JP7436061B2 - Driving support devices, methods and programs - Google Patents

Description

The present invention relates to a driving support device, method, program, and system.

BACKGROUND ART In recent years, it has become a social problem for a vehicle to be victimized by so-called aggressive driving by another vehicle while driving. Here, Patent Document 1 discloses a technique for providing information to encourage the driver of the own vehicle to take self-defense when it is determined that the driver of another vehicle is a habitual driver of aggressive driving.

Japanese Patent Application Publication No. 2018-112892

However, Patent Document 1 has a problem in that the accuracy of determining whether or not another vehicle is aggressively driving with respect to the own vehicle is insufficient. The reason for this is that the criteria for determining aggressive driving in Patent Document 1 are uniform and subjective.

The present disclosure has been made to solve such problems, and provides a driving support device, a method, and a driving support device for improving the accuracy of determining whether or not another vehicle is aggressively driving with respect to one's own vehicle. The purpose is to provide programs and systems.

The driving support device according to the first aspect of the present disclosure includes:
an acquisition unit that acquires surrounding images taken from the own vehicle while it is running;
a selection unit that selects candidate vehicles that may be driving aggressively toward the own vehicle from among other vehicles included in the surrounding image;
a collection unit that collects detailed information regarding the candidate vehicle;
a determination unit that obtains a determination result as to whether or not the candidate vehicle is driving aggressively based on the detailed information;
a notification unit that notifies outside of notification information including the detailed information when the determination result indicates that the candidate vehicle is driving aggressively;
Equipped with.

The driving support method according to the second aspect of the present disclosure includes:
The computer is
Obtain surrounding images taken from the own vehicle while driving,
Selecting candidate vehicles that are likely to be driving aggressively toward the host vehicle from among other vehicles included in the surrounding image;
collecting detailed information about the candidate vehicle;
Obtaining a determination result as to whether the candidate vehicle is driving aggressively based on the detailed information;
When the determination result indicates that the candidate vehicle is driving aggressively, notification information including the detailed information is notified to the outside.

The driving assistance program according to the third aspect of the present disclosure includes:
Acquisition processing that acquires surrounding images taken from the own vehicle while driving;
Selection processing for selecting candidate vehicles that may be driving aggressively toward the host vehicle from among other vehicles included in the surrounding image;
a collection process of collecting detailed information regarding the candidate vehicle;
a determination process that obtains a determination result as to whether or not the candidate vehicle is driving aggressively based on the detailed information;
If the determination result indicates that the candidate vehicle is driving aggressively, a notification process that notifies an external party of notification information including the detailed information;
have the computer execute it.

The driving support system according to the fourth aspect of the present disclosure includes:
an acquisition unit that acquires a surrounding image taken from the own vehicle while it is running;
a selection unit that selects a candidate vehicle that is likely to be driving aggressively toward the host vehicle from among other vehicles included in the surrounding image;
a collection unit that collects detailed information regarding the candidate vehicle;
an in-vehicle device having;
a server connected to the in-vehicle device via a network;
Equipped with
The in-vehicle device transmits the collected detailed information to the server via the network,
The server is
Determining whether or not the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
Information based on the result of the determination is notified to the outside via the network.

A driving support device according to a fifth aspect of the present disclosure includes:
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an on-vehicle device. a receiving unit that receives from the in-vehicle device via a network;
a determination unit that determines whether the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
a notification unit that notifies information based on the determination result by the determination unit to the outside via the network;
Equipped with.

The driving support method according to the sixth aspect of the present disclosure includes:
The computer is
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an on-vehicle device. is received from the in-vehicle device via the network,
Determining whether the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
Information based on the result of the determination is notified to the outside via the network to the in-vehicle device.

The driving assistance program according to the seventh aspect of the present disclosure includes:
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an on-vehicle device. from the in-vehicle device via a network;
A process of determining whether or not the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
a process of notifying information based on the determination result to the in-vehicle device externally via the network;
have the computer execute it.

According to the present disclosure, it is possible to provide a driving support device, method, program, and system for improving the accuracy of determining whether or not another vehicle is aggressively driving with respect to the own vehicle.

1 is a block diagram showing the configuration of a driving support device according to the first embodiment. FIG. 3 is a flowchart showing the flow of the driving support method according to the first embodiment. FIG. 2 is a block diagram showing the configuration of a driving support system according to a second embodiment. FIG. 3 is a sequence diagram showing the flow of the driving support method according to the second embodiment. FIG. 7 is a diagram for explaining the concept of a driving support system according to the third embodiment. FIG. 7 is a block diagram showing the configuration of a group of on-vehicle devices mounted on the host vehicle according to the third embodiment. FIG. 3 is a block diagram showing the hardware configuration of a reporting unit according to the third embodiment. 7 is a sequence diagram showing the flow of a driving support method according to the third embodiment. FIG. FIG. 3 is a block diagram showing the configuration of a driving support system according to a fourth embodiment. FIG. 12 is a sequence diagram showing the flow of collection of learning data for a judgment model, learning process, and subsequent judgment process according to the fourth embodiment.

Embodiments of the present disclosure will be described in detail below with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and for clarity of explanation, redundant explanation will be omitted as necessary. Note that hereinafter, a vehicle equipped with a driving support device according to each embodiment will be referred to as a "self-vehicle". Furthermore, the term "vehicle-mounted device" in this specification does not necessarily have to be built into the vehicle, and includes any device that can be removed from the vehicle at will, such as a portable terminal.

<Embodiment 1>
FIG. 1 is a block diagram showing the configuration of a driving support device 1 according to the first embodiment. The driving support device 1 is, for example, an information processing device such as an in-vehicle device mounted on an automobile (own vehicle). It is assumed that the own vehicle is equipped with a camera capable of photographing at least either the front or the rear, and images of the own vehicle while driving are recorded.

