Information processing device

Abstract

To enable more accurate driving assessment.SOLUTION: An information processing device provided herein is configured to: extract dangerous situation image data that satisfies given conditions from assessment target driving data; confirm each dangerous situation image as to whether the image is associated with an acceleration greater than or equal to a first value or not; and determine driving associated with dangerous situation images that are confirmed to be not associated with acceleration greater than or equal to the first value, to be good driving.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device. [Background technology]

[0002] Various techniques have been developed to evaluate driving (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-38513 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional technologies only detect dangerous driving, such as sudden braking and sudden steering, and rate such dangerous driving poorly. In other words, conventional technologies only rate driving based on driving safety, and do not rate driving based on driving technique.

[0005] One example of a problem to be solved by the present invention is to perform a more accurate driving evaluation. [Means for solving the problem]

[0006] In order to solve the above problem, the invention described in claim 1 comprises a dangerous situation image extraction unit that extracts dangerous situation images that meet specified conditions from the driving data to be evaluated, an acceleration confirmation unit that confirms for each of the dangerous situation images whether the dangerous situation image is accompanied by an acceleration of a first value or more, and a driving evaluation unit that evaluates driving related to a dangerous situation image that is confirmed by the acceleration confirmation unit to not be accompanied by an acceleration of the first value or more as excellent driving.

[0007] The invention described in claim 7 is an information processing method executed by a computer, comprising: a danger situation image extraction step of extracting danger situation image data that meets predetermined conditions from the driving data to be evaluated; an acceleration confirmation step of confirming, for each of the danger situation images, whether the danger situation image involves an acceleration of a first value or more; and a driving evaluation step of evaluating, as excellent driving, driving related to a danger situation image that has been confirmed by the acceleration confirmation unit to not involve an acceleration of the first value or more.

[0008] The invention described in claim 8 causes the information processing method described in claim 7 to be executed by a computer.

[0009] The invention as recited in claim 9 stores the information processing program as recited in claim 8. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an information processing device 100 according to an embodiment of the present invention. [Figure 2] 1 is a diagram showing the relationship between an information processing device 100 and an automobile AM that is the subject of a driving evaluation. [Figure 3] FIG. 2 is a diagram illustrating a control unit 110 according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing a processing operation in an information processing device 100 according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] An information processing device according to one embodiment of the present invention includes a risk-situation image extraction unit that extracts risk-situation images that satisfy predetermined conditions from the driving data to be evaluated, an acceleration confirmation unit that checks whether each of the risk-situation images is accompanied by an acceleration of a first value or greater, and a driving evaluation unit that evaluates driving related to a risk-situation image that is confirmed by the acceleration confirmation unit to not be accompanied by an acceleration of the first value or greater as excellent driving. Therefore, in this embodiment, by setting the predetermined condition to "an image indicating the occurrence of a dangerous situation," it is possible to evaluate driving in which the driver did not suddenly brake or swerve despite the occurrence of a dangerous situation as excellent driving. Therefore, it is possible to highly evaluate the driving of a driver who avoids sudden braking or abrupt steering despite the occurrence of a dangerous situation through high driving skills, thereby enabling more accurate driving evaluation.

[0012] The predetermined condition may be at least one of the following: a sudden oncoming vehicle, sudden braking by a preceding vehicle, a sudden cut-in by a vehicle traveling in a parallel lane, a bicycle, or a pedestrian. By doing so, it becomes possible to evaluate as excellent driving a driver who did not suddenly brake or steer despite the occurrence of a dangerous situation such as a sudden oncoming vehicle, sudden braking by a preceding vehicle, a sudden cut-in by a vehicle traveling in a parallel lane, or a bicycle or pedestrian.

[0013] The information processing device may further include a training data acquisition unit that acquires training data, which is data related to images that satisfy the predetermined conditions, and the dangerous situation image extraction unit may extract the dangerous situation image data using the training data. In this way, it becomes possible to extract dangerous situation images using AI (artificial intelligence) technology.

[0014] The information processing device may further include a traveling data storage unit that stores traveling data of a plurality of vehicles, and a teacher data extraction unit that extracts, from the stored traveling data, images that involve acceleration equal to or greater than a second value and satisfy the predetermined condition, and extracts data related to the images as the teacher data. In this way, it becomes possible to extract teacher data from the large amount of stored traveling data. As a result, it becomes possible to obtain a large amount of teacher data.

