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 apparatus.

Background Art

[0002] As a technique for evaluating driving, various techniques have been developed (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, only dangerous driving such as sudden braking and sudden steering is detected, and such dangerous driving is only evaluated low. That is, in the conventional technology, only driving evaluation based on driving safety is performed, and driving evaluation based on driving skill is not performed.

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

Means for Solving the Problems

[0006] In order to solve the above problems, the invention according to claim 1 includes a dangerous situation image extraction unit that extracts a dangerous situation image satisfying a predetermined condition from evaluation target driving 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 related to a dangerous situation image confirmed by the acceleration confirmation unit not to be accompanied by an acceleration equal to or greater than the first value as excellent driving.

[0007] The invention described in claim 7 is an information processing method performed by a computer, comprising: a hazardous situation image extraction step of extracting hazardous situation image data that satisfies predetermined conditions from driving data to be evaluated; an acceleration confirmation step of checking whether each of the hazardous situation images is accompanied by an acceleration of a first value or greater; and a driving evaluation step of evaluating driving related to a hazardous situation image that has been confirmed by the acceleration confirmation unit not to be accompanied by an acceleration of a first value or greater as good driving.

[0008] The invention described in claim 8 involves having a computer execute the information processing method described in claim 7.

[0009] The invention described in claim 9 stores the information processing program described in claim 8. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an information processing device 100 according to one embodiment of the present invention. [Figure 2] This diagram shows the relationship between the information processing device 100 and the automobile AM, which is the subject of the driving evaluation. [Figure 3] This figure shows a control unit 110 according to one embodiment of the present invention. [Figure 4] This figure shows the processing operation in an information processing device 100 according to one embodiment of the present invention. [Modes for carrying out the invention]

[0011] An information processing device according to one embodiment of the present invention includes: a hazardous situation image extraction unit that extracts hazardous situation images that satisfy predetermined conditions from driving data to be evaluated; an acceleration confirmation unit that checks whether each of the hazardous situation images is accompanied by an acceleration of a first value or greater; and a driving evaluation unit that evaluates driving related to a hazardous situation image that has been confirmed by the acceleration confirmation unit not to be accompanied by an acceleration of a first value or greater as good driving. Therefore, in this embodiment, by setting the predetermined condition to "an image that indicates that a hazardous situation has occurred," it is possible to evaluate driving in which the driver did not perform sudden braking or sudden steering despite a hazardous situation occurring as good driving. Therefore, it is possible to highly evaluate the driving of a driver who avoided sudden braking or sudden steering with high driving skill despite a hazardous situation occurring, and to perform a more accurate driving evaluation.

[0012] The aforementioned predetermined conditions may be that at least one of the following occurs: a sudden appearance of an oncoming vehicle, sudden braking of a preceding vehicle, sudden cutting in of a vehicle traveling in a parallel lane, sudden appearance of a bicycle, or sudden appearance of a pedestrian. In this way, it becomes possible to evaluate driving as good driving when a driver does not perform sudden braking or sudden steering despite the occurrence of dangerous situations such as a sudden appearance of an oncoming vehicle, sudden braking of a preceding vehicle, sudden cutting in of a vehicle traveling in a parallel lane, or sudden appearance of a bicycle or pedestrian.

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

[0014] The information processing device may further include a driving data storage unit that stores driving data of multiple vehicles, and a training data extraction unit that extracts images from the stored driving data that have an acceleration of a second value or greater and satisfy the predetermined conditions, and extracts data related to such images as training data. In this way, it becomes possible to extract training data from a large amount of stored driving data. As a result, it becomes possible to obtain a large amount of training data.

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

[0016] A system according to one embodiment of the present invention comprises the information processing device and the server device. Therefore, in this embodiment, it is possible to evaluate driving in which the driver did not perform sudden braking or sudden steering despite the occurrence of a dangerous situation as good driving. Therefore, it is possible to highly evaluate the driving of a driver who avoided sudden braking or sudden steering through high driving skill despite the occurrence of a dangerous situation. Furthermore, it is possible to extract training data from a large amount of accumulated driving data, and it is possible to extract images of dangerous situations based on a large amount of training data. As a result, in this embodiment, it is possible to perform more accurate driving evaluation.

[0017] Also, an information processing method according to an 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 satisfying a predetermined condition from 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 more, and a driving evaluation step of evaluating driving related to a dangerous situation image confirmed by the acceleration confirmation unit not to be accompanied by an acceleration of the first value or more as excellent driving. Therefore, in this embodiment, by setting the predetermined condition to "an image indicating that a dangerous situation has occurred", it is possible to evaluate as excellent driving a driving in which the driver did not perform sudden braking or sudden steering despite the occurrence of a dangerous situation. Therefore, it is possible to highly evaluate the driving of a driver who has avoided sudden braking or sudden steering with high driving skills despite the occurrence of a dangerous situation, and it is possible to perform a more accurate driving evaluation.

