result, the information processing device 100 realizes the association between the target vehicle TC10 and the vehicle 10 by associating the target vehicle TC10 captured in the surveillance camera image with the vehicle ID of the specified vehicle 10. Then, the information processing device 100 specifies the destination associated with the specified vehicle ID as the destination of the target vehicle TC10. In this way, the information processing device 100 can specify an appropriate destination of information when transmitting information to the automobile 10 that is likely to be involved in a traffic accident.

Returning to FIG. 1, the explanation will be continued. The information processing device 100 notifies the specified automobile 10 of the alert information regarding the non-connected vehicle CA1 (step S6). As a result of such processing, the automobile 10 will perform various driving controls based on the notified information indicating the alert regarding the unconnected vehicle CA1. For example, the automobile 10 may be decelerated below a predetermined speed based on the information indicating a warning regarding the unconnected vehicle CA1, or may be stopped by gradually decelerating.

Further, for example, the automobile 10 may travel so as to avoid the unconnected vehicle CA1 based on the information indicating the warning regarding the unconnected vehicle CA1. For example, the automobile 10 may travel by controlling the driving operation so as to move to a position away from the unconnected vehicle CA1.

As described above, the information processing device 100 according to the embodiment refers to the automobile 10 which is highly likely to be involved in a traffic accident with the non-connected vehicle CA1 which runs dangerously from the surveillance camera image taken by the surveillance camera 20. We will provide a solution for cases where you want to call attention to traffic accidents. Conventionally, the destination of the automobile 10 cannot be specified only by the surveillance camera image taken by the surveillance camera 20. In response to this problem, the information processing apparatus 100 uses the estimated image as a search query and searches the in-vehicle camera image providing device SIS for the in-vehicle camera image corresponding to the estimated image, so that the in-vehicle camera image corresponding to the estimated image is searched. The vehicle equipped with the in-vehicle device in which the image is taken is specified as the target vehicle photographed by the surveillance camera 20. Then, the information processing device 100 notifies the automobile 10 of danger information such as a traffic accident caused by the unconnected vehicle CA1. In this way, the information processing device 100 can suitably notify the specified automobile 10 of danger information such as a traffic accident caused by the unconnected vehicle CA1. For example, it has been difficult for the automobile 10 to acquire information about an object located in an area (blind spot) that cannot be photographed by an in-vehicle camera. However, the information processing device 100 utilizes the surveillance camera image taken by the surveillance camera 20, and even if the unconnected vehicle CA1 suddenly jumps out from the blind spot of the automobile 10, it is caused by the non-connected vehicle CA1. It is possible to notify the automobile 10 of dangerous information such as a traffic accident.

As a result of the above-mentioned processing, the automobile 10 can perform various driving controls based on the information notified by the information processing device 100. For example, the automobile 10 is controlled to decelerate below a predetermined speed or to stop by gradually decelerating based on the information indicating the alert regarding the unconnected vehicle CA1 notified by the information processing device 100. It can be performed. As a result, the automobile 10 performs various driving controls according to various traffic conditions, dangerous situations, and the like, so that it is possible to realize more safe driving. Therefore, the automobile 10 can realize appropriate traveling based on the information notified by the information processing device 100 even when the side environment and the situation cannot be recognized.

[3. Information processing device configuration]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 transmits / receives information between the vehicle 10, the surveillance camera 20, the surveillance camera image providing device FIS, and the vehicle-mounted camera image providing device SIS via the wireless network. More specifically, the communication unit 110 is registered in the information registered in the surveillance camera image storage unit FISM of the surveillance camera image providing device FIS and in the in-vehicle camera image storage unit SISM of the in-vehicle camera image providing device SIS. Get information and.

In the example shown in FIG. 3, an example in which the surveillance camera image storage unit FISM and the in-vehicle camera image storage unit SISM are provided outside the information processing device 100 has been described, but the embodiment is limited to this. is not it. For example, the information processing device 100 may acquire the surveillance camera image storage unit FISM and the vehicle-mounted camera image storage unit SISM from the surveillance camera image providing device FIS and the vehicle-mounted camera image providing device SIS and store them in the storage unit 120. ..

(About the surveillance camera image storage unit FISM)
Here, FIG. 4 shows an example of the surveillance camera image storage unit FISM according to the embodiment according to the embodiment. FIG. 4 is a diagram showing an example of the surveillance camera image storage unit FISM according to the embodiment according to the embodiment. In the example shown in FIG. 4, the surveillance camera image storage unit FISM according to the embodiment has items such as “camera ID”, “surveillance camera image”, and “time information”.

The "camera ID" is an identifier that identifies the surveillance camera 20. The “surveillance camera image” is information related to the surveillance camera image associated with the “camera ID”. The "time information" is information regarding the time taken by the surveillance camera 20 associated with the "surveillance camera image".

For example, in FIG. 4, the surveillance camera image of "SC1" identified by the camera ID is "FIM1" and the time information is "DA1". In the example shown in FIG. 4, the surveillance camera image and the time information are represented by abstract codes such as "FIM1" and "DA1", but the surveillance camera image and the time information have a specific file format related to the image and the time information. , A numerical value indicating the date and time, or the like.

(About in-vehicle camera image storage SISM)
Subsequently, FIG. 5 shows an example of the vehicle-mounted camera image storage unit SISM according to the embodiment. FIG. 5 is a diagram showing an example of the vehicle-mounted camera image storage unit SISM according to the embodiment. In the example shown in FIG. 5, the vehicle-mounted camera image storage unit SISM has items such as "vehicle ID", "vehicle-mounted camera image", and "time information".

The "vehicle ID" is an identifier that identifies the vehicle 10. The "vehicle-mounted camera image" is information related to the vehicle-mounted camera image associated with the "vehicle ID". The "time information" is information regarding the time taken by the vehicle-mounted device of the vehicle 10 associated with the "vehicle-mounted camera image".

For example, in FIG. 5, the vehicle-mounted camera image of the “MO1” identified by the vehicle ID is “SIM1” and the time information is “DA1”. In the example shown in FIG. 5, the in-vehicle camera image and time information are represented by abstract codes such as “SIM1” and “DA1”, but the in-vehicle camera image and time information may have a specific file format related to the image or the time information. , A numerical value indicating the date and time, or the like.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 120 has an estimated image storage unit 121 and a destination storage unit 122.

(About the estimated image storage unit 121)
The estimated image storage unit 121 according to the embodiment stores an estimated image estimated based on the surveillance camera image. Here, FIG. 6 shows an example of the estimated image storage unit 121 according to the embodiment. In the example shown in FIG. 6, the estimated image storage unit 121 has items such as "estimated image ID", "estimated image", and "time information".

The "estimated image ID" is an identifier that identifies the estimated image. The "estimated image" is information about the estimated image associated with the "estimated image ID". The "time information" is information related to the estimated time when the estimated image associated with the "estimated image" was taken.