[0015] A server device according to one embodiment of the present invention includes a travel data storage unit that stores travel data of a plurality of vehicles, and a teacher data extraction unit that extracts, from the stored travel data, images that involve acceleration equal to or greater than a second value and satisfy predetermined conditions, and extracts data related to the images as teacher data. Therefore, in this embodiment, it is possible to extract teacher data from the large amount of accumulated travel data. As a result, it is possible to obtain a large amount of teacher data.

[0016] A system according to one embodiment of the present invention includes the information processing device and the server device. Therefore, in this embodiment, it is possible to evaluate driving in which a driver does not suddenly brake or swerve despite a dangerous situation occurring as excellent driving. Therefore, it is possible to highly evaluate the driving of a driver who avoids sudden braking or abrupt steering despite a dangerous situation occurring through high driving skills. Furthermore, it is possible to extract training data from a large amount of accumulated driving data, and it is possible to extract dangerous situation images based on the large amount of training data. As a result, this embodiment allows for more accurate driving evaluation.

[0017] Furthermore, an information processing method according to one embodiment of the present invention is an information processing method executed by a computer, and includes a dangerous situation image extraction step of extracting dangerous situation image data that meets predetermined conditions from the evaluation target driving data, an acceleration confirmation step of confirming whether each of the dangerous situation images is accompanied by an acceleration of a first value or greater, and a driving evaluation step of evaluating driving related to a dangerous situation image that is confirmed by the acceleration confirmation unit to not be accompanied by an acceleration of the first value or greater as excellent driving. Therefore, in this embodiment, by setting the predetermined condition to "an image indicating the occurrence of a dangerous situation," it is possible to evaluate driving in which the driver did not perform sudden braking or abrupt steering despite the occurrence of a dangerous situation as excellent driving. Therefore, it is possible to highly evaluate the driving of a driver who avoids sudden braking or abrupt steering despite the occurrence of a dangerous situation using high driving skills, and to perform more accurate driving evaluation.

[0018] An information processing program according to an embodiment of the present invention causes a computer to execute the above-described information processing method, thereby enabling more accurate driving evaluation to be performed using a computer.

[0019] Furthermore, a computer-readable storage medium according to one embodiment of the present invention stores the information processing program. Therefore, in this embodiment, the information processing program can be distributed as a standalone program in addition to being incorporated into a device, and version upgrades can be easily performed. [Example]

[0020] <Information processing device 100> 1 is a diagram showing an information processing device 100 according to an embodiment of the present invention. The information processing device 100 includes a control unit 110, a storage unit 120, and a communication unit 130. The control unit 110 is configured by a computer. The storage unit 120 is a storage device that stores information, such as a hard disk or memory. The communication unit 130 is a communication device for transmitting and receiving information to and from other devices.

[0021] The information processing device 100 may be, for example, a device installed outside the automobile AM that is the target of driving evaluation, as shown in Fig. 2(A), or may be a device mounted on the automobile AM that is the target of driving evaluation, as shown in Fig. 2(B). If the information processing device 100 is a device installed outside the automobile AM, the information processing device 100 receives driving data (evaluation target driving data) from the automobile AM via the communication unit 130 and evaluates the received evaluation target driving data via the control unit 110. On the other hand, if the information processing device 100 is a device mounted on the automobile AM, the information processing device 100 evaluates driving data acquired by cameras and sensors mounted on the automobile AM via the control unit 110.

[0022] 3 is a diagram showing a control unit 110 according to an embodiment of the present invention. The control unit 110 includes a dangerous situation image extraction unit 111, an acceleration confirmation unit 112, and a driving evaluation unit 113.

[0023] The danger situation image extraction unit 111 extracts danger situation images that satisfy predetermined conditions from the driving data to be evaluated (evaluation target driving data). The driving data includes driving condition data in addition to images taken while driving. The driving images are, for example, images of the surroundings (front, side, and rear) of the vehicle while driving. The images may be still images or videos. The driving condition data includes information about the acceleration of the vehicle while driving. The driving data may be acquired by a camera or sensor installed in the vehicle, or by a camera or sensor installed on the roadway.

