Information processing device, information processing method, and recording medium

Abstract

Provided are: an information processing device, an information processing method, and a recording medium that make it possible to improve the efficiency of analysis of images captured by a camera or the like mounted on a mobile body.　The information processing device comprises: an object detection means for detecting a specific object appearing in an image captured by a camera mounted on the mobile body; an estimation means for estimating a grace period until the object approaches a predetermined distance on the basis of at least a movement state of the mobile body; a selection means for selecting an object to be analyzed on the basis of the grace period; an analysis means for analyzing a region in which the selected object appears; and an analysis request means for transmitting the image to a server capable of analyzing the image.

Description

Information processing device, information processing method, and recording medium

[0001] The present invention relates to an information processing device, an information processing method, and a recording medium.

[0002] Patent Literature 1 discloses a mobile body control device that can more appropriately control a mobile body. The mobile body control device described in this document includes a recognition unit that recognizes the surrounding situation of a mobile body, and a contact unavoidability determination unit that, when an object that may come into contact with the mobile body is present around the mobile body, determines whether contact between the mobile body and the object is unavoidable based on the recognition result by the recognition unit.

[0003] JP 2023-108224 A

[0004] As pointed out in Patent Document 1, when there are many objects around a moving body that may come into contact with the moving body, a processing load is placed on the moving body control device. For this reason, the moving body control device of Patent Document 1 reduces the frame rate when processing the entire area of ​​the camera image captured by the camera 10, and performs detailed analysis using partial images with a higher frame rate in important situations where it is important to determine whether or not contact between the vehicle and another vehicle is unavoidable. However, this method may result in omissions in the analysis of objects captured in other areas of the camera image.

[0005] An object of the present disclosure is to provide an information processing device, an information processing method, and a recording medium that can contribute to improving the efficiency of analysis of images captured by a camera or the like mounted on a moving object.

[0006] According to a first aspect, there is provided an information processing device including an object detection means for detecting a specific type of object captured in an image taken by a camera mounted on a moving body, an estimation means for estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body, a selection means for selecting an object to be analyzed based on the grace period, an analysis means for analyzing an area in which the selected object is captured, and an analysis request means for transmitting the image to a server capable of analyzing the image.

[0007] According to a second aspect, there is provided an information processing method that detects a specific type of object captured in an image taken by a camera mounted on a moving body, estimates a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body, selects an object to be analyzed based on the grace period, analyzes an area in which the selected object is captured, transmits the image to a server capable of analyzing images, and receives from the server an analysis result of the image of an area in which an object is captured with a grace period equal to or greater than a predetermined threshold.

[0008] According to a third aspect, there is provided a recording medium having recorded thereon a program that causes a computer to execute the following processes: detecting a specific type of object that appears in an image captured by a camera mounted on a moving body; estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body; selecting an object to be analyzed based on the grace period; analyzing an area in which the selected object appears; transmitting the image to a server capable of analyzing images; and receiving from the server an analysis result of the image of an area in which an object appears whose grace period is equal to or exceeds a predetermined threshold.

[0009] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and a recording medium that can contribute to improving the efficiency of analysis of images captured by a camera or the like mounted on a moving body.

[0010] FIG. 1 is a diagram showing one configuration of the present disclosure. FIG. 2 is a flow chart showing the operation of the present disclosure. FIG. 3 is a diagram for explaining the operation of the present disclosure. FIG. 4 is a diagram for explaining the operation of the present disclosure. FIG. 5 is a diagram showing one configuration of the present disclosure. FIG. 6 is a functional block diagram showing the configuration of an in-vehicle terminal of the present disclosure. FIG. 7 is a sequence diagram for explaining the operation of the present disclosure. FIG. 8 is a diagram for explaining the operation of the present disclosure. FIG. 9 is a functional block diagram showing another configuration of an in-vehicle terminal of the present disclosure. FIG. 10 is an example of a table used by the in-vehicle terminal of the present disclosure to calculate a grace time. FIG. 11 is a diagram showing one configuration of the present disclosure. FIG. 12 is a diagram showing the configuration of a computer constituting an information processing device or an in-vehicle terminal of the present disclosure.