For example, in FIG. 6, the estimated image of “CA1” identified by the estimated image ID is “PIM1” and the time information is “DA1”. In the example shown in FIG. 6, the estimated image and time information are represented by abstract codes such as "PIM1" and "DA1", but the estimated image and time information are represented by a specific file format related to the image and the date and time. It may be a numerical value or the like indicating.

(About destination storage unit 122)
In the destination storage unit 122 according to the embodiment, the vehicle ID of the vehicle and the destination such as the contact are stored in association with each other. Here, FIG. 7 is a diagram showing an example of the destination storage unit 122 according to the embodiment. In the example shown in FIG. 7, the destination storage unit 122 has items such as “vehicle ID” and “destination”. The "vehicle ID" is an identifier that identifies the vehicle 10. The "destination" is a destination associated with the "vehicle ID", and is, for example, an e-mail address or the like.

For example, in FIG. 7, in the destination storage unit 122, the destination of the automobile indicated by the automobile ID “MO1” is “AD1”. In FIG. 6, the destination is represented by an abstract code such as "AD1", but the destination is various information for indicating a notification destination such as an e-mail address or an IP address.

(About control unit 130)
The control unit 130 is a controller, and for example, various programs (traffic risk reduction programs) stored in a storage device inside the information processing device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Corresponding to one example) is realized by executing the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a determination unit 132, an estimation unit 133, a specific unit 134, and a notification unit 135, and functions and operations of information processing described below. To realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. Specifically, the acquisition unit 131 acquires an in-vehicle camera image taken by the in-vehicle device of the automobile 10 and a surveillance camera image taken by the surveillance camera 20. To give a more specific example, the acquisition unit 131 acquires various information registered in the surveillance camera image storage unit FISM from the surveillance camera image providing device FIS, and stores the in-vehicle camera image from the in-vehicle camera image providing device SIS. Acquires various information registered in the department SISM.

For example, in the example of FIG. 1, the acquisition unit 131 acquires a surveillance camera image including the unconnected vehicle CA1 taken by the surveillance camera 21. Further, in the example of FIG. 1, the acquisition unit 131 acquires a surveillance camera image including the automobile 10 taken by the surveillance camera 22. In this case, in the example of FIG. 1, it is assumed that the surveillance camera image taken by the surveillance camera 21 captures the non-connected vehicle CA1 traveling at a speed significantly exceeding the legal speed. Further, it is assumed that the surveillance camera image taken by the surveillance camera 22 includes the surveillance camera image including the automobile 10. Then, the acquisition unit 131 registers the acquired various information in the storage unit 120.

In addition, the acquisition unit 131 acquires the angle information of the surveillance camera, which is the information regarding the angle at which the surveillance camera image was taken, together with the surveillance camera image. In addition, the acquisition unit 131 acquires the angle information of the vehicle-mounted camera that is estimated to have taken the vehicle-mounted camera image together with the vehicle-mounted camera image.

(About judgment unit 132)
The determination unit 132 determines whether or not the other vehicle photographed by the surveillance camera is a dangerous vehicle having a high possibility of causing a traffic accident. Further, when the vehicle photographed by the surveillance camera violates the traffic rule more than a predetermined number of times, the determination unit 132 determines the vehicle as a dangerous vehicle.

The determination unit 132 refers to the surveillance camera image taken by the surveillance camera 20 and determines whether or not the vehicle transferred to the surveillance camera image is a dangerous vehicle having a high possibility of causing a traffic accident. For example, when the determination unit 132 receives the surveillance camera image acquired from the surveillance camera image storage unit ISM by the acquisition unit 131, the vehicle 10 is a dangerous vehicle based on whether or not the photographed vehicle 10 satisfies a predetermined condition. It is determined whether or not it is.

For example, the determination unit 132 determines at least when the photographed automobile 10 travels by a predetermined driving operation, travels at a speed equal to or higher than a predetermined threshold value, or violates a traffic rule more than a predetermined number of times. If any one of them is used, it is determined that the vehicle is dangerous.

The determination unit 132 may determine the automobile 10 as a dangerous automobile when the automobile 10 repeats meandering driving. That is, in the surveillance camera image acquired from the surveillance camera 20, when the unconnected vehicle CA1 repeats the meandering operation, the determination unit 132 performs a predetermined driving operation in which the non-connected vehicle CA1 is likely to cause a traffic accident. Since the vehicle is running, the non-connected vehicle CA1 is determined to be a dangerous vehicle.

On the other hand, in the surveillance camera image acquired from the surveillance camera 20, the determination unit 132 determines that the non-connected vehicle CA1 is unlikely to cause a traffic accident when the non-connected vehicle CA1 is traveling in compliance with the traffic rules. The non-connected vehicle CA1 is not determined to be a dangerous vehicle because it is driven by the driving operation of.

Further, for example, in the surveillance camera image acquired from the surveillance camera 20, the determination unit 132 determines that the non-connected vehicle CA1 is a dangerous vehicle when the unconnected vehicle CA1 is traveling at a speed equal to or higher than the legal speed, and is not a non-connected vehicle. When the connected vehicle CA1 is traveling at a speed lower than the legal speed, the non-connected vehicle CA1 does not have to be determined as a dangerous vehicle.

Further, for example, it is assumed that the license plate of the non-connected vehicle CA1 is specified by using a conventional technique such as an image analysis technique for a surveillance camera image including the unconnected vehicle CA1. In this case, the determination unit 132 acquires the violation history of the non-connected vehicle CA1 associated with the license plate and violates the traffic rule more than a predetermined number of times, when the non-connected vehicle CA1 violates the traffic rule. May be determined as a dangerous vehicle. On the other hand, the determination unit 132 may not determine the unconnected vehicle CA1 as a dangerous moving vehicle when the unconnected vehicle CA1 violates the traffic rule less than a predetermined number of times.

In addition, the determination unit 132 determines whether or not the vehicle included in the surveillance camera image is a vehicle that is likely to be involved in a traffic accident. For example, when the determination unit 132 determines that any of the automobiles 10 whose image is included in the surveillance camera image is a dangerous moving object, the determination unit 132 is another automobile 10 whose image is included in the surveillance camera image and is involved in a traffic accident. The other vehicle 10 having a high possibility of being damaged is determined to be the target vehicle. Further, when any one of the automobiles 10 whose image is included in the surveillance camera image is determined to be a dangerous moving object, the determination unit 132 is another automobile 10 whose image is included in the surveillance camera image and is involved in a traffic accident. The other vehicle 10 having a high possibility of being damaged is determined to be the target vehicle.