[0024] The predetermined condition is "an image indicating that a dangerous situation has occurred." In other words, the dangerous situation image extraction unit 111 extracts an image indicating that a dangerous situation has occurred from the travel data to be evaluated. The predetermined condition is, for example, "the occurrence of at least one of (1) an oncoming vehicle suddenly jumping out, (2) a preceding vehicle suddenly braking, (3) a vehicle traveling in the parallel lane suddenly cutting in, (4) a bicycle suddenly jumping out, and (5) a pedestrian suddenly jumping out." In other words, the images indicating dangerous situations extracted by the dangerous situation image extraction unit 111 are, for example, an image indicating an oncoming vehicle suddenly jumping out, an image indicating a preceding vehicle suddenly braking, an image indicating a vehicle traveling in the parallel lane suddenly cutting in, or an image indicating a bicycle or pedestrian suddenly jumping out.

[0025] The risk image extraction unit 111 may extract risk situation image data that satisfies predetermined conditions using, for example, AI (artificial intelligence) technology. That is, the risk image extraction unit 111 may extract risk situation image data that satisfies predetermined conditions from the evaluation target driving data based on, for example, teacher data. The teacher data is data related to an image that satisfies the predetermined conditions, and may be the image itself or data that indicates the characteristics of the image. That is, the risk image extraction unit 111 may extract, as risk situation image data, an image that has the same characteristics as an image that satisfies the predetermined conditions.

[0026] In this case, the control unit 110 has a teacher data acquisition unit 114 that acquires teacher data. The teacher data acquisition unit 114 may acquire the teacher data by receiving it from another device via the communication unit 130, or the teacher data may be stored in advance in the storage unit 120, and the teacher data acquisition unit 114 may acquire the teacher data from this storage unit 120.

[0027] The acceleration checking unit 112 checks whether each of the dangerous situation images extracted by the dangerous situation image extraction unit 111 is accompanied by an acceleration equal to or greater than a predetermined value (first value). Generally, driving that generates large acceleration is dangerous. For example, when the driver brakes suddenly or steers suddenly, the acceleration becomes large. In other words, by appropriately setting the first value, the acceleration checking unit 112 can check whether dangerous driving has been performed, for example, whether sudden braking or sudden steering has been performed, when a dangerous situation occurs in the vehicle.

[0028] At this time, the acceleration confirmation unit 112 may determine that each of the extracted dangerous situation images does not involve acceleration equal to or greater than the first value when no acceleration equal to or greater than the first value occurs within a predetermined time from the time corresponding to the dangerous situation image. In other words, the acceleration confirmation unit 112 may confirm whether or not acceleration equal to or greater than the first value occurs within the predetermined time after a dangerous situation occurs for the vehicle, such as a sudden oncoming vehicle. In this way, it is possible to confirm whether or not the driver engaged in dangerous driving, such as sudden braking or abrupt steering, due to the dangerous situation after the dangerous situation occurs for the vehicle.

[0029] The driving evaluation unit 113 evaluates as good driving the driving related to the dangerous situation image that is confirmed by the acceleration confirmation unit 112 as not involving acceleration equal to or greater than the first value. In other words, the driving evaluation unit 113 evaluates as good driving the driving in which the driver did not brake or steer suddenly despite a dangerous situation occurring in the vehicle.

[0030] In this way, in this embodiment, driving in which the driver did not brake suddenly or steer suddenly even though a dangerous situation occurred is evaluated as good driving. Therefore, it is possible to highly evaluate the driving of a driver who avoids braking suddenly or steering suddenly through high driving skills even though a dangerous situation occurred, and to perform a more accurate driving evaluation.

[0031] The driving evaluation unit 113 may store an image relating to driving that has been evaluated as good driving in the storage unit 120. In this case, the driving evaluation unit 113 may store video (for example, video of 30 seconds before and after) relating to driving that has been evaluated as good driving in the storage unit 120. In this way, it becomes possible to store an image that shows high driving skills.