[0011] First, an overview of one embodiment of the present disclosure will be described with reference to the drawings. In this disclosure, the drawings relate to one or more embodiments. The reference numerals in the drawings attached to this overview are attached to each element for convenience as an example to facilitate understanding, and are not intended to limit the present disclosure to the illustrated form. Furthermore, connecting lines between blocks in the drawings and the like referred to in the following description include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of main signals (data) and do not exclude bidirectionality. A program is executed via a computer device, which includes, for example, a processor, a storage device, an input device, a communication interface, and, if necessary, a display device. Furthermore, this computer device is configured to be able to communicate with internal or external devices (including computers) via the communication interface, whether wired or wireless. Although ports or interfaces are present at the input / output connection points of each block in the drawings, they are not shown.

[0012] In one embodiment, the present disclosure can be realized by an information processing device 10 including, as shown in FIG. 1 , an object detection means 11, an estimation means 12, a selection means 13, an analysis means 14, and an analysis request means 15. More specifically, the object detection means 11 detects a specific type of object captured in an image captured by a camera C mounted on a moving body V. The estimation means 12 estimates a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body. The selection means 13 selects an object to be analyzed based on the grace period. The analysis means 14 analyzes an area in which the selected object is captured. The analysis request means 15 transmits the image captured by the camera C to an image analysis server 20.

[0013] The information processing device 10 configured as described above operates as follows: First, the information processing device 10 detects a specific type of object in an image captured by a camera C mounted on a moving object (step S01 in FIG. 2).

[0014] Next, the information processing device 10 estimates a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body (step S02 in FIG. 2). Examples of the movement status of the moving body include the movement direction, speed, and acceleration of the vehicle equipped with camera C. The movement direction may be estimated from the steering angle, acceleration direction, turn signal direction, etc. of the vehicle. Based on the speed and movement direction of the vehicle, the information processing device 10 estimates a grace period until the object captured by camera C approaches within a predetermined distance. Note that the movement direction and movement speed of the object captured by camera C may be taken into consideration when estimating this grace period.

[0015] Next, the information processing device 10 selects an object to be analyzed based on the estimated grace period (step S03 in FIG. 2). If multiple objects are detected in step S01, the information processing device 10 selects, from among these multiple objects, an object with a shorter grace period as the object to be analyzed. Note that multiple objects may be selected.

[0016] Next, the information processing device 10 analyzes the area in which the selected object is captured (step S04 in FIG. 2). Finally, the information processing device 10 transmits the image captured by the camera C to the image analysis server 20 (step S05 in FIG. 2).

[0017] In the example of Figure 2, after steps S01 to S04 in Figure 2, an image is sent to the image analysis server 20, but the processing of steps S01 to S04 in Figure 2 may be performed after the image is sent to the image analysis server 20, or both may be performed in parallel.

[0018] 3 and 4 are diagrams illustrating the operation of the present disclosure. FIG. 3 shows a state in which persons P1 and P2 are captured in an image captured by camera C. When the information processing device 10 detects persons P1 and P2, it estimates the grace period until each of them approaches within a predetermined distance based on the movement status of the moving object. For example, since person P1 is located far from the moving object, the grace period until the person approaches within the predetermined distance is estimated to be long. On the other hand, since person P2 is located nearby, the grace period until the person approaches within the predetermined distance is estimated to be short. In this case, the information processing device 10 selects person P2, whose grace period is short, as the analysis target. Then, the information processing device 10 analyzes the area in which person P2 is captured and predicts, for example, the behavior of person P2. This allows the information processing device 10 to evaluate the possibility of crossing with person P2 and take measures to avoid this. Furthermore, the information processing device 10 transmits an image including person P1, whose grace period is long, to the image analysis server 20 and requests analysis. This will result in a delay in the analysis of the area containing person P1, but as mentioned above, since person P1 is located far from the moving object, there is little problem even if there is a delay in the analysis when comparing with person P2.

