Center device, safe driving education system, and safe driving education method

Abstract

To prevent a trainee from losing the motivation to attend an educational content.SOLUTION: A center device includes a controller. The controller is configured to: receive vehicle data including a video of the surroundings of a vehicle, from the vehicle; detect a scene of excellent driving operation based on the received vehicle data; generate an educational content including the video of the scene; and distribute the educational content to trainees including a person who has performed the excellent driving operation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The disclosed embodiments relate to a center device, a safe driving education system, and a safe driving education method. [Background technology]

[0002] Conventionally, video footage captured by in-vehicle devices such as drive recorders has been used as e-learning teaching materials (hereinafter referred to as "educational content") for safe driving education within a specific group, for example, within a company.

[0003] In such cases, for example, dangerous driving footage actually taken in a company car driven by an employee is often used. For example, when the on-board device of a company car driven by an employee detects a so-called near miss scene, the on-board device transmits the vehicle data, including the video and location information, taken at that time, to the central device of the safe driving education system.

[0004] The center device then analyzes the vehicle data received from the in-vehicle device and generates educational materials based on the analysis results. For example, if the analysis results show that the near miss was caused by exceeding the legal speed limit, the center device will generate educational materials about complying with the legal speed limit.

[0005] The generated teaching materials are distributed to devices such as smartphones and personal computers (PCs) used by employees within the company, including the people who were actually driving the vehicles in the scenes that served as the source material for the teaching materials. Each employee can then take e-learning courses using the distributed teaching materials via these devices.

[0006] However, in such cases, the educational materials contain content that essentially denies the person who engaged in dangerous driving, which could reduce the motivation of not only the person involved but also other employees who could become the next perpetrators of dangerous driving to take the e-learning course.

[0007] In response to this, a driving evaluation device has been proposed that counts recommended driving behaviors performed by a driver and outputs the individual driver's evaluation information from an in-vehicle speaker or an in-vehicle display in order to evaluate good driving manners rather than dangerous driving (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Japanese Patent Publication No. 2022-074635 Summary of the Invention [Problem to be solved by the invention]

[0009] However, when using the above-mentioned conventional technology, evaluation information is output to each individual driver, not through e-learning, so other employees cannot directly know that one employee has driven well. In other words, even if the above-mentioned conventional technology is used, it cannot prevent the above-mentioned decline in motivation to take e-learning courses.

[0010] One aspect of the embodiment has been made in consideration of the above, and aims to provide a center device, a safe driving education system, and a safe driving education method that can prevent a decrease in motivation to take educational content. [Means for solving the problem]

[0011] According to one aspect of the embodiment, the center device includes a controller that receives vehicle data from a vehicle, including video of the vehicle's surroundings, detects scenes in which good driving was performed based on the received vehicle data, generates educational content including video of the scenes, and distributes the educational content to participants, including the person who performed the good driving. [Effects of the Invention]

[0012] According to one aspect of the embodiment, educational content including video of a good driving scene is generated, and the generated educational content is distributed to at least the person who performed the good driving. As a result, the person can receive positive evaluation through the educational content, and can feel a sense of satisfaction by having other participants receive education based on the good driving that the person performed. Therefore, the center device according to the embodiment can prevent a decrease in motivation to receive the educational content. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an outline of a safe driving education method according to an embodiment. [Figure 2] FIG. 2 is a diagram showing an example of the types of teaching materials. [Figure 3] FIG. 3 is a diagram illustrating an example of a distribution destination. [Figure 4] FIG. 4 is a diagram showing an example of a review-based educational material screen displayed on the student device. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of a safe driving education system according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of a drive recorder according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the event condition information. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of a center device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of the configuration of a lecture attendance device according to the embodiment. [Figure 10] FIG. 10 is a diagram showing a processing sequence executed by the safe driving education system according to the embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a Q&A style teaching material screen displayed on the student device. [Figure 12] FIG. 12 is a diagram showing an example of a teaching material screen that has been subjected to the concealment process and is displayed on the student device. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of the center device, the safe driving education system, and the safe driving education method disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the following embodiments.

[0015] In the following, a safe driving education system according to the embodiment will be mainly described as a safe driving education system 1 (see FIG. 1). The safe driving education system 1 is a system that generates e-learning teaching materials for safe driving education and the like and distributes them to participants. The e-learning teaching materials are an example of "educational content."

[0016] In the following description, the center device according to the embodiment is assumed to be the center device 100 (see FIG. 1) included in the safe driving education system 1. The safe driving education method according to the embodiment is assumed to be a safe driving education method executed by the controller 103 (see FIG. 8) of the center device 100.

[0017] In the following, "good driving" refers to exemplary driving in safe driving education, not only complying with traffic rules but also driving with good manners. "Good driving" is detected based on the degree of agreement between multiple elements indicated by the image analysis results of video captured by a vehicle and notable elements of predetermined good driving behavior. Details will be described later.