For example, the positional relationship between the surveillance camera 21 in which a dangerous vehicle is photographed and the surveillance camera 22 in which another vehicle 10 is photographed is known, and the distance between the surveillance camera 21 and the surveillance camera 22 is less than a predetermined distance. Suppose there is. In this case, the determination unit 132 determines that the dangerous vehicle and the vehicle 10 are less than a predetermined distance, so that the vehicle 10 whose image is included in the surveillance camera image is a target vehicle that is likely to be involved in a traffic accident. do. The determination unit 132 may involve a vehicle 10 whose image is included in the same surveillance camera image as the dangerous vehicle or another vehicle 10 photographed by the same surveillance camera 20 as the dangerous vehicle within a predetermined time in a traffic accident. It may be determined that the vehicle is a target vehicle having high characteristics.

Further, for example, the determination unit 132 determines that the vehicle 10 included in the surveillance camera image is likely to be involved in a traffic accident when the determined dangerous vehicle is located near the blind spot of the vehicle 10. , The vehicle 10 is determined to be the target vehicle. Here, the blind spot of the automobile 10 is estimated based on the direction and speed of the dangerous automobile and the orientation and speed of the automobile 10. For example, the blind spot of the automobile 10 is a side surface of the automobile 10.

(About estimation unit 133)
The estimation unit 133 estimates various types of information. Specifically, the estimation unit 133 is photographed by an in-vehicle camera photographed by the surveillance camera 20 or mounted on a vehicle 10 existing in the vicinity of the surveillance camera 20 based on the surveillance camera image captured by the surveillance camera 20. Estimate the image. Further, the estimation unit 133 estimates the estimated image by setting the vehicle located in a predetermined positional relationship with the dangerous vehicle determined by the determination unit 132 as the target vehicle. For example, the estimation unit 133 generates an estimation image predicted to be taken by the in-vehicle device of the target vehicle from the surveillance camera image acquired by the acquisition unit 131.

Here, the information that can be acquired is limited only by one surveillance camera image, and if an estimated image is generated based on one surveillance camera image, an estimated image with low accuracy may be generated. Therefore, the estimation unit 133 generates an estimation image using the surveillance camera images acquired from the plurality of surveillance cameras. Specifically, the estimation unit 133 uses an estimated image based on a first surveillance camera image taken by the first surveillance camera and a second surveillance camera image taken by a second surveillance camera different from the first surveillance camera. To estimate. For example, the estimation unit 133 estimates using various surveillance camera images continuously taken by the surveillance camera 20 and various surveillance camera images taken by another surveillance camera 20 installed in the vicinity of the surveillance camera 20. Generate an image. In this case, the estimation unit 133 generates an estimated image based on the orientation, speed, size, vehicle height, and the like of the target vehicle. Then, the estimation unit 133 stores the estimated image in the estimation image storage unit 121.

In addition, the orientation installed for each surveillance camera and the terrain located for each surveillance camera may differ. In this case, if the estimated image is generated without performing the correction process based on the orientation installed for each surveillance camera image or the terrain in which it is located, an estimated image with low accuracy may be generated. Therefore, the estimation unit 133 performs correction processing based on the orientation installed for each surveillance camera image and the terrain in which the estimation unit 133 is located. Specifically, the estimation unit 133 determines the target vehicle based on the surveillance camera image, the orientation of the surveillance camera when the surveillance camera 20 is photographed, and the orientation of the in-vehicle camera of the target vehicle captured by the surveillance camera. The image taken by the in-vehicle camera mounted on the vehicle is estimated as an estimated image.

For example, the estimation unit 133 generates an estimated image based on the angle information of the surveillance camera acquired by the acquisition unit 131, and stores the estimated image in the estimation image storage unit 121. For example, the angle information of the surveillance camera includes, as the shooting angle of the surveillance camera 20, an angle calculated from the coordinates with respect to each direction based on the terrain in which the surveillance camera 20 is installed. It should be noted that such an estimated image generation process can be realized by various estimation techniques for estimating an image taken from another viewpoint from an image taken from a certain viewpoint.

(About specific part 134)
The identification unit 134 specifies various types of information. Specifically, the specific unit 134 refers to the estimated image storage unit 121, and among a plurality of vehicles equipped with the in-vehicle camera, the vehicle equipped with the in-vehicle camera that captures the in-vehicle camera image corresponding to the estimated image. To identify. Then, the specific unit 134 realizes the notification to the target vehicle photographed by the surveillance camera image by associating the specified vehicle with the target vehicle photographed by the surveillance camera image.

For example, the specific unit 134 uses the estimated image stored in the estimated image storage unit 121 as a search query, and searches for the in-vehicle camera image corresponding to the estimated image from the in-vehicle camera image acquired from the in-vehicle camera image providing device SIS. Then, the identification unit 134 identifies the vehicle equipped with the vehicle-mounted device that has captured the vehicle-mounted camera image corresponding to the estimated image as the target vehicle photographed by the surveillance camera 20. That is, the specific unit 134 uses the connected vehicle whose destination is known based on the matching result of the estimated image and the vehicle-mounted camera image as the surveillance camera image. Link to the photographed target vehicle.

To give a more specific example of the specific processing, in the example of FIG. 2, the specific unit 134 matches the estimated image PIM1 generated by the estimation unit 133 with the vehicle-mounted camera image SIM1. For example, in the specific unit 134, the vehicle-mounted camera image SIM1 and the estimated image PIM1 correspond to each other when the degree of similarity between the estimated image PIM1 and the vehicle-mounted camera image SIM1 is equal to or higher than a predetermined threshold value. Then it is determined.

In this case, when the vehicle-mounted camera image SIM1 and the estimated image PIM1 include the known building TO1, the specific unit 134 includes the building TO1 included in the vehicle-mounted camera image SIM1 and the building TO1 included in the estimated image PIM1. The similarity is calculated by comparing.

For example, the specific unit 134 includes the outer shape of the building TO1 included in the in-vehicle camera image SIM1, the relative position of the building TO1 estimated from other objects and landscapes, and the building TO1 included in the estimated image PIM1. The degree of similarity is calculated from the outer shape of the building and the relative position of the building TO1 estimated from other objects and landscapes. The calculation process for calculating such similarity can be realized by conventional techniques such as image analysis and image matching. Further, the specific unit 134 may calculate the similarity by comparing the feature amount extracted from the vehicle-mounted camera image SIM1 with the feature amount extracted from the estimated image PIM1. Then, the specific unit 134 determines that the vehicle-mounted camera image SIM1 and the estimated image PIM1 correspond to each other when the calculated similarity is equal to or higher than a predetermined threshold value.

Then, when it is determined that the vehicle-mounted camera image SIM1 and the estimated image PIM1 correspond to each other, the specific unit 134 associates the target vehicle TC10 with the vehicle 10 on which the vehicle-mounted device that captures the vehicle-mounted camera image SIM1 is mounted. By performing such processing, the specific unit 134 is equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to the estimated image estimated from the surveillance camera image among a plurality of automobiles equipped with the in-vehicle camera. The automobile 10 can be specified. As a result, the specific unit 134 realizes the association between the target vehicle TC10 and the vehicle 10 by associating the target vehicle TC10 captured in the surveillance camera image with the vehicle ID of the specified vehicle 10. Then, the specifying unit 134 specifies the destination associated with the specified vehicle ID as the destination of the target vehicle TC10.