[0019] FIG. 4 shows an image captured by camera C in which persons P3 and P4 are captured. When the information processing device 10 detects persons P3 and P4, it estimates the grace period until each of them approaches within a predetermined distance based on the movement status of the moving object. For example, if the moving object is about to turn right as indicated by the arrow in FIG. 4, person P3 will be moving away from the moving object, and therefore the grace period until the person approaches within the predetermined distance is estimated to be long. On the other hand, person P4 will be approaching the moving object, and therefore the grace period until the person approaches within the predetermined distance is estimated to be short. In this case, the information processing device 10 selects person P4, whose grace period is short, as the analysis target. The information processing device 10 then analyzes the area in which person P4, whose grace period is short, is captured, and predicts, for example, the behavior of person P4. This allows the information processing device 10 to evaluate the possibility of crossing with person P4 and take measures to avoid this. Furthermore, the information processing device 10 transmits an image including person P3, whose grace period is long, to the image analysis server 20 and requests analysis. This will result in a delay in the analysis of the area containing person P3, but as mentioned above, person P3 is likely to move away from the moving object, so a delay in analysis when comparing with person P4 is not a major problem.

[0020] As described above, according to the present disclosure, it is possible to improve the efficiency of analyzing images captured by a camera C or the like mounted on a moving body.

[0021] [First Embodiment] Next, a first embodiment will be described in which image analysis processing is efficiently shared between an in-vehicle terminal on the camera C side and an image analysis server. Fig. 5 is a diagram showing one configuration of the present disclosure. Referring to Fig. 5, a configuration is shown that includes a vehicle V equipped with a camera C, an in-vehicle terminal 100 mounted on the vehicle, and an image analysis server 200 that can receive images from the in-vehicle terminal 100 via a network N. The in-vehicle terminal 100 and the image analysis server 200 share the analysis of images captured by the camera C.

[0022] 6 is a functional block diagram showing the configuration of the in-vehicle terminal 100 of the present disclosure. Referring to FIG. 6, the configuration includes an object detection unit 101, an estimation unit 102, a selection unit 103, an analysis unit 104, and an analysis request unit 105.

[0023] The object detection unit 101 detects objects captured in images captured by a camera C mounted on the vehicle V. Furthermore, the object detection unit 101 extracts, from the detected objects, objects of a type that can be the subject of pre-set image analysis, and sends them to the estimation unit 102. Traffic participants such as pedestrians, automobiles, and bicycles can be set as the types of objects that can be the subject of image analysis. The object detection unit 101 corresponds to the object detection means 11 described above.

[0024] The estimation unit 102 identifies the position of an object in real space from the position of the object captured in the image. Furthermore, the estimation unit 102 grasps the movement status of the vehicle V from position information of the vehicle V obtained by the vehicle V's GPS (Global Positioning System) or GNSS (Global Navigation Satellite System). Based on this information, the estimation unit 102 estimates a grace period for each object captured in the image to approach within a predetermined distance from the vehicle V. The movement status of the vehicle V may be calculated based on values ​​from a speed sensor or an acceleration sensor in addition to using information from the GPS or GNSS. Furthermore, if the movement direction and speed of each object captured in the image can be identified from a dynamic map or the like, the grace period may be calculated taking these into consideration. The estimation unit 102 corresponds to the estimation means 12 described above.

[0025] The selection unit 103 selects objects to be subjected to image analysis based on the grace period estimated for each object captured in the image. An example of a rule for selecting objects to be subjected to image analysis is a rule for selecting objects with a relatively short estimated grace period. In this case, the selection unit 103 may select multiple objects to be subjected to image analysis. In this case, the selection unit 103 may prioritize the multiple objects. Furthermore, the selection unit 103 may determine the priority based on the object type in addition to the grace period. Furthermore, when multiple objects are detected, the selection unit 103 may also prioritize the object with a higher priority as a type. Furthermore, a rule for selecting objects to be subjected to image analysis may be a rule for selecting objects with the estimated grace period less than a predetermined threshold. The selection unit 103 corresponds to the selection means 13 described above.