[0018] Furthermore, the expressions "specific," "predetermined," and "constant" in the following description may be read as "predetermined."

[0019] First, an outline of a safe driving education method according to an embodiment will be described with reference to Figs. 1 to 3. Fig. 1 is an explanatory diagram of an outline of a safe driving education method according to an embodiment. Fig. 2 is a diagram showing an example of types of educational materials. Fig. 3 is a diagram showing an example of distribution destinations.

[0020] 1, the safe driving education system 1 includes a drive recorder 10, a center device 100, and student devices 200 (200-1, 200-2, ...). The student devices 200 correspond to an example of a "terminal device."

[0021] The drive recorder 10 is a video recording device mounted on a vehicle. The drive recorder 10 according to the embodiment has an in-vehicle camera 12a and an outside-vehicle camera 12b. The in-vehicle camera 12a and the outside-vehicle camera 12b are examples of "cameras." The in-vehicle camera 12a is provided so as to be able to capture images of the interior of the vehicle. The outside-vehicle camera 12b is provided so as to be able to capture images of the exterior of the vehicle surroundings, and is capable of capturing images mainly of the area ahead of the vehicle.

[0022] While the vehicle is running, the drive recorder 10 records vehicle data, including the interior and exterior images captured by the interior camera 12a and exterior camera 12b, in a ring buffer memory in an overwritable manner for a certain period of time. The certain period is, for example, 24 hours. The vehicle data may include various data indicating the vehicle's status, such as date and time information, location information, vehicle speed, and G-force, in addition to the interior and exterior images.

[0023] The drive recorder 10 is also configured to be able to detect specific events that satisfy preset event conditions. For example, when detecting dangerous driving, the drive recorder 10 detects a specific event when a change in vehicle speed or G-value satisfies an event condition corresponding to the occurrence of an accident or a near miss.

[0024] In this embodiment, the drive recorder 10 is preset with an event condition for detecting good driving. This event condition is, for example, arrival near a location where dangerous driving is likely to occur, as opposed to good driving. Locations where dangerous driving is likely to occur include, for example, locations where pedestrian obstruction, speeding exceeding the legal limit, traffic congestion, etc. are likely to occur. Such locations have the advantage of making it easier to compare good driving with dangerous driving.

[0025] When the drive recorder 10 detects this specific event, it sets the vehicle data for a certain period of time before and after the detection time to be overwritten. Alternatively, the drive recorder 10 records the vehicle data for a certain period of time before and after the detection time to another recording medium. Note that this overwriting prevention process or the process of recording to another recording medium may be performed in response to an instruction from the center device 100.

[0026] Furthermore, when the drive recorder 10 detects a specific event, it transmits to the center device 100 the vehicle data that is set to be overwrite-prohibited.

[0027] The center device 100 is configured to be able to analyze the vehicle status when a specific event is detected based on the vehicle data transmitted from the vehicle. The center device 100 is also configured to be able to generate e-learning materials based on the analysis results.

[0028] The center device 100 is also configured to be able to provide a service of distributing the generated teaching materials to the student devices 200. The student devices 200 are terminal devices used by students (equivalent to an example of a "user") taking e-learning courses. The student devices 200 are realized, for example, by a PC (Personal Computer) such as the student device 200-1, or a smartphone such as the student device 200-2.

[0029] In such a safe driving education system 1, it is desirable to prevent a decrease in the motivation of participants to take the e-learning course. Therefore, in the safe driving education method according to the embodiment, the controller 103 of the center device 100 receives vehicle data including video of the vehicle's surroundings from the vehicle. Furthermore, the controller 103 detects scenes in which good driving was performed based on the received vehicle data, and generates e-learning teaching materials including video of the scenes. Furthermore, the controller 103 distributes the teaching materials to participants, including the person who performed the good driving.

[0030] 1, when the drive recorder 10 detects a specific event based on a preset event condition (step S1), it transmits vehicle data for a certain period of time before and after the event detection to the center device 100 (step S2). As already mentioned, the vehicle data includes in-vehicle video, out-vehicle video, date and time information (date and time of event occurrence), location information, vehicle speed, G value, etc.

[0031] Then, the controller 103 of the center device 100 detects scenes in which good driving was performed based on the received vehicle data, and generates teaching materials including footage of the relevant scenes (step S3).The controller 103 then distributes the generated teaching materials to each student receiving device 200 (step S4), and the student receives the teaching materials distributed to the student receiving device 200.

[0032] In this embodiment, the educational materials delivered to the learning device 200 are either in a review format or a Q&A format, as shown in FIG. 2. The review format is educational materials that include a video of a scene of good driving along with a review that highly evaluates the driver who performed good driving. The review format includes content that praises the type of driving and what was good about the driver. By viewing this review format educational material, students can deepen their understanding of good driving.