In addition, the identification unit 134 may perform the identification process based on the sameness between the date and time when the surveillance camera image was taken by the surveillance camera 20 and the date and time when the in-vehicle camera image was taken by the in-vehicle device of the automobile 10. For example, the specific unit 134 predicts that the similarity calculated based on the in-vehicle camera image and the estimated image is equal to or higher than a predetermined threshold value, the date and time when the in-vehicle camera image was taken, and the estimated image is taken. When the date and time to be set are within the same time (for example, within a few seconds), the target vehicle and the vehicle 10 equipped with the vehicle-mounted device that captured the vehicle-mounted camera image may be linked.

(About notification unit 135)
The notification unit 135 notifies various information. Specifically, the notification unit 135 notifies the vehicle specified by the specific unit 134 of information to be notified to the target vehicle. Here, the information to be notified is determined by analyzing the image taken by the surveillance camera.

For example, the notification unit 135 identifies the vehicle ID of the vehicle 10 specified by the specific unit 134. Then, the notification unit 135 makes various notifications with the destination associated with the specified vehicle ID as the destination of the target vehicle. For example, the notification unit 135 may notify information about the characteristics of the vehicle such as the color and shape of the vehicle that is a dangerous moving body and the name of the vehicle model. In addition, the notification unit 135 may notify information regarding the speed of the vehicle that is a dangerous moving object. Further, the notification unit 135 may notify the position of the vehicle which is a dangerous moving object estimated from the image.

For example, it is assumed that the specific unit 134 associates the target vehicle with the vehicle 10 identified by the vehicle ID "MO1". In such a case, the notification unit 135 specifies the destination "AD1" of the specified vehicle 10 as the destination of the target vehicle from the destination storage unit 122. Then, the notification unit 135 makes various notifications with the destination "AD1" as the destination of the target vehicle. For example, the notification unit 135 notifies that the non-connected vehicle CA1 is a dangerous mobile body. As a result of such processing, the target vehicle can perform various driving controls based on the information indicating the warning regarding the unconnected vehicle CA1 notified by the notification unit 135.

[4. Processing procedure]
Next, the procedure of the linking process executed by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart showing an example of the flow of the linking process executed by the information processing apparatus 100 according to the embodiment.

As shown in FIG. 8, the acquisition unit 131 acquires a surveillance camera image from the surveillance camera image providing device FIS (step S101). Then, the determination unit 132 determines the dangerous vehicle and the target vehicle from the surveillance camera image (step S102). When the determination unit 132 does not determine between the dangerous vehicle and the target vehicle from the surveillance camera image (step S102; No), the determination unit 132 returns to the front of step S101.

On the other hand, when the determination unit 132 determines between the dangerous vehicle and the target vehicle from the surveillance camera image (step S102; Yes), the estimation unit 133 estimates an estimated image that is predicted to be captured by the in-vehicle device of the target vehicle. (Step S103). Then, the specific unit 134 searches for an image similar to the estimated image estimated by the estimation unit 133 among the vehicle-mounted camera images (step S104). In addition, the identification unit 134 identifies an automobile that is a source of an in-vehicle camera image similar to the estimated image (step S105). Then, the notification unit 135 sets the destination of the specified vehicle as the destination of the target vehicle, and notifies the information of the alert (step S106).

[5. Modification example]
The information processing device 100 described above may be implemented in various different forms other than the above-described embodiment. Therefore, another embodiment of the information processing apparatus 100 will be described below.

[5-1. Mobile]
In the above embodiment, the automobile has been described as an example, but the present invention may be applied to any moving body instead of the automobile. For example, the moving body is a bicycle, a drone, a bus, a train, or the like. Further, the moving body may be a vehicle in which a non-connected vehicle becomes a connected vehicle by mounting a communication device, an information processing device, or the like attached later, or an autonomous driving vehicle or the like. That is, the connected vehicle may have a photographing function of photographing 360 ° including the front and the rear and a communication function of transmitting the photographed image (that is, an in-vehicle camera image) to the information processing device 100. It does not matter whether or not the vehicle can realize automatic driving.

[5-2. camera〕
In the above embodiment, the surveillance camera has been described as an example, but the surveillance camera may be any camera. For example, a surveillance camera is typically a camera installed outside the vehicle. For example, the surveillance camera may be a camera fixed to the roadside or a camera fixed to a building. Further, for example, the surveillance camera may be a camera mounted on a drone parked above the intersection. For example, the camera may be a depth camera, an infrared camera, or the like. Further, the information processing device 100 is a distance to a target vehicle measured by, for example, an infrared sensor or various radio wave sensors, in addition to a camera that acquires an image in which various pixels and image regions correspond to positions in the real world. The presence of the target vehicle was determined from the position and orientation in which the sensor was installed, sensor information that could be acquired by various sensors of the target vehicle was estimated, and the sensor information acquired from each vehicle 10 was estimated. The vehicle from which the sensor information similar to the sensor information is acquired may be associated with the target vehicle.

[5-3. In-vehicle device]
In the above embodiment, the vehicle-mounted device has been described as an example, but the vehicle-mounted device may be applied to any terminal device instead of the vehicle-mounted device. Specifically, the terminal device may be a terminal device or the like used by a user who accesses content such as a web page displayed on a browser or content for an application. For example, the terminal device may be a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), a smart watch, a wearable device, or the like. ..

Further, for example, the in-vehicle device has a function such as a GPS (Global Positioning System) sensor, detects the position information of the automobile, and acquires it at predetermined intervals (for example, once or more per second). For example, the location information may be the location information of the base station communicating with the vehicle, the automobile 10 estimated using the radio waves of WiFi (registered trademark) (Wireless Fidelity), or the like.

[5-4. Judgment processing Emergency vehicle]
In the above embodiment, the information processing device 100 has described an example of the determination process for determining whether or not the non-connected vehicle CA1 is a vehicle having a high possibility of causing a traffic accident from the surveillance camera image. Not limited to. Specifically, the information processing device 100 may determine whether or not the unconnected vehicle CA1 included in the surveillance camera image is an emergency vehicle such as an ambulance.

For example, the information processing device 100 analyzes the surveillance camera image by a conventional technique such as image analysis, so that the non-connected vehicle CA1 included in the surveillance camera image is an emergency vehicle based on the vehicle type, license plate, vehicle outline, and the like. Judge whether or not. Then, the information processing device 100 may determine the vehicle that can be an obstacle of the emergency vehicle from the surveillance camera image as the target vehicle, and notify the vehicle 10 associated with the determined target vehicle. In this way, the information processing apparatus 100 can determine the unconnected vehicle CA1 that is characteristic in various situations according to various situations. Thereby, for example, when the ambulance carries a suddenly ill person and heads for the hospital, the information processing device 100 can give a notification so that the automobile 10 does not interfere with the ambulance.