[0026] The analysis unit 104 performs image analysis on the area containing the object selected by the selection unit 103 and transmits the results to the vehicle's control unit. For example, the analysis unit 104 may perform image analysis on the area containing the selected object and predict the behavior of the object in the image. This behavior prediction can be performed using various image-based behavior prediction techniques. Furthermore, the analysis unit 104 can also use a large-scale language model capable of performing image analysis or a VLM (Vision-Language Model). An example of a VLM capable of scene analysis is LLaVA (Large Language and Vision Assistant). The analysis unit 104 corresponds to the analysis means 14 described above.

[0027] If the behavior prediction determines that there is a high possibility that a pedestrian will suddenly jump out into the road, it becomes possible to make an emergency stop of the vehicle V. Similarly, if the behavior prediction determines that there is a high possibility that a vehicle diagonally ahead will suddenly change lanes, it becomes possible to make the vehicle V change lanes or slow down. Note that if there are multiple objects selected by the selection unit 103 and each object has been assigned a priority, the analysis unit 104 will perform image analysis in accordance with the priority.

[0028] The analysis request unit 105 transmits images captured by the camera C to the image analysis server 200 connected via the network N and requests analysis. When the analysis request unit 105 requests image analysis from the image analysis server 200, it may specify an object that was not analyzed by the analysis unit 104, request image analysis, and receive the results. For example, when analyzing objects with a grace period shorter than a predetermined threshold, the in-vehicle terminal 100 requests the image analysis server 20 to analyze objects with a grace period equal to or greater than the predetermined threshold. In this way, objects with a long grace period that were not analyzed by the in-vehicle terminal V can be included as objects to be analyzed. The analysis request unit 105 corresponds to the analysis request means 15 described above.

[0029] The image analysis server 200 is a server capable of analyzing images, and performs image analysis on the images captured by the camera C received from the in-vehicle terminal 100. The image analysis server 200 then transmits the results of the image analysis to the in-vehicle terminal 100.

[0030] Next, the operation of this embodiment will be described in detail with reference to the drawings. Fig. 7 is a sequence diagram for explaining the operation of the present disclosure. Referring to Fig. 7, first, the in-vehicle terminal 100 detects a specific type of object from an image captured by the camera C (step S001).

[0031] Next, the on-board terminal 100 acquires the vehicle's movement status (step S002). Next, the on-board terminal 100 estimates, for each object shown in the image, the time until the object approaches within a predetermined distance from the vehicle V, based on the position of the object shown in the image and the vehicle's movement status (step S003).

[0032] Next, the in-vehicle terminal 100 selects an object to be subjected to image analysis based on the estimated grace period (step S004), and then performs image analysis on the area in which the selected object is captured (step S005).

[0033] In parallel with the image analysis, the in-vehicle terminal 100 transmits the image captured by the camera C to the image analysis server 200 and requests the image analysis server 200 to analyze it (step S006).

[0034] The image analysis server 200, which has received the request to analyze the image, analyzes the image received from the in-vehicle terminal 100 (step S007). Then, the image analysis server 200 transmits the image analysis results to the in-vehicle terminal 100 (step S008).

[0035] FIG. 8 is a diagram illustrating the operation of the present disclosure. Objects A1 to A5 in FIG. 8 represent objects detected by the object detection unit 101. The estimation unit 102 estimates the grace period for objects A1 to A5 to approach a predetermined distance from vehicle V based on the positions of objects A1 to A5 captured in the image and the vehicle's movement status. The arrows in FIG. 9 indicate the path of vehicle V estimated from its movement status. The estimation unit 102 estimates the grace period taking this movement status into consideration. In the example of FIG. 9, object A5 is moving away from vehicle V and does not intersect with the path of vehicle V, so it is not included in the calculation of the grace period. Furthermore, object A4 is waiting for a traffic light just before an intersection and does not intersect with the path of vehicle V, so it is not included in the calculation of the grace period. In the example of FIG. 9, objects A1, A2, and A3 are subject to image analysis on the edge side (on the in-vehicle terminal 100) in the order of the grace period. Then, the image analysis server 200 is requested to perform image analysis on the objects A4 and A5, which were not included in the calculation of the grace period.