[0033] The Q&A format is a teaching material that presents a video of a scene of good driving along with a question and answer option about good driving based on the video. By selecting an option and answering, students can deepen their understanding of good driving while having fun like a quiz.

[0034] The center device 100 is realized as, for example, a cloud server. The center device 100 is managed, for example, by a business operator that operates the safe driving education system 1. Hereinafter, this business operator will be referred to as "our company" where appropriate.

[0035] Furthermore, the center device 100 can provide a service of distributing educational materials not only to the student devices 200 used by its own students, but also to student devices 200 used by other companies or an unspecified number of individuals, etc. Hereinafter, these other companies and unspecified number of individuals will be referred to as "other than the company" as appropriate.

[0036] As shown in FIG. 3, the controller 103 of such a center device 100 can specify the person who drove well, the person's own students including the person, and students other than the person's own students as the distribution destinations.

[0037] If the person in question is designated, the person in question can receive high praise for their good driving through e-learning. If a trainee from the company, including the person in question, is designated, the trainee from the company can deepen their understanding of good driving through e-learning and be made aware of who the person in question was who drove well. If a trainee from another company is designated, this trainee will have the opportunity to learn about good examples of good driving.

[0038] An example of a teaching material screen in the teaching material generated by the safe driving education system 1 according to this embodiment will now be described with reference to Fig. 4. Here, an example of a teaching material screen using a review method will be described. Fig. 4 is a diagram showing an example of a teaching material screen using a review method displayed on the student device 200.

[0039] As shown in FIG. 4, the review-based learning material screen DS1 is generated as learning material including, for example, a video of a scene where good driving was performed and a review that explains the scene.

[0040] Figure 4 shows an example of a scene in which a driver gives way to a pedestrian at a crosswalk without traffic lights. In the video, the controller 103 highlights the pedestrian, which is one of the elements of interest in the scene, for example, by surrounding the pedestrian with a detection frame. This clearly shows the element of interest, the pedestrian, in the scene in which the driver gives way to the pedestrian at the crosswalk, allowing the trainee to easily understand the situation.

[0041] If the recipient is the person in question, the controller 103 generates and posts a review for the person in question as shown in the drawing. If the recipient is a student of the company who also includes the person in question, the controller 103 generates and posts a review for the student in question who also includes the person in question as shown in the drawing.

[0042] These reviews explain what the driving was like and what was good about it, and also praise the person involved.

[0043] In step S3, the controller 103 detects scenes in which good driving was performed, for example, by performing image analysis on the video outside the vehicle. In the image analysis, the controller 103 breaks down various situations shown in the video into multiple elements. The multiple elements include, for example, the type of object captured in the video and the position of the object.

[0044] The controller 103 also calculates the degree of agreement between each of the multiple decomposed elements and a predetermined notable element in good driving behavior, and detects scenes in which good driving was performed according to the degree of agreement between each of the multiple elements. The controller 103 also generates a review text with content according to the degree of agreement between each of the multiple elements.

[0045] For example, attention elements relating to the type of object include a crosswalk, a pedestrian, a traffic light, a vehicle, etc. Attention elements relating to the position of an object include front, rear, left, right, etc.

[0046] Specifically, the controller 103 detects the area of ​​each object from within the video and calculates the degree of correspondence between the detected area and the template images of the target elements, namely, the crosswalk, pedestrian, traffic light, and vehicle, for example, by pattern matching.

[0047] Furthermore, the controller 103 calculates the degree of coincidence with each of the target positions, which are the front, rear, left and right, based on the position of the detected area and the shooting range of the camera.

[0048] Then, the controller 103 detects a scene in which good driving was performed according to each calculated degree of coincidence. For example, the controller 103 determines whether the degree of coincidence that the attention element regarding the type of object is a crosswalk or a pedestrian, the degree of coincidence that there is no traffic light, and the degree of coincidence that the attention element regarding the position of the object is ahead are each equal to or greater than a threshold. If they are equal to or greater than the threshold, the controller 103 detects the scene as one in which good driving was performed, in which the driver "yields to a pedestrian at a crosswalk without traffic lights." This makes it possible to generate teaching materials that include footage of good driving, in which the driver yields to a pedestrian without obstructing the pedestrian's crossing.

[0049] In response to this, the controller 103 generates a review about the scene. The center device 100 may have a database in which keywords describing each attention element and review templates are registered in advance, and generate a review by combining keywords according to the degree of match and applying them to the template. The center device 100 may also use a pre-trained AI language model to automatically generate a review by inputting each detected attention element and each degree of match.

[0050] 4 shows an example in which the recipient is the person in question or a student of the same company including the person in question, but if the recipient is a student other than the same company, the controller 103 performs a process of concealing personal information to protect privacy. This point will be described later with reference to FIG. 12.