[5-5. Estimate processing Generate an estimated image from the position and the direction of travel]
In the above embodiment, the information processing apparatus 100 is photographed by an in-vehicle camera photographed by the surveillance camera 20 or mounted on a vehicle located in the vicinity of the surveillance camera 20 based on the surveillance camera image captured by the surveillance camera 20. Although an example of the estimation process for estimating the image is described, the present invention is not limited to the above estimation process. For example, the information processing device 100 may generate an estimated image based on the position and orientation of the target vehicle when generating an estimated image of the target vehicle from the surveillance camera image.

For example, the information processing device 100 estimates the position and orientation of the target vehicle from the surveillance camera image. Then, the information processing apparatus 100 may generate an image predicted to be captured by the in-vehicle device of the target vehicle as an estimated image by setting the estimated position as the viewpoint and the estimated direction as the direction of the gazing point. As described above, the information processing device 100 according to the embodiment generates an estimated image based on the position and orientation of the target vehicle, so that the accuracy of the estimated image can be improved.

[5-6. Specific processing (1) Automobile attribute information]
In the above embodiment, the information processing device 100 describes an example of specific processing for identifying a vehicle equipped with an in-vehicle camera that has captured an in-vehicle camera image corresponding to an estimated image among a plurality of vehicles equipped with the in-vehicle camera. However, it is not limited to the above specific processing. For example, it is assumed that the vehicle ID, the vehicle-mounted camera image, and the attribute information, which is information related to the attributes of the vehicle, are associated and stored in the vehicle-mounted camera image providing device SIS. In this case, the information processing device 100 estimates the attribute information of the target vehicle photographed by the surveillance camera 20, and the estimated attribute information of the target vehicle and the attribute information of the vehicle 10 acquired from the in-vehicle camera image providing device SIS. When the above is similar, the automobile 10 may be specified as the target automobile.

For example, it is assumed that information on the outer shape of the vehicle, the color of the vehicle, the type of the vehicle, the speed, and the like is acquired in advance from the vehicle-mounted camera image providing device SIS as the attribute information of the automobile 10. In this case, the information processing device 100 uses the estimated image as a search query and searches for the vehicle-mounted camera image corresponding to the estimated image from the vehicle-mounted camera image acquired from the vehicle-mounted camera image providing device SIS. At this time, the information processing device 100 identifies an in-vehicle camera image including the vehicle 10 showing the attribute information corresponding to the attribute information of the target vehicle included in the estimated image.

For example, when the attribute information of the target vehicle included in the estimated image and the attribute information of the vehicle 10 included in the vehicle-mounted camera image are the same or similar, the information processing device 100 has the target vehicle and the vehicle-mounted camera image. It is linked with the automobile 10 equipped with the in-vehicle device that photographed the image. As a result, the information processing apparatus 100 can perform specific processing with high accuracy.

[5-7. Specific processing (2) Dangerous acts other than automobiles]
In the above embodiment, the information processing device 100 describes an example of specific processing for identifying a vehicle equipped with an in-vehicle camera that has captured an in-vehicle camera image corresponding to an estimated image among a plurality of vehicles equipped with the in-vehicle camera. However, it is not limited to the above specific processing. For example, it is assumed that the distance between the bicycle, the child, the animal, or the like and the target vehicle is less than a predetermined distance. In this case, the information processing device 100 identifies a bicycle, a child, an animal, or the like from the surveillance camera image acquired from the surveillance camera 20 by using a conventional technique such as image analysis. In this case, the information processing device 100 identifies a vehicle in which a bicycle, a child, an animal, or the like is presumed to exist in the blind spot from the surveillance camera image acquired from the surveillance camera 20, and identifies the vehicle as the target vehicle. The destination of the associated vehicle 10 is specified as the destination of the target vehicle.

As described above, the information processing device 100 according to the embodiment can prevent a traffic accident by specifying the destination of the target vehicle even when a bicycle, a child, an animal, or the like jumps out. Conventionally, even if the automobile 10 has an in-vehicle camera, the bicycle, children, animals, etc. other than the automobile may enter a blind spot that cannot be grasped by the in-vehicle camera, and the in-vehicle camera may not be able to recognize the bicycle, children, animals, etc. rice field. In this case, if a bicycle, a child, an animal, or the like jumps out of the blind spot of the automobile 10, a traffic accident will be encountered. In response to this problem, the information processing device 100 can specify the destination of the target vehicle even when a bicycle, a child, an animal, or the like jumps out. As a result, the automobile 10 can prevent a traffic accident.

[5-8. Specific processing (3) Violating vehicle]
In the above embodiment, the information processing device 100 is an example of a specific process for identifying a vehicle 10 equipped with an in-vehicle camera that has captured an in-vehicle camera image corresponding to an estimated image among a plurality of vehicles equipped with the in-vehicle camera. Although described, the present invention is not limited to the above specific processing. For example, the information processing device 100 identifies a target vehicle that violates the stop prohibition based on the surveillance camera image taken by the surveillance camera 20. Further, the information processing device 100 is the specified target vehicle, and by performing the above-mentioned specific processing on the target vehicle that violates the stop prohibition, the vehicle 10 corresponding to the target vehicle that violates the stop prohibition. The car ID and the destination may be specified.

Then, the information processing device 100 may provide information regarding a claim for a fine or the like to the police or the like after a predetermined period from the specified automobile ID. Further, the information processing device 100 may store a flag in a predetermined storage unit, such as a dangerous vehicle that repeats violations, in association with the specified vehicle ID. When performing such processing, the information processing apparatus 100 does not have to perform notification using the specific result.

It should be noted that the above modification can be applied to a vehicle that violates any kind of vehicle instead of a vehicle that violates the prohibition of stopping. For example, the information processing device 100 identifies a target vehicle that violates the overtaking prohibition based on a surveillance camera image taken by the surveillance camera 20. Further, the information processing device 100 is the specified target vehicle, and the vehicle 10 of the vehicle 10 corresponding to the target vehicle that violates the overtaking prohibition by performing specific processing on the target vehicle that violates the overtaking prohibition. The ID and the destination may be specified.

[5-9. Specific processing (4) Identify unconnected vehicles that drive dangerously]
In the above embodiment, the information processing device 100 uses the external shape of the building included in the in-vehicle camera image, the relative position of the building estimated from other objects, the landscape, and the like, and the building included in the estimated image. An example of the process of calculating the similarity from the outer shape and the relative position of the building estimated from other objects and landscapes has been described, but the above-mentioned specific process is performed on any object instead of the building. May be applied. For example, the object may be a dangerous vehicle or the like.

Here, the specific process will be described with reference to FIG. FIG. 9 is a diagram showing a specific example of the specific processing executed by the information processing apparatus according to the modified example. The information processing device 100 identifies the destination of the vehicle 10 from which the vehicle-mounted camera image has been acquired by associating the dangerous vehicle included in the surveillance camera image with the dangerous vehicle included in the vehicle-mounted camera image (step S31).