[0036] 9, when the upper limit number of objects to be analyzed is 2, objects A1 and A3 become the objects to be analyzed on the edge side (on the in-vehicle terminal 100 side) in the order of the grace period. Then, the image analysis server 200 is requested to perform image analysis on objects A2, A4, and A5, which were not included in the calculation of the grace period.

[0037] As described above, according to the present disclosure, it is possible to improve the efficiency of the analysis of images captured by the camera C of the vehicle V. The reason for this is that a configuration is adopted in which the time until each object in the image approaches within a predetermined distance is estimated, and priority is given to analyzing the image of an object with a short time until the object approaches within a predetermined distance.

[0038] [Second Embodiment] Next, a second embodiment will be described in which a change has been made to the method of calculating the grace period. Fig. 10 is a functional block diagram showing another configuration of the on-board terminal 100a of the present disclosure. The difference from the on-board terminal 100 of the first embodiment shown in Fig. 6 is the method of calculating the grace period in the estimation unit 102a. Since the other configurations are almost the same as those of the first embodiment, the following description will focus on the differences in operation.

[0039] The estimation unit 102a calculates the grace period using a value set for each object as the predetermined distance when estimating the grace period until an object approaches within a predetermined distance. FIG. 11 shows an example of a table used by the estimation unit 102a of the present disclosure to calculate the grace period. In the example of FIG. 11, the reference distances are set to 1 m for pedestrians, 2 m for vehicles, and 2 m for bicycles. In this case, the estimation unit 102a estimates the grace period until an object approaches within the predetermined distance (1 m) for pedestrians. Furthermore, the estimation unit 102a estimates the grace period until an object approaches within the predetermined distance (2 m) for vehicles and bicycles. In this way, by setting different reference distances for each type of object, the grace period for a specific type of object can be adjusted to a shorter value. As a result, a specific type of object can be more likely to be selected as a target for image analysis. For example, in the example of FIG. 11, the reference distance for vehicles and bicycles is set to a longer value. Therefore, even if the pedestrian and the vehicle (or bicycle) are located at the same distance from the vehicle V, the grace period for the vehicle (or bicycle) is shorter.

[0040] According to this embodiment, the in-vehicle terminal 100a can be made to preferentially select a specific type of object as a target for image analysis.

[0041] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and further modifications, substitutions, and adjustments can be made without departing from the basic technical concept of the present disclosure. For example, the network configurations, element configurations, and data representation formats shown in the drawings are examples intended to aid in understanding the present disclosure, and are not limited to the configurations shown in these drawings.

[0042] For example, in the first and second embodiments described above, the information processing device is an in-vehicle terminal 100 or 100a. However, other devices may be equipped with the functionality of an information processing device. For example, as shown in FIG. 12 , a roadside device installed on a roadside may be provided with the functionality of the information processing device of the present disclosure. In this case, the roadside device 300 includes an object detection unit 301, an estimation unit 302, a selection unit 303, an analysis unit 304, and an analysis request unit 305. The roadside device 300 detects a specific type of object captured in an image captured by a camera C and estimates a grace period until the detected object approaches within a predetermined distance. The roadside device 300 then selects an object to be analyzed based on this grace period.