[0051] As described above, in the safe driving education method according to the embodiment, the controller 103 of the center device 100 receives vehicle data including video of the vehicle's surroundings from the vehicle. Furthermore, the controller 103 detects scenes of good driving based on the received vehicle data, and generates e-learning teaching materials including video of the scenes. Furthermore, the controller 103 distributes the teaching materials to participants, including the person who performed the good driving.

[0052] Therefore, according to the safe driving education method of the embodiment, e-learning teaching materials including video of good driving scenes are generated, and the generated teaching materials are distributed to at least the person who performed the good driving. As a result, the person can receive positive evaluations through the e-learning, and can also feel a sense of satisfaction by knowing that other participants will receive education based on the good driving that the person performed. Therefore, the center device 100 according to the embodiment can prevent a decrease in motivation to take the e-learning course.

[0053] An example of the configuration of the safe driving education system 1 including the center device 100 to which the safe driving education method according to the above-described embodiment is applied will be described in more detail below.

[0054] Fig. 5 is a diagram showing an example of the configuration of a safe driving education system 1 according to an embodiment. As shown in Fig. 5, the safe driving education system 1 includes drive recorders 10-1, 10-2, ... 10-m (m is a natural number equal to or greater than 1), a center device 100, and participant devices 200-1, 200-2, ... 200-n (n is a natural number equal to or greater than 1).

[0055] Each drive recorder 10, the center device 100, and each participant device 200 are connected to each other so that they can communicate with each other via a network N, which may be the Internet, a mobile phone network, a C-V2X (Cellular Vehicle to Everything) communication network, or the like.

[0056] As described above, the drive recorder 10 records vehicle data including interior and exterior images captured by the interior camera 12a and exterior camera 12b, as well as various data indicating the vehicle's status, in a ring buffer memory in an overwritable manner for a certain period of time.

[0057] Furthermore, if the drive recorder 10 detects a specific event such as an accident or a near miss while the vehicle is running, the drive recorder 10 sets the vehicle data for a certain period of time before and after the detection time to be prohibited from being overwritten, or records the vehicle data for a certain period of time before and after the detection time to another recording medium.

[0058] Furthermore, when the drive recorder 10 detects a specific event, it transmits to the center device 100 the vehicle data that is set to be overwrite-prohibited.

[0059] As described above, the center device 100 is realized as, for example, a cloud server, and is managed by the operator of the safe driving education system 1. The center device 100 collects vehicle data transmitted from each drive recorder 10.

[0060] The center device 100 also detects scenes in which good driving was performed based on the collected vehicle data, and generates teaching materials that include footage of those scenes. The center device 100 also accumulates and manages the generated teaching materials. The center device 100 also provides a service for distributing teaching materials to each student device 200. In this case, as described above, the center device 100 can distribute teaching materials not only to the student devices 200 used by its own students, but also to student devices 200 used by students other than its own students.

[0061] As described above, the attending device 200 is a terminal device used by the attendees, and is realized by a PC, a smartphone, etc. In addition to these, the attending device 200 may also be realized by, for example, a tablet terminal, a wearable device, etc.

[0062] Next, a configuration example of the drive recorder 10 will be described. Fig. 6 is a diagram showing a configuration example of the drive recorder 10 according to the embodiment. As shown in Fig. 6, the drive recorder 10 has an HMI (Human Machine Interface) unit 11, a sensor unit 12, a communication unit 13, a storage unit 14, and a controller 15.

[0063] The HMI unit 11 is a component that provides interface components related to input and output to a user who operates the drive recorder 10. The HMI unit 11 includes an input interface that accepts input operations from the user. The input interface is realized by, for example, a touch panel. The input interface may also be realized by a microphone or the like. The input interface may also be realized by software components.

[0064] The HMI unit 11 also includes an output interface that presents visual and audio information to the user. The output interface is realized by, for example, a display, a speaker, etc. The HMI unit 11 may also provide the user with an input interface and an output interface integrated into one, for example, by a touch panel display.

[0065] The sensor unit 12 is a group of various sensors mounted on the drive recorder 10. The sensor unit 12 includes, for example, an in-vehicle camera 12a, an out-vehicle camera 12b, a GPS (Global Positioning System) sensor 12c, and a G sensor 12d.

[0066] In-vehicle camera 12a is provided so as to be able to capture images inside the vehicle. In-vehicle camera 12a is attached near the windshield, dashboard, or the like so that at least the driver's face is included in the capture range.

[0067] Exterior camera 12b is installed so that it can capture images of the outside of the vehicle. Exterior camera 12b is attached near the windshield, the dashboard, the rear window, etc. Note that interior camera 12a and exterior camera 12b do not necessarily need to be separate and may be integrated into one camera, for example, a 360-degree camera.

[0068] The GPS sensor 12c measures the GPS position of the vehicle. The G sensor 12d measures the G value, which is the acceleration value applied to the vehicle.