[0032] 4 is a diagram showing the processing operation of information processing device 100 according to an embodiment of the present invention. Risk-situation image extraction unit 111 extracts risk-situation images that satisfy predetermined conditions from the evaluation target driving data (step S401). Acceleration confirmation unit 112 checks whether each risk-situation image extracted by risk-situation image extraction unit 111 is accompanied by acceleration equal to or greater than a first value, and driving evaluation unit 113 evaluates driving related to risk-situation images that are confirmed by acceleration confirmation unit 112 not to be accompanied by acceleration equal to or greater than the first value as excellent driving (step S402).

[0033] <Extraction of training data> The control unit 110 may include a teacher data extraction unit 115 that extracts teacher data from a plurality of pieces of driving data. In this case, the information processing device 100 may store the driving data of a plurality of vehicles in the storage unit 120. The teacher data extraction unit 115 may then extract teacher data from this stored driving data. The teacher data extraction unit 115 stores the extracted teacher data in the storage unit 120, for example.

[0034] For example, the teacher data extraction unit 115 may extract, from the accumulated driving data, images that involve acceleration equal to or greater than a predetermined value (second value) and that satisfy the above-mentioned predetermined conditions, and use data related to the extracted images as teacher data. Here, the second value may be the same as or different from the above-mentioned first value. In this way, it becomes possible to extract teacher data from the large amount of accumulated driving data. As a result, it becomes possible to obtain a large amount of teacher data.

[0035] At this time, it is preferable that the teacher data extraction unit 115 extracts, as teacher data, only data relating to the image portion of each extracted image before the occurrence of acceleration equal to or greater than the second value. In this way, the images relating to the teacher data do not include images of the moment when dangerous driving such as sudden braking or abrupt steering is performed, but only images before that moment are included.

[0036] If the information processing device 100 is a device installed in the automobile AM to be evaluated, an external device (server device SS) should have a memory unit that accumulates driving data of multiple vehicles and a control unit that has functions similar to those of the teacher data extraction unit 115, and the information processing device 100 should receive the teacher data from the server device SS via a communication unit 130, as shown in Figure 2 (B).

[0037] The present invention has been described above in terms of preferred embodiments thereof. While the present invention has been described herein with reference to specific examples, various modifications and variations can be made to these examples without departing from the spirit and scope of the present invention as set forth in the claims. [Explanation of symbols]

[0038] 100 Information processing device 110 control section 111 Danger situation image extraction unit 112 Acceleration check section 113 Driving Evaluation Department 114 Teacher Data Acquisition Unit 115 Teacher Data Extraction Unit 120 Storage section 130 Communications Department

Claims

1. a risky situation image extraction unit that extracts risky situation images that satisfy predetermined conditions from the evaluation target travel data; an acceleration confirmation unit that confirms whether each of the dangerous situation images is accompanied by an acceleration equal to or greater than a first value; and a driving evaluation unit that evaluates driving relating to a dangerous situation image that has been confirmed by the acceleration confirmation unit to not involve acceleration equal to or greater than the first value as excellent driving.

2. 2. The information processing device according to claim 1, wherein the predetermined condition is the occurrence of at least one of an oncoming vehicle suddenly jumping out, a preceding vehicle suddenly braking, a vehicle traveling in a parallel lane suddenly cutting in, a bicycle suddenly jumping out, and a pedestrian suddenly jumping out.

3. The image processing device further includes a training data acquisition unit that acquires training data related to the image that satisfies the predetermined condition, The information processing device according to claim 1 , wherein the danger situation image extracting unit extracts the danger situation image using the training data.

4. a travel data storage unit that stores travel data of a plurality of vehicles; 4. The information processing device according to claim 3, further comprising a teacher data extraction unit that extracts, from the accumulated driving data, images that involve acceleration equal to or greater than a second value and that satisfy the predetermined condition, and extracts data related to the images as the teacher data.

5. 1. A computer-implemented information processing method, comprising: a risk situation image extraction step of extracting risk situation images that satisfy predetermined conditions from the evaluation target travel data; an acceleration confirmation step of confirming whether each of the dangerous situation images is accompanied by an acceleration equal to or greater than a first value; and a driving evaluation step of evaluating, as good driving, driving related to a dangerous situation image that is confirmed by the acceleration confirmation step to not involve acceleration equal to or greater than the first value.

6. An information processing program that causes a computer to execute the information processing method according to claim 5.

7. A computer-readable storage medium storing the information processing program according to claim 6.

Images