[0043] (Hardware Configuration) In each embodiment of the present disclosure, each component of each device represents a functional unit block. Some or all of the components of each device are realized by an arbitrary combination of an information processing device 900 and a program, for example, as shown in FIG. 13. FIG. 13 is a block diagram showing an example of the hardware configuration of the information processing device 900 that realizes each component of each device. The information processing device 900 includes, as an example, the following configuration: - CPU (Central Processing Unit) 901 - ROM (Read Only Memory) 902 - RAM (Random Access Memory) 903 - Program 904 loaded into RAM 903 - Storage device 905 that stores the program 904 - Drive device 907 that reads and writes to a recording medium 906 - Communication interface 908 that connects to a communication network 909 - Input / output interface 910 that inputs and outputs data - Bus 911 that connects each component

[0044] Each component of each device in each embodiment is realized by the CPU 901 acquiring and executing a program 904 that realizes these functions. That is, the CPU 901 in FIG. 13 executes an object detection program and an analysis target selection program, and performs an update process for each calculation parameter stored in the RAM 903, the storage device 905, etc. The program 904 that realizes the function of each component of each device is stored in the storage device 905 or the ROM 902 in advance, for example, and is read by the CPU 901 as needed. The program 904 may be supplied to the CPU 901 via the communication network 909, or may be stored in advance on the recording medium 906, and the drive device 907 may read the program and supply it to the CPU 901.

[0045] There are various variations in the method of realizing each device. For example, each device may be realized by any combination of a separate information processing device 900 and a program for each component. Furthermore, multiple components of each device may be realized by any combination of a single information processing device 900 and a program. In other words, each unit (processing means, function) of the information processing device described above can be realized by a computer program that causes a processor installed in the device to execute each of the above processes using its hardware.

[0046] In addition, some or all of the components of each device may be realized by other general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus.

[0047] Some or all of the components of each device may be realized by a combination of the above-mentioned circuits and programs.

[0048] When some or all of the components of each device are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each device is connected via a communication network.

[0049] It should be noted that the above-described embodiments are preferred embodiments of the present disclosure, and the scope of the present disclosure is not limited to only the above-described embodiments. In other words, those skilled in the art can modify or substitute the above-described embodiments to construct various modified forms without departing from the gist of the present disclosure.

[0050] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0051] [Supplementary Note 1] An information processing device including: object detection means for detecting a specific type of object captured in an image captured by a camera mounted on a moving object; estimation means for estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving object; selection means for selecting an object to be analyzed based on the grace period; analysis means for analyzing an area in which the selected object is captured; and analysis request means for transmitting the image to a server capable of analyzing images. [Supplementary Note 2] The estimation means of the information processing device described above may further estimate the movement direction and movement speed of the object from the image, and estimate the grace period based on the movement status of the moving object and the movement direction and movement speed of the object. [Supplementary Note 3] The information processing device described above may be configured to be able to set different values ​​for the predetermined distance based on the type of the object. [Supplementary Note 4] The selection means of the information processing device described above may determine a priority order for the objects to be analyzed based on the type of the object or the grace period, and the analysis means may perform analysis of the area based on the priority order. [Supplementary Note 5] The analysis means of the above-mentioned information processing device may be configured to predict the behavior of the object based on an image of the object captured in the area. [Supplementary Note 6] The analysis request means of the above-mentioned information processing device may be configured to receive from the server an analysis result of the image of an area in which an object whose grace period is equal to or greater than a predetermined threshold is captured. [Supplementary Note 7] An information processing method comprising: detecting a specific type of object captured in an image taken by a camera mounted on a moving object; estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving object; selecting an object to be analyzed based on the grace period; analyzing the area in which the selected object is captured; and transmitting the image to a server capable of analyzing images; and receiving from the server an analysis result of the image of the area in which an object whose grace period is equal to or greater than a predetermined threshold is captured.[Supplementary Note 8] A recording medium storing a program causing a computer to execute the following steps: detecting a specific type of object in an image captured by a camera mounted on a moving object; estimating a grace period until the object approaches a predetermined distance based on at least the movement status of the moving object; selecting an object to be analyzed based on the grace period; analyzing an area in which the selected object is captured; transmitting the image to a server capable of analyzing images; and receiving from the server an analysis result of the image in an area in which an object whose grace period is equal to or exceeds a predetermined threshold. Note that the embodiments described in each of the above Supplements can be combined with each other after making necessary modifications. For example, a configuration that combines the contents of Supplementary Note 2 and Supplementary Note 3 is also within the scope of the present specification. In this case, the information processing device estimates a grace period until the object approaches the reference distance using a reference distance set for each type of object. Note that the embodiments of Supplements 7 to 8 can be expanded into the embodiments of Supplements 2 to 6, as in Supplementary Note 1.