[0069] In addition to the sensor unit 12, the drive recorder 10 is also connected to an in-vehicle sensor 5, which is a group of various sensors mounted on the vehicle. The in-vehicle sensor 5 includes, for example, a vehicle speed sensor, an accelerator sensor, a brake sensor, etc. The in-vehicle sensor 5 is connected to the drive recorder 10 via an in-vehicle network such as a CAN (Controller Area Network).

[0070] The communication unit 13 is realized by a network adapter etc. The communication unit 13 is connected to the network N wirelessly, and transmits and receives information to and from the center device 100 via the network N.

[0071] The storage unit 14 is realized by a storage device such as a read-only memory (ROM), a random access memory (RAM), a flash memory, etc. In the example of Fig. 6, the storage unit 14 stores a vehicle data DB 14a, event condition information 14b, and an image recognition model 14c.

[0072] The vehicle data DB 14a is a database of vehicle data recorded by the drive recorder 10. The event condition information 14b is information in which predetermined event conditions for detecting the above-mentioned specific events are set. The event conditions are transmitted as appropriate from, for example, the center device 100 and stored in the event condition information 14b.

[0073] An example of the event condition information 14b will now be described with reference to FIG. 7. FIG. 7 is a diagram showing an example of the event condition information 14b. As shown in FIG. 7, one or more event conditions for detecting a specific event are set in the event condition information 14b. An "event ID" is an identification ID for each event condition. The event conditions are set for "location information," "vehicle speed," "pedestrians," etc. The "pedestrians" setting is set to indicate whether or not there are pedestrians.

[0074] 7 shows an example in which the event condition for event ID "001" is "A crosswalk near XX Park ±30 m." In this case, the drive recorder 10 detects a specific event when the vehicle reaches a range of ±30 m from the point indicating A crosswalk near XX Park. Note that A crosswalk is, for example, a crosswalk without traffic lights.

[0075] Similarly, for example, the event conditions for event ID "002" are "A crosswalk near XX Park ±30 m," the vehicle speed is "0," and there is a pedestrian present. In this case, the drive recorder 10 detects a specific event when the vehicle stops within a range of ±30 m from the point indicating A crosswalk near XX Park and there is a pedestrian present.

[0076] Similarly, for example, the event condition for event ID "003" is "±200 m in front of Post Office B on National Highway YY." In this case, the drive recorder 10 detects a specific event when the vehicle reaches a range of ±200 m from in front of Post Office B on National Highway YY.

[0077] These are examples of event conditions for detecting good driving, but unlike dangerous driving, good driving is difficult to detect based on changes in G-values, etc. Therefore, as shown in Figure 7, it is preferable that the event conditions for detecting good driving be configured using location information, and vehicle speed and the presence or absence of pedestrians linked to this location information. As mentioned above, location information makes it easier to compare good driving with dangerous driving if it is in a location where dangerous driving is more likely to occur, as opposed to good driving.

[0078] Returning to the description of Figure 6, the image recognition model 14c is an AI (Artificial Intelligence) model for image recognition. The image recognition model 14c is, for example, a DNN (Deep Neural Network) model trained using a deep learning algorithm.

[0079] The image recognition model 14c is read into the controller 15 as a DNN model, and is then configured to be able to detect various objects included in each frame image when each frame image of an in-vehicle video or an outside-vehicle video is input to the controller 15. For example, when each frame image of an outside-vehicle video is input, the image recognition model 14c is configured to be able to detect pedestrians, vehicles, traffic lights, vehicle license plates, the lighting colors of traffic lights, and the like that appear in each frame image.

[0080] Furthermore, the image recognition model 14c is configured to be able to detect, for example, the driver's face captured in each frame image when each frame image of the in-vehicle video is input. Furthermore, the image recognition model 14c is configured to be able to estimate the driver's line of sight, etc., based on a group of facial feature points. Furthermore, the image recognition model 14c is configured to be able to detect objects other than faces.

[0081] The controller 15 corresponds to a so-called processor. The controller 15 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphical Processing Unit), or the like. The controller 15 executes a program according to an embodiment (not shown) stored in the storage unit 14, using RAM as a work area. The controller 15 can also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0082] The controller 15 executes information processing by the drive recorder 10 in the processing sequence shown in Fig. 10. The explanation using Fig. 10 will be given later.

[0083] Next, a configuration example of the center device 100 will be described. Fig. 8 is a diagram showing a configuration example of the center device 100 according to the embodiment. As shown in Fig. 8, the center device 100 has a communication unit 101, a storage unit 102, and a controller 103. In addition, an HMI unit 50 is connected to the center device 100.