[0018] Also, an information processing program according to an embodiment of the present invention causes a computer to execute the above information processing method. Therefore, in this embodiment, it is possible to perform a more accurate driving evaluation using a computer.

[0019] Also, a computer-readable storage medium according to an embodiment of the present invention stores the above information processing program. Therefore, in this embodiment, the above information processing program can be distributed alone in addition to being incorporated into a device, and it is possible to easily perform version updates and the like.

Example

[0020] <Information processing device 100> FIG. 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, for example, a hard disk or a 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 a device installed outside the automobile AM that is the object of driving evaluation, for example, as shown in FIG. 2(A), or may be a device installed in the automobile AM that is the object of driving evaluation, as shown in FIG. 2(B). If the information processing device 100 is a device set outside the automobile AM, the information processing device 100 receives driving data (evaluation target driving data) from the automobile AM through the communication unit 130, and the control unit 110 evaluates the received evaluation target driving data. On the other hand, if the information processing device 100 is a device installed in the automobile AM, the information processing device 100 evaluates the driving data acquired by a camera or sensor installed in the automobile AM by the control unit 110.

[0022] FIG. 3 is a diagram showing the 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 dangerous situation image extraction unit 111 extracts a dangerous situation image that satisfies a predetermined condition from the driving data (evaluation target driving data) to be evaluated. The driving data includes driving state data in addition to the images during driving. The images during driving are, for example, those taken of the surroundings (front, side, rear) of the vehicle during driving. The images may be still images or moving images. The driving state data includes information regarding the acceleration of the vehicle during driving. The driving data may be acquired by a camera or sensor installed in the automobile, or may be acquired by a camera or sensor installed on the road.

[0024] The predetermined condition described above is that the image shows that a dangerous situation has occurred. In other words, the dangerous situation image extraction unit 111 extracts images that show that a dangerous situation has occurred from the driving data to be evaluated. The predetermined condition described above is, for example, that "at least one of the following has occurred: (1) a sudden appearance of an oncoming vehicle, (2) sudden braking of a preceding vehicle, (3) sudden cutting in of a vehicle traveling in a parallel lane, (4) a sudden appearance of a bicycle, or (5) a sudden appearance of a pedestrian." In other words, the images showing dangerous situations extracted by the dangerous situation image extraction unit 111 are, for example, images showing a sudden appearance of an oncoming vehicle, images showing sudden braking of a preceding vehicle, images showing a sudden cutting in of a vehicle traveling in a parallel lane, or images showing a sudden appearance of a bicycle or pedestrian.

[0025] The hazard image extraction unit 111 may, for example, use AI (artificial intelligence) technology to extract hazard image data that meets predetermined conditions. In other words, the hazard image extraction unit 111 may, for example, extract hazard image data that meets predetermined conditions from the driving data to be evaluated based on training data. The training data is data relating to images that meet the predetermined conditions, and may be the image itself or data that describes the characteristics of the image. In other words, the hazard image extraction unit 111 may extract images that have the same characteristics as images that meet the above predetermined conditions as hazard image data.

[0026] In this case, the control unit 110 is provided with a teacher data acquisition unit 114 that acquires teacher data. The teacher data acquisition unit 114 may acquire teacher data by receiving it from another device via the communication unit 130, or it may store the teacher data 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 confirmation unit 112 checks whether each of the dangerous situation images extracted by the dangerous situation image extraction unit 111 is accompanied by an acceleration of a predetermined value (first value) or higher. Generally, driving that produces large acceleration is dangerous. For example, acceleration increases when a driver brakes suddenly or makes a sudden turn. In other words, by appropriately setting the first value, the acceleration confirmation unit 112 can confirm whether dangerous driving occurred when a dangerous situation arises in the vehicle, for example, whether sudden braking or sudden turning occurred.

[0028] In this case, the acceleration confirmation unit 112 should determine that a hazardous situation image does not involve acceleration of a first value or greater if, for each of the extracted hazardous situation images, acceleration of a first value or greater does not occur within a predetermined time period from the time corresponding to that hazardous situation image. In other words, the acceleration confirmation unit 112 should check whether acceleration of a first value or greater occurred within the predetermined time period after a hazardous situation occurred for the vehicle, such as a sudden appearance of an oncoming vehicle. By doing so, it is possible to check whether the driver performed dangerous driving actions such as sudden braking or sudden steering after a hazardous situation occurred for the vehicle.

[0029] The driving evaluation unit 113 evaluates driving in relation to a dangerous situation image that has been confirmed by the acceleration confirmation unit 112 not to be accompanied by an acceleration of a first value or higher as good driving. In other words, the driving evaluation unit 113 evaluates driving in which the driver did not perform sudden braking or sudden steering despite a dangerous situation occurring in the vehicle as good driving.