[0052] The disclosures of the above-cited patent documents are incorporated herein by reference and may be used as the basis or part of this disclosure, as necessary. Modifications and adjustments of the embodiments and examples are possible within the scope of this disclosure (including the claims), and further based on its basic technical concept. Furthermore, various combinations and selections (including partial deletions) of various disclosed elements (including elements of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible within the scope of this disclosure. In other words, this disclosure naturally includes various modifications and alterations that would be possible by a person skilled in the art in accordance with the entire disclosure, including the claims, and the technical concept. In particular, with regard to the numerical ranges described herein, any numerical value or subrange within that range should be construed as specifically described, even if not otherwise specified. Furthermore, the disclosures of the above-cited documents, when used in part or in whole in combination with the disclosures herein as part of this disclosure, in accordance with the spirit of this disclosure, are also deemed to be included in the disclosures of this application.

[0053] REFERENCE SIGNS LIST 11 object detection means 12 estimation means 13 selection means 14 analysis means 15 analysis request means 100, 100a vehicle-mounted terminal 101, 301 object detection unit 102, 102a, 302 estimation unit 103, 303 selection unit 104, 304 analysis unit 105, 305 analysis request unit 200 image analysis server 300 roadside device 900 information processing device 901 CPU (Central Processing Unit) 902 ROM (Read Only Memory) 903 RAM (Random Access Memory) 904 program 905 storage device 906 recording medium 907 drive device 908 communication interface 909 communication network 910 Input / output interface 911 Bus A1 to A5 Object C Camera P1 to P4 Person V Vehicle

Claims

1. An information processing device comprising: an object detection means for detecting a specific type of object captured in an image taken by a camera mounted on a moving body; an estimation means for estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body; a selection means for selecting an object to be analyzed based on the grace period; an analysis means for analyzing an area in which the selected object is captured; and an analysis request means for transmitting the image to a server capable of analyzing images.

2. The information processing device according to claim 1, wherein said estimation means further estimates the moving direction and moving speed of said object from said image, and estimates said grace period based on the moving status of said moving body and the moving direction and moving speed of said object.

3. An information processing device according to claim 1 or 2, wherein the predetermined distance can be set to a different value depending on the type of the object.

4. An information processing device according to any one of claims 1 to 3, wherein the selection means determines the priority of the objects to be analyzed based on the type of the object or the grace period, and the analysis means performs analysis of the area based on the priority.

5. An information processing device according to any one of claims 1 to 4, wherein said analysis means predicts the behavior of said object based on the image of said object captured in said area.

6. An information processing device according to any one of claims 1 to 5, wherein the analysis requesting means receives from the server an analysis result of the image of an area in which an object having a grace period equal to or greater than a predetermined threshold is displayed.

7. An information processing method comprising: detecting a specific type of object in an image taken by a camera mounted on a moving body; estimating a grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body; selecting an object to be analyzed based on the grace period; analyzing an area in which the selected object is captured; transmitting the image to a server capable of analyzing images; and receiving from the server an analysis result of the image in an area in which an object with a grace period equal to or greater than a predetermined threshold is captured.

8. A recording medium having recorded thereon a program that causes a computer to execute the following processes: detecting a specific type of object captured in an image taken by a camera mounted on a moving body; estimating the grace period until the object approaches within a predetermined distance based on at least the movement status of the moving body; selecting an object to be analyzed based on the grace period; analyzing the area in which the selected object is captured; transmitting the image to a server capable of analyzing images; and receiving from the server the analysis results of the image of the area in which an object is captured with a grace period equal to or greater than a predetermined threshold.

Images