[0084] The HMI unit 50 is a component that provides interface components related to input and output to an operator or the like who operates the center device 100. The HMI unit 50 includes an input interface that accepts input operations from an operator or the like. The input interface is realized by, for example, a touch panel. The input interface may also be realized by a keyboard, a mouse, a pen tablet, a microphone, or the like. The input interface may also be realized by software components.

[0085] The HMI unit 50 also includes an output interface that presents visual information and audio information to the operator, etc. The output interface is realized by, for example, a display, a speaker, etc. The HMI unit 50 may also be configured to provide the operator, etc. with an input interface and an output interface as a single unit by, for example, a touch panel display.

[0086] The communication unit 101 is realized by a network adapter etc. The communication unit 101 is connected to the network N by wire or wirelessly, and transmits and receives information between the drive recorder 10 and the student attending device 200 via the network N.

[0087] The storage unit 102 is realized by a storage device such as a ROM, a RAM, a flash memory, an HDD (Hard Disk Drive), etc. In the example of Fig. 8, the storage unit 102 stores a collected information DB 102a, an image recognition model 102b, learning material generation information 102c, a learning material DB 102d, and a student information DB 102e.

[0088] The collected information DB 102a is a database that stores vehicle data collected from each drive recorder 10. The image recognition model 102b is an AI model for image recognition. Like the image recognition model 14c described above, the image recognition model 102b is a DNN model trained using, for example, a deep learning algorithm.

[0089] The image recognition model 102b is loaded into the controller 103 as a DNN model, and is configured to be able to detect various objects contained in each frame image when each frame image of an in-vehicle image or an outside-vehicle image is input to the controller 103.

[0090] The image recognition model 102b is configured to be able to detect, for example, the face of a person appearing in each frame image when each frame image of the in-vehicle video is input. The image recognition model 102b is also configured to be able to extract a group of facial feature points from a face detection frame. The image recognition model 102b is also configured to be able to detect objects other than faces.

[0091] In addition, when each frame image of the outside-of-vehicle video is input, the image recognition model 102b is configured to be able to detect, for example, pedestrians, vehicles, traffic lights, vehicle license plates, and the color of traffic lights that appear in each frame image.

[0092] The teaching material generation information 102c is information in which various parameters are set and used when the controller 103 generates teaching materials. The various parameters include, for example, parameters relating to the screen layout of the teaching material.

[0093] The teaching material DB 102d is a database that stores teaching materials generated by the controller 103. The student information DB 102e is a database that stores information about students of e-learning classes that use teaching materials distributed by the center device 100.

[0094] The controller 103 corresponds to a so-called processor. The controller 103 is realized by a CPU, an MPU, a GPU, or the like. The controller 103 executes a program according to an embodiment (not shown) stored in the storage unit 102, using RAM as a work area. The controller 103 can also be realized by an integrated circuit such as an ASIC or an FPGA.

[0095] The controller 103, like the above-mentioned controller 15, executes information processing by the center device 100 in the processing sequence shown in Fig. 10. The explanation using Fig. 10 will be given later.

[0096] Next, we will explain a configuration example of the attendance device 200. Fig. 9 is a diagram showing a configuration example of the attendance device 200 according to the embodiment. As shown in Fig. 9, the attendance device 200 has an HMI unit 201, a communication unit 202, a storage unit 203, and a controller 204.

[0097] The HMI unit 201 is a component that provides interface components related to input and output for students. The HMI unit 201 is a component similar to the HMI units 11 and 50 already described, and therefore further description will be omitted.

[0098] The communication unit 202 is realized by a network adapter etc. The communication unit 202 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the center device 100 via the network N.

[0099] The storage unit 203 is realized by a storage device such as a ROM, a RAM, a flash memory, a HDD, etc. In the example of Fig. 9, the storage unit 203 stores a teaching material DB 203a.

[0100] The educational material DB 203a is a database in which educational materials received by the controller 204 from the center device 100 via the communication unit 202 are stored.

[0101] The controller 204 corresponds to a so-called processor. The controller 204 is realized by a CPU, an MPU, a GPU, or the like. The controller 204 executes a program according to an embodiment (not shown) stored in the storage unit 203, using RAM as a work area. The controller 204 can also be realized by an integrated circuit such as an ASIC or an FPGA.

[0102] The controller 204, like the above-mentioned controller 15 and controller 103, executes information processing by the student receiving device 200 in the processing sequence shown in FIG.

[0103] Next, the information processing according to this processing sequence will be described. Fig. 10 is a diagram showing the processing sequence executed by the safe driving education system 1 according to the embodiment.

[0104] In the drive recorder 10, the controller 15 records vehicle data (step S101). The controller 15 also determines whether or not a specific event set in the event condition information 14b has been detected (step S102).

[0105] If an event is detected (step S102, Yes), the controller 15 transmits vehicle data for a certain period of time before and after the event detection time to the center device 100 (step S103). If no event is detected (step S102, No), the controller 15 repeats the process from step S101.