For example, in the example of FIG. 9, the information processing device 100 acquires the surveillance camera image FIM2 including the automobile CA2 from the surveillance camera image providing device FIS as the surveillance camera image. At this time, the information processing device 100 identifies the automobile CA2 by using a conventional technique such as image analysis. It is assumed that the automobile CA2 included in the surveillance camera image FIM2 is a dangerous automobile.

Further, the information processing apparatus 100 acquires the on-board camera image SIM2 including the automobile CA2 as the in-vehicle camera image from the in-vehicle camera image providing device SIS. At this time, the information processing device 100 identifies the automobile CA2 by using a conventional technique such as image analysis. It is assumed that the automobile CA2 included in the in-vehicle camera image SIM2 is a dangerous automobile.

Then, the information processing device 100 uses a conventional technique such as image analysis, and is included in the surveillance camera image FIM2 based on the similarity of information such as the license plate, the type of the vehicle, the outer shape of the vehicle, and the color of the vehicle. It is determined that the CA2 and the automobile CA2 included in the vehicle-mounted camera image SIM2 are the same. For example, the information processing device 100 calculates the degree of similarity between the automobile CA2 included in the surveillance camera image FIM2 and the automobile CA2 included in the in-vehicle camera image SIM2.

For example, the information processing device 100 can be used for information such as the license plate of the automobile CA2 included in the surveillance camera image FIM2 and the automobile CA2 included in the in-vehicle camera image SIM2, the type of vehicle, the outer shape of the vehicle, and the color of the vehicle. Based on this, the similarity is calculated. The calculation process for calculating such similarity can be realized by conventional techniques such as image analysis and image matching. Further, the information processing apparatus 100 compares the feature amount extracted from the image of the automobile CA1 included in the surveillance camera image FIM2 with the feature amount extracted from the image of the automobile CA1 included in the in-vehicle camera image SIM2. Then, the similarity may be calculated. Then, the information processing apparatus 100 determines that the surveillance camera image FIM2 and the vehicle-mounted camera image SIM2 correspond to each other when the calculated similarity is equal to or higher than a predetermined threshold value.

Then, when the information processing device 100 determines that the surveillance camera image FIM2 and the vehicle-mounted camera image SIM2 correspond to each other, the information processing device 100 can identify the vehicle 10 equipped with the vehicle-mounted camera that captured the vehicle-mounted camera image SIM2. As a result, the information processing device 100 realizes that the vehicle ID of the specified vehicle 10 is specified by associating the surveillance camera image FIM2 with the vehicle-mounted camera image SIM2.

[5-10. Specific processing (5) Always specific]
In the above embodiment, the information processing device 100 is equipped with an in-vehicle device that captures an in-vehicle camera image corresponding to the estimated image when the surveillance camera 20 detects that the automobile 10 is likely to have a traffic accident. Although an example of the specific process for identifying the vehicle 10 as the target vehicle photographed by the surveillance camera 20, the specific process is not limited to the above-mentioned specific process. For example, the information processing device 100 is not limited to the case where the surveillance camera 20 detects that the automobile 10 is likely to have a traffic accident, but the estimated image is used as a search query and acquired from the in-vehicle camera image providing device SIS. The in-vehicle camera image corresponding to the estimated image is searched from the in-vehicle camera image, and the vehicle equipped with the in-vehicle device that captured the estimated image and the corresponding in-vehicle camera image is always specified as the target vehicle photographed by the surveillance camera 20. You may. As a result, the information processing device 100 can quickly identify an appropriate destination in advance, so that it is possible to prevent a traffic accident or the like.

[5-11. Notification processing (1) Notification content]
In the above embodiment, the information processing device 100 may notify any information as information indicating a warning regarding the unconnected vehicle. For example, information indicating a warning regarding a non-connected vehicle includes the characteristics of the non-connected vehicle such as the license plate, the type of the vehicle, the outer shape of the vehicle, the color of the vehicle, the estimated operating speed of the unconnected vehicle, and the unconnected vehicle. Includes location information, etc. In addition, the information indicating the warning regarding the non-connected vehicle includes control information regarding the traveling of the automobile 10.

[5-12. Notification processing (2) Notification mode]
In the above embodiment, the notification mode of the information indicating the alert regarding the unconnected vehicle may be any mode. For example, the notification mode may be a notification mode acquired only by the automobile 10. Further, the notification mode may be a mode that can be understood by the passengers of the automobile 10.

[5-13. Notification processing (3) Violating vehicle]
In the above embodiment, the information processing apparatus 100 has described an example of a notification process for notifying information indicating a warning regarding a non-connected vehicle, but the information processing device 100 is not limited to the above notification process. For example, the information processing device 100 stops the vehicle stop prohibition violation when the vehicle ID or the destination of the vehicle 10 which is the vehicle stop prohibition violation is specified by performing the linking process on the vehicle 10 which is the vehicle stop prohibition violation. The vehicle 10 may be notified of the content such as.

It should be noted that the above modification can be applied to the automobile 10 that violates any kind of violation instead of the automobile 10 that is a violation of the prohibition of stopping. For example, the information processing device 100 stops the overtaking prohibition violation when the automobile ID of the automobile 10 which is the overtaking prohibition violation and the destination are specified by performing the linking process on the automobile 10 which is the overtaking prohibition violation. The vehicle 10 may be notified of the content such as.

[6. Other embodiments]
In addition, other embodiments will be described. In the above-described embodiment, the information processing device 100 is a vehicle equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to an estimated image estimated from the surveillance camera image among a plurality of vehicles equipped with the in-vehicle camera. An example of the process of specifying is described. In another embodiment, the information processing device 100 identifies the vehicle 10 based on the license plate of the vehicle 10 included in the image when the image includes the vehicle 10 that is likely to be involved in a traffic accident. An example of is shown.

In another embodiment, it is assumed that the license plate of the automobile 10 and the destination of the automobile 10 are associated and stored in the storage unit. In this case, when the surveillance camera image includes the automobile 10 that is likely to be involved in a traffic accident, the information processing apparatus 100 identifies the automobile 10 based on the number plate of the automobile 10 included in the surveillance camera image. ..

For example, when the surveillance camera image includes a vehicle 10 that is likely to be involved in a traffic accident, the information processing device 100 is a vehicle specified by analyzing the surveillance camera image using a conventional technique such as image analysis. It is determined whether or not the number plate of 10 and the number plate of the automobile 10 stored in the storage unit match. Then, the information processing device 100 corresponds to the license plate when it is determined that the license plate of the automobile 10 identified by analyzing the surveillance camera image and the license plate of the automobile 10 stored in the storage unit match. The destination of the automobile 10 attached and stored is specified.