[0030] Thus, in this embodiment, driving in which the driver does not perform sudden braking or sudden steering despite the occurrence of a dangerous situation is evaluated as excellent driving. Therefore, it is possible to highly evaluate the driving of a driver who avoids sudden braking or sudden steering through high driving skill despite the occurrence of a dangerous situation, and it is possible to perform a more accurate driving evaluation.

[0031] The driving evaluation unit 113 may store images related to driving that has been evaluated as excellent driving in the storage unit 120. In this case, the driving evaluation unit 113 should store video footage (for example, 30 seconds of video before and after the driving that has been evaluated as excellent driving) in the storage unit 120. This makes it possible to store images that demonstrate high driving skills.

[0032] Figure 4 shows the processing operation in an information processing device 100 according to one embodiment of the present invention. The hazardous situation image extraction unit 111 extracts hazardous situation images that satisfy predetermined conditions from the driving data to be evaluated (step S401). The acceleration confirmation unit 112 checks whether each of the hazardous situation images extracted by the hazardous situation image extraction unit 111 is accompanied by an acceleration of a first value or greater, and the driving evaluation unit 113 evaluates the driving related to the hazardous situation image that has been confirmed by the acceleration confirmation unit 112 not to be accompanied by an acceleration of a first value or greater as good driving (step S402).

[0033] <Extracting training data> The control unit 110 may also have a training data extraction unit 115 that extracts training data from multiple driving data sets. In this case, the information processing device 100 may store driving data from multiple vehicles in a storage unit 120. The training data extraction unit 115 may then extract training data from this stored driving data. For example, the training data extraction unit 115 stores the extracted training data in the storage unit 120.

[0034] The training data extraction unit 115 may, for example, extract images from the accumulated driving data that have an acceleration of a predetermined value (second value) or greater and satisfy the predetermined conditions described above, and use the data related to these extracted images as training data. Here, the second value may be the same as or different from the first value described above. In this way, it becomes possible to extract training data from a large amount of accumulated driving data. As a result, it becomes possible to obtain a large amount of training data.

[0035] In this case, the training data extraction unit 115 should extract only the data relating to the portion of each extracted image before an acceleration of a second value or higher occurs, as training data. By doing so, the images related to the training data will not include images of the moment when dangerous driving such as sudden braking or sudden steering occurs, but will only include images from before that moment.

[0036] If the information processing device 100 is a device installed in the automobile AM ​​being evaluated, then it is preferable that the external device (server device SS) has a storage unit for accumulating driving data of multiple vehicles and a control unit having the same function as the training data extraction unit 115, and that the information processing device 100 receives training data from the server device SS via the communication unit 130, as shown in Figure 2(B).

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

[0038] 100 Information Processing Devices 110 Control Unit 111 Hazardous Situation Image Extraction Unit 112 Acceleration Confirmation Unit 113 Operation Evaluation Department 114 Training Data Acquisition Unit 115 Training Data Extraction Unit 120 Storage section 130 Communications Department

Claims

1. A hazardous situation image extraction unit extracts hazardous situation images that meet predetermined conditions from the driving data to be evaluated, For each of the aforementioned hazardous situation images, an acceleration confirmation unit is provided to confirm whether or not the hazardous situation image is accompanied by an acceleration of a first value or greater. An information processing device having an operation evaluation unit that evaluates operation related to a dangerous situation image, which has been confirmed by the acceleration confirmation unit not to be accompanied by an acceleration of a first value or higher, as good operation.

2. The information processing apparatus according to claim 1, wherein the predetermined condition is that at least one of the following has occurred: a sudden appearance of an oncoming vehicle, sudden braking of a preceding vehicle, sudden cutting in of a vehicle traveling in a parallel lane, a sudden appearance of a bicycle, and a sudden appearance of a pedestrian.

3. The system further includes a training data acquisition unit that acquires training data which is data relating to images that satisfy the aforementioned predetermined conditions, The information processing apparatus according to claim 1 or 2, wherein the hazardous situation image extraction unit extracts the hazardous situation image using the training data.

4. A driving data storage unit that stores driving data from multiple vehicles, The information processing apparatus according to claim 3, further comprising: a training data extraction unit that extracts images from the accumulated driving data that have an acceleration of a second value or greater and satisfy the predetermined conditions, and extracts data relating to such images as training data.

5. A method of information processing performed by a computer, A hazardous situation image extraction process extracts hazardous situation images that meet predetermined conditions from the driving data to be evaluated, For each of the aforementioned hazardous situation images, an acceleration confirmation step is performed to confirm whether or not the hazardous situation image is accompanied by an acceleration of a first value or greater. An information processing method comprising: an operation evaluation step of evaluating operation related to a dangerous situation image in which it has been confirmed by the acceleration confirmation step that the acceleration does not exceed the first value as good operation.

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

7. A computer-readable storage medium storing the information processing program described in claim 6.

Images