[0106] The controller 103 of the center device 100 detects scenes in which good driving was performed based on the vehicle data of step S103 (step S104). Then, the controller 103 determines whether or not the scene in question has been detected (step S105), and if it has been detected (step S105, Yes), generates teaching materials including footage of the scene in question (step S106).

[0107] If the detection is not possible (No at step S105), the controller 103 repeats the process from step S103.

[0108] An example of a teaching material screen in the teaching material generated in step S106 will now be described with reference to Fig. 11. Note that an example of a review-style teaching material screen has already been described with reference to Fig. 4, so here an example of a Q&A-style teaching material screen will be described. Fig. 11 is a diagram showing an example of a Q&A-style teaching material screen displayed on the student learning device 200.

[0109] As shown in Fig. 11, the Q&A style educational material screen DS2 is generated as educational material including a video comparing, for example, a driver who performed good driving with a driver who was judged to have performed relatively poor driving. This makes it easy to understand the difference between good driving and driving that is relatively poor compared to good driving.

[0110] For example, the controller 103 compares the driving results of multiple drivers (two in this case) who drove the same route, and compares various factors that distinguish good driving from bad driving, such as the distance between vehicles, vehicle speed, degree of swaying, and movement of the field of vision.

[0111] The controller 103 then visualizes and highlights the comparison results, such as the aforementioned inter-vehicle distance, vehicle speed, degree of sway, and movement of the field of view, which are differences of interest. FIG. 11 shows an example in which the controller 103 visualizes and highlights the inter-vehicle distance on the educational material screen DS2 with an upward arrow. By visualizing the differences of interest, it is possible to clearly indicate the differences between the videos being compared. Furthermore, by visualizing the inter-vehicle distance with an arrow, it is possible to clearly indicate the difference in inter-vehicle distance based on the length of the arrow, etc.

[0112] If the distribution destination is the company's own company, the controller 103 displays the names of the compared drivers on the educational material screen DS2. In Fig. 11, the comparison targets are Yamada from the sales department and Tanaka from the sales department.

[0113] A question corresponding to this image is displayed, for example, below the image. The student answers the question by selecting an answer from the options provided for the question.

[0114] The method for generating the question sentence is the same as that for the review sentence described above. That is, the controller 103 generates a question sentence with a content corresponding to the degree of match of each of the aforementioned target elements based on the image analysis results of the scene in which Yamada performed good driving. For example, if the degree of match that the target element is a vehicle, the degree of match that the vehicle is ahead, and the degree of match between the inter-vehicle distance based on the vehicle's position and a predetermined appropriate inter-vehicle distance are each above a threshold, the center device 100 generates an option indicating that the correct answer is the appropriate inter-vehicle distance. In response to this, the center device 100 also generates, as an incorrect answer option, each of the target elements (e.g., inattentiveness or speed) whose degree of match is below a threshold.

[0115] Returning to the explanation of Fig. 10, the controller 103 then determines whether or not the educational material generated in step S106 is to be distributed to parties other than the company (step S107). If the educational material is to be distributed to parties other than the company (step S107, Yes), the controller 103 determines whether or not the video included in the educational material is subject to privacy protection (step S108).

[0116] If there is a privacy protection target (step S108, Yes), the controller 103 executes anonymization processing for this protection target (step S109). If there is no distribution to any other company (step S107, No) or if there is no privacy protection target (step S108, No), the controller 103 transitions the processing to step S110.

[0117] An example of the teaching material screen that has been anonymized in step S109 will now be described with reference to Fig. 12. Fig. 12 is a diagram showing an example of the teaching material screen that has been anonymized and is displayed on the student attending device 200. Note that here, the teaching material screen DS3 that has been anonymized from the teaching material screen DS1 shown in Fig. 4 will be taken as an example.

[0118] 12, when the controller 103 distributes the generated teaching materials to a party other than its own company, it performs image processing to conceal personal information as an anonymization process. This image processing involves performing mosaic processing, blurring processing, filling in processing, etc. on specific parts corresponding to, for example, at least a person's face or a vehicle's license plate.

[0119] Fig. 12 shows an example in which mosaic processing is applied to the entire pedestrian detection frame. If personal information is present in the text information, the controller 103 also performs text editing processing to conceal this information as concealment processing. For example, compared to Fig. 4, Fig. 12 shows an example in which "You" and "Sales Department Yamada-san" have been replaced with "Driver."

[0120] When the anonymization process is applied to the educational material screen DS2 in FIG. 11, the license plates of each vehicle are blurred, etc. Furthermore, text information such as "Sales Department, Yamada-san" or "Yamada-san" is replaced with, for example, "Driver C-san." Similarly, text information such as "Sales Department, Tanaka-san" or "Tanaka-san" is replaced with, for example, "Driver D-san." By performing various anonymization processes such as these, it is possible to prevent unnecessary leakage of personal information when expanding to an unspecified number of people outside one's own company.