As described above, the information processing device 100 according to the other embodiment warns the automobile 10 that is likely to be involved in a traffic accident from the surveillance camera image taken by the surveillance camera 20. Provide a solution if you want to. For example, the information processing device 100 corresponds to the license plate when it is determined that the license plate of the automobile 10 identified by analyzing the surveillance camera image and the license plate of the automobile 10 stored in the storage unit match. The destination of the automobile 10 attached and stored is specified. As a result, the information processing device 100 can preferably identify a mobile body that satisfies a predetermined condition.

In addition, the relationship between the embodiment and other embodiments will be described below. The information processing device 100 according to the embodiment exerts an advantageous effect when the license plate of the automobile 10 cannot be identified from the surveillance camera image due to the angle relationship between the surveillance camera 20 and the automobile 10. For example, the information processing device 100 according to the embodiment may be a vehicle equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to an estimated image estimated from a surveillance camera image among a plurality of vehicles equipped with an in-vehicle camera. By specifying, the destination of the automobile can be preferably specified. In this way, the information processing device 100 according to the embodiment can specify the destination of the automobile 10 even when the license plate of the automobile 10 cannot be specified. That is, the information processing apparatus 100 according to the embodiment can provide information that supplements the processing performed by the information processing apparatus 100 according to the other embodiment.

[7. Hardware configuration]
Further, the in-vehicle device, the surveillance camera 20, the surveillance camera image providing device FIS, the in-vehicle camera image providing device SIS, and the information processing device 100 of the automobile 10 according to the above-described embodiment are, for example, a computer 1000 having a configuration as shown in FIG. Realized by. Hereinafter, the information processing device 100 will be described as an example. FIG. 10 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and the CPU 1100 transmits the data generated by the CPU 1100 via the network N to the other device.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the wearable device 200 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

[8. others〕
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed can be manually performed, or are described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically dispersed / physically distributed in any unit according to various loads and usage conditions. Can be integrated and configured. For example, the information processing device 100, the surveillance camera image providing device FIS, and the in-vehicle camera image providing device SIS may be integrated into one information processing device. In this case, the information processing device acquires a surveillance camera image taken from the surveillance camera 20, and acquires an in-vehicle camera image taken by the in-vehicle device of the automobile 10.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the specific unit can be read as a specific means or a specific circuit.

[9. effect〕
As described above, the information processing apparatus 100 according to the embodiment has an estimation unit 133 and a specific unit 134. Based on the surveillance camera image taken by the surveillance camera, the estimation unit 133 estimates an image taken by the surveillance camera or taken by an in-vehicle camera mounted on a vehicle located in the vicinity of the surveillance camera. The identification unit 134 identifies the vehicle equipped with the vehicle-mounted camera that has captured the vehicle-mounted camera image corresponding to the estimated image among the plurality of vehicles equipped with the vehicle-mounted camera.

As described above, the information processing apparatus 100 according to the embodiment is predetermined in order to identify the vehicle equipped with the vehicle-mounted camera that has captured the vehicle-mounted camera image corresponding to the estimated image among the plurality of vehicles equipped with the vehicle-mounted camera. A moving body satisfying the above conditions can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, the estimation unit 133 estimates an image taken by the in-vehicle camera mounted on the target vehicle taken by the surveillance camera as an estimated image, and the specific unit 134 has a plurality of specific units 134. Among the automobiles, the automobile equipped with the in-vehicle camera that captured the in-vehicle camera image corresponding to the estimated image is associated with the target automobile.

As a result, the information processing device 100 according to the embodiment is provided with a predetermined condition for associating the vehicle equipped with the vehicle-mounted camera that has captured the vehicle-mounted camera image corresponding to the estimated image among the plurality of vehicles and the target vehicle. A moving body satisfying the above conditions can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, the image captured by the vehicle-mounted camera and the information that can identify the vehicle on which the vehicle-mounted camera is mounted are associated and stored in the vehicle-mounted camera image storage unit SISM so as to be accessible. Then, the identification unit 134 searches the vehicle-mounted camera image storage unit SISM based on the estimated image, and identifies the vehicle equipped with the vehicle-mounted camera that has captured the vehicle-mounted camera image corresponding to the estimated image.

As a result, the information processing apparatus 100 according to the embodiment searches the vehicle-mounted camera image storage unit SISM based on the estimated image, and identifies the vehicle equipped with the vehicle-mounted camera that has captured the vehicle-mounted camera image corresponding to the estimated image. , A moving body satisfying a predetermined condition can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, the estimation unit 133 has a predetermined positional relationship with the dangerous vehicle when the other vehicle photographed by the surveillance camera is a dangerous vehicle having a high possibility of causing a traffic accident. The estimated image is estimated with the located vehicle as the target vehicle.

As a result, the information processing device 100 according to the embodiment sets the vehicle located in a predetermined positional relationship with the dangerous vehicle when the other vehicle photographed by the surveillance camera is a dangerous vehicle having a high possibility of causing a traffic accident. Since the estimated image is estimated as the target vehicle, a moving body satisfying a predetermined condition can be preferably specified.

Further, in the information processing device 100 according to the embodiment, when it is determined that the vehicle photographed by the surveillance camera violates the traffic rule, the estimation unit 133 estimates the estimated image with the vehicle as the target vehicle.

As a result, the information processing device 100 according to the embodiment estimates the estimated image of the vehicle as the target vehicle when it is determined that the vehicle photographed by the surveillance camera violates the traffic rules. A moving body satisfying the above conditions can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, the estimation unit 133 determines the surveillance camera image, the orientation of the surveillance camera when the surveillance camera is photographed, and the orientation of the in-vehicle camera of the target vehicle photographed by the surveillance camera. Based on the above, an image taken by an in-vehicle camera mounted on the target vehicle is estimated as an estimated image.

As a result, the information processing apparatus 100 according to the embodiment is based on the surveillance camera image, the orientation of the surveillance camera when the surveillance camera is photographed, and the orientation of the in-vehicle camera of the target vehicle photographed by the surveillance camera. Since the image taken by the in-vehicle camera mounted on the target vehicle is estimated as an estimated image, a moving body satisfying a predetermined condition can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, when the landmark is displayed on the surveillance camera, the estimation unit 133 estimates the estimated image based on how the landmark is displayed when viewed from the vehicle-mounted camera. , The identification unit 134 identifies and identifies, among a plurality of automobiles, an automobile equipped with an in-vehicle camera that captures an in-vehicle camera image showing the landmark so as to correspond to the appearance of the landmark in the estimated image. Link the car with the target car.

As a result, the information processing device 100 according to the embodiment is equipped with an in-vehicle camera that captures an in-vehicle camera image showing the landmark so as to correspond to the appearance of the landmark in the estimated image among a plurality of automobiles. Since the vehicle is specified and the specified vehicle is associated with the target vehicle, a moving body satisfying a predetermined condition can be preferably specified.