[0121] Returning to the explanation of Fig. 10, the controller 103 then distributes the educational material to the student attending device 200 based on, for example, an automatic distribution scheduler (not shown) (step S110). Then, in the student attending device 200, the controller 204 presents the distributed educational material to the HMI unit 201 (step S111).

[0122] As described above, the center device 100 according to the embodiment includes the controller 103. The controller 103 receives vehicle data including video of the vehicle's surroundings from the vehicle, detects scenes in which good driving was performed based on the received vehicle data, generates e-learning teaching materials (corresponding to an example of "educational content") including video of the scenes, and distributes the teaching materials to participants including the person who performed the good driving.

[0123] That is, the center device 100 according to the embodiment generates e-learning educational materials including footage of good driving scenes, and distributes the generated educational materials to at least the person who performed the good driving. As a result, the person can receive positive evaluations for themselves through e-learning, and can also feel a sense of satisfaction by having other students receive education based on the good driving they performed. Therefore, the center device 100 according to the embodiment can prevent a decrease in motivation to take e-learning courses, i.e., to take educational content.

[0124] In the above-described embodiment, it is possible to specify a participant other than the company as the distribution destination. However, the participant may be an overseas traveler who has traveled from overseas and rents a car in Japan. In this case, as shown in FIG. 11, a comparison video of a Japanese person driving at the same driving location and a video of an overseas traveler driving at the same driving location are used to visualize the differences in driving style, where the driver is looking, etc., thereby enabling safe driving education for overseas traveler. In other words, according to this embodiment, it is also possible to generate educational content for inbound tourists.

[0125] Furthermore, according to this embodiment, by using comparative footage of driving by an expert and a beginner at the same driving location, it is also possible to generate teaching materials for becoming a veteran driver, which is particularly useful for training commercial vehicle drivers.

[0126] Further advantages and modifications will readily occur to those skilled in the art. Therefore, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents. [Explanation of symbols]

[0127] 1. Safe driving education system 5. In-vehicle sensors 10 Drive Recorder 11 HMI section 12 Sensor section 12a In-car camera 12b Exterior camera 12c GPS sensor 12d G sensor 13 Communications Department 14 Storage section 14a Vehicle data DB 14b Event Condition Information 14c Image Recognition Model 15 Controller 50 HMI section 100 Center Device 101 Communications Department 102 Storage section 102a Collected Information DB 102b Image Recognition Model 102c Teaching material generation information 102d Teaching material DB 102e Participant Information DB 103 Controller 200 Learning Device 201 HMI Department 202 Communications Department 203 Storage section 203a Teaching material DB 204 Controller

Claims

1. receiving vehicle data including images of the vehicle's surroundings from the vehicle; Detecting scenes of good driving based on the received vehicle data; Generate educational content including footage of the scene, a controller that distributes the educational content to participants including the person who performed the good driving; A center device comprising:

2. The controller The educational content is generated in a review format in which a review explaining the scene is posted together with a video of the scene in which the good driving was performed, or in a Q&A format in which a question and answer session related to the scene is provided together with a video of the scene in which the good driving was performed. The center device according to claim 1 .

3. The image of the scene where the good driving was performed is a first image, The controller A second image, which is an image of a case where driving that is worse than the good driving is performed in the same location as the scene where the good driving is performed, is placed next to the first image as a comparison image. The center device according to claim 2 .

4. The controller highlighting a portion of interest that is different between the first image and the second image; The center device according to claim 3 .

5. The portion of interest is at least the distance between vehicles. The center device according to claim 4.

6. The controller highlighting the vehicle-to-vehicle distance with an arrow; The center device according to claim 5 .

7. The controller A situation in which a driver gives way to a pedestrian at a crosswalk without traffic lights is detected as a scene in which good driving has been performed. The center device according to claim 1 .

8. The controller The educational content is provided so as to be able to be distributed to an unspecified number of students, When distributing the educational content to the unspecified number of students, a concealment process is performed to conceal personal information in the educational content. The center device according to any one of claims 1 to 7.

9. The system comprises an in-vehicle device, a center device, and a terminal device used by a student, The in-vehicle device Transmitting vehicle data including an image of the area around the vehicle to the center device; The center device receiving the vehicle data from the in-vehicle device; Detecting scenes of good driving based on the received vehicle data; Generate educational content including footage of the scene, delivering the educational content to the terminal devices of the participants, including the person who performed the good driving; The terminal device receiving the educational content from the center device; Safe driving education system.

10. receiving vehicle data from a vehicle, the vehicle data including an image of an area around the vehicle; Detecting good driving scenes based on the received vehicle data; generating educational content including the video of the scene; delivering the educational content to participants including the person who performed the good driving; Safe driving education methods, including:

Images