Further, in the information processing apparatus 100 according to the embodiment, when the automobile is reflected in the surveillance camera, the estimation unit 133 estimates the estimated image based on how the dangerous automobile is reflected when viewed from the in-vehicle camera. Among a plurality of automobiles, the identification unit 134 identifies an automobile equipped with an in-vehicle camera that captures an in-vehicle camera image showing the automobile so as to correspond to the appearance of the automobile in the estimated image, and identifies the automobile and the target. Link with a car.

As a result, the information processing device 100 according to the embodiment is equipped with an in-vehicle camera that captures an in-vehicle camera image of the dangerous vehicle so as to correspond to the appearance of the dangerous vehicle in the estimated image among the plurality of automobiles. Since the vehicle is specified and the specified vehicle is associated with the target vehicle, a moving body satisfying a predetermined condition can be preferably specified.

Further, the information processing device 100 according to the embodiment further includes a notification unit 135 for notifying the vehicle specified by the specific unit 134 of information to be notified to the target vehicle, and the information to be notified is a surveillance camera. It is determined by analyzing the images taken by.

As a result, the information processing device 100 according to the embodiment should notify the specified vehicle of the information to be notified to the target vehicle, which is determined by analyzing the image taken by the surveillance camera. In order to notify the information, it is possible to preferably identify a moving body that satisfies a predetermined condition.

Further, in the information processing device 100 according to the embodiment, the notification unit 135 notifies the automobile of information including warning information regarding the automobile having a high possibility of causing a traffic accident or control information regarding the traveling of the automobile.

As a result, the information processing device 100 according to the embodiment satisfies a predetermined condition in order to notify the automobile of information including alert information regarding the automobile having a high possibility of causing a traffic accident or control information regarding the traveling of the automobile. The moving body can be preferably specified.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

N network 1 Information processing system 10 Automobiles 20, 21, 22 Surveillance camera 100 Information processing device 110 Communication unit 120 Storage unit 121 Estimated image storage unit 122 Destination storage unit 130 Control unit 131 Acquisition unit 132 Judgment unit 133 Estimating unit 134 Specific unit 135 Notification unit FIS Surveillance camera image providing device FISM Surveillance camera image storage unit SIS In-vehicle camera image providing device SISM In-vehicle camera image storage unit

Claims (14)

An estimation unit that estimates an image taken by the surveillance camera or an image taken by an in-vehicle camera mounted on a vehicle existing in the vicinity of the surveillance camera based on the surveillance camera image taken by the surveillance camera.
An information processing device including a specific unit that identifies a vehicle equipped with an in-vehicle camera that captures an in-vehicle camera image corresponding to the estimated image among a plurality of vehicles equipped with an in-vehicle camera. The estimation unit
An image taken by the in-vehicle camera mounted on the target vehicle taken by the surveillance camera is estimated as an estimated image, and is estimated.
The specific part is
The information processing device according to claim 1, wherein among the plurality of automobiles, an automobile equipped with an in-vehicle camera that has captured an in-vehicle camera image corresponding to the estimated image is associated with the target automobile. An image taken by the in-vehicle camera and information that can identify the vehicle in which the in-vehicle camera is mounted are associated and stored in a storage unit that is accessible and connected.
The second aspect of claim 2, wherein the specific unit searches the storage unit based on the estimated image and identifies an automobile equipped with an in-vehicle camera that has taken an in-vehicle camera image corresponding to the estimated image. Information processing equipment. The estimation unit
The information processing device according to claim 2, wherein among the automobiles photographed by the surveillance camera, the automobile having a high possibility of being involved in a traffic accident is regarded as the target automobile, and the estimated image is estimated. The estimation unit
When the other vehicle photographed by the surveillance camera is a dangerous vehicle having a high possibility of causing a traffic accident, the estimated image is estimated with the vehicle located in a predetermined positional relationship with the dangerous vehicle as the target vehicle. The information processing apparatus according to claim 4, wherein the information processing device is characterized by the above. The estimation unit
The information processing apparatus according to claim 2, wherein when it is determined that the vehicle photographed by the surveillance camera violates the traffic rules, the estimated image is estimated with the vehicle as the target vehicle. .. The estimation unit
An in-vehicle camera mounted on the target vehicle based on the surveillance camera image, the orientation of the surveillance camera when the surveillance camera was taken, and the orientation of the in-vehicle camera of the target vehicle captured by the surveillance camera. The information processing apparatus according to any one of claims 2 to 6, wherein the image captured by the camera is estimated as an estimated image. When a landmark is shown on the surveillance camera,
The estimation unit
The estimated image is estimated based on how the landmark appears when viewed from the vehicle-mounted camera.
The specific part is
Among the plurality of automobiles, the automobile equipped with the in-vehicle camera that has taken the in-vehicle camera image showing the landmark so as to correspond to the appearance of the landmark in the estimated image is specified, and the identified automobile and the vehicle. The information processing device according to claim 2, wherein the information processing device is associated with the target vehicle. When the car is seen in the surveillance camera
The estimation unit estimates the estimated image based on how the vehicle looks when viewed from the vehicle-mounted camera.
Among the plurality of automobiles, the specific unit identifies and identifies an automobile equipped with an in-vehicle camera that captures an in-vehicle camera image showing the automobile so as to correspond to how the automobile is reflected in the estimated image. The information processing apparatus according to claim 4, wherein the vehicle is linked to the target vehicle. The estimation unit
A claim characterized in that an estimated image is estimated based on a first surveillance camera image taken by the first surveillance camera and a second surveillance camera image taken by a second surveillance camera different from the first surveillance camera. Item 4. The information processing apparatus according to any one of Items 1 to 9. A notification unit for notifying the vehicle specified by the specific unit of information to be notified to the target vehicle is further provided.
The information processing apparatus according to any one of claims 1 to 10, wherein the information to be notified is determined by analyzing an image captured by the surveillance camera. The notification unit
The information processing device according to claim 11, further comprising notifying the automobile of information including alerting information regarding an automobile having a high possibility of causing a traffic accident or control information regarding the running of the automobile. The way the computer does
Based on the surveillance camera image taken by the surveillance camera, an estimation step of estimating an image taken by the surveillance camera or taken by an in-vehicle camera mounted on an automobile existing in the vicinity of the surveillance camera, and an estimation process.
A method characterized by including a specific step of identifying a vehicle equipped with an in-vehicle camera that has taken an in-vehicle camera image corresponding to the estimated image among a plurality of vehicles equipped with an in-vehicle camera. An estimation procedure for estimating an image taken by the surveillance camera or an image taken by an in-vehicle camera mounted on a vehicle existing in the vicinity of the surveillance camera based on the surveillance camera image taken by the surveillance camera, and an estimation procedure.
Traffic characterized by having a computer execute a specific procedure for identifying a vehicle equipped with an in-vehicle camera that has taken an in-vehicle camera image corresponding to the estimated image among a plurality of vehicles equipped with an in-vehicle camera. Risk reduction program.

Images