Further, it is assumed that the host vehicle is traveling on a predetermined road at a predetermined speed or higher, for example, 60 km/h or higher, and one or more other vehicles (other automobiles) are traveling in the vicinity. It is assumed that the other vehicle is running in front of, behind, to the side (laterally), diagonally, etc. of the own vehicle.

The driving support device 1 includes an acquisition section 11 , a selection section 12 , a collection section 13 , a determination section 14 , and a notification section 15 . The acquisition unit 11 acquires a surrounding image photographed from the own vehicle while the vehicle is running. Note that the surrounding image includes one or more other vehicles. The selection unit 12 selects candidate vehicles that are likely to be driving aggressively toward the own vehicle from among other vehicles included in the surrounding image.

For example, the selection unit 12 analyzes the surrounding image, extracts the shape of the other vehicle, and calculates the inter-vehicle distance between the own vehicle and the other vehicle based on the position of the other vehicle in the image. Then, when the inter-vehicle distance is less than or equal to a predetermined distance, the selection unit 12 determines that there is a possibility that another vehicle is driving at the vehicle, and determines that the other vehicle is driving at the other vehicle. Selected as a possible candidate vehicle. Note that the selection unit 12 may select two or more candidate vehicles. Note that the method of selection by the selection unit 12 is not limited to this, and for example, the aggressive driving determination process described in Patent Document 1 may be applied.

Here, aggressive driving refers to driving that is done intentionally by the driver of another vehicle, in other words, a driving situation in which the vehicle movements of the other vehicle are under the control of the driver, and is considered dangerous driving such as drunk driving. is different. Therefore, even if the driver of the own vehicle tries to move away from another vehicle, the driver of the other vehicle intentionally follows or does not let the driver move away from the other vehicle. This includes conditions such as those listed in the operating conditions. In other words, aggressive driving includes a state in which another vehicle intentionally follows (repeatedly approaches rapidly, etc.) the host vehicle.

When a candidate vehicle is selected by the selection unit 12, the collection unit 13 collects detailed information regarding the candidate vehicle. Detailed information includes an enlarged image of a specific area of the candidate vehicle, the analysis result of the enlarged image, the time during which the distance between the candidate vehicle and your own vehicle is maintained within a predetermined distance, and the number of times the inter-vehicle distance is within a predetermined distance. Examples include, but are not limited to, the following. Note that the collection unit 13 may aggregate various collected information to generate detailed information on the candidate vehicle.

The determination unit 14 obtains a determination result as to whether or not the candidate vehicle is performing aggressive driving based on the detailed information. Here, the determination unit 14 inputs the detailed information collected this time to the "determination model for aggressive driving" learned in advance based on the detailed information, and obtains the output of the determination model as the determination result. is desirable. Thereby, it is possible to perform a more accurate determination that reflects past cases of aggressive driving. In this case, the determination model only needs to be held inside or outside the driving support device 1.

When the determination result by the determination unit 14 indicates that the candidate vehicle is driving aggressively, the notification unit 15 notifies the outside of notification information including detailed information. Here, the outside may be, for example, the police or other institutions, as long as they have equipment that can notify by wireless communication. The notification can be made by using communication means such as a telephone or e-mail.

FIG. 2 is a flowchart showing the flow of the driving support method according to the first embodiment. First, the acquisition unit 11 acquires a surrounding image photographed from the own vehicle while it is running (S11). Next, the selection unit 12 selects candidate vehicles that are likely to be driving aggressively toward the own vehicle from among other vehicles included in the surrounding image (S12).

After step S12, that is, when the selection unit 12 selects a candidate vehicle, the collection unit 13 collects detailed information regarding the candidate vehicle (S13). Subsequently, the determination unit 14 obtains a determination result as to whether or not the candidate vehicle is performing aggressive driving based on the detailed information (S14). Thereafter, when the determination result in step S14 indicates that the candidate vehicle is driving aggressively, the notification unit 15 notifies the outside of notification information including detailed information (S15).

In this manner, in the present embodiment, in step S12, a candidate vehicle that is likely to be driving aggressively is selected from the surrounding images, and then detailed information that can be determined in detail about the candidate vehicle is collected. Then, based on the collected detailed information, it is again determined whether the candidate vehicle is driving aggressively. Therefore, it is possible to improve the accuracy of determining whether or not another vehicle is aggressively driving with respect to the own vehicle.

Furthermore, if it is determined that the candidate vehicle is driving aggressively, detailed information regarding the candidate vehicle can be notified to the outside. Furthermore, appropriate information can be notified. Therefore, the notified organization can take appropriate measures and support the driver of the own vehicle.

Note that the driving support device 1 includes a processor, a memory, and a storage device, which are not shown in the drawings. Further, the storage device stores a computer program in which the processing of the driving support method according to the present embodiment is implemented. Then, the processor reads a computer program from the storage device into the memory and executes the computer program. Thereby, the processor realizes the functions of the acquisition section 11, the selection section 12, the collection section 13, the determination section 14, and the notification section 15.

Alternatively, the acquisition unit 11, the selection unit 12, the collection unit 13, the determination unit 14, and the notification unit 15 may each be realized by dedicated hardware. Further, a part or all of each component of each device may be realized by a general-purpose or dedicated circuit, a processor, etc., or a combination thereof. These may be configured by a single chip or multiple chips connected via a bus. A part or all of each component of each device may be realized by a combination of the circuits and the like described above and a program. Further, as the processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), an ECU (Electronic Control Unit), etc. can be used.

In addition, when some or all of the components of the driving support device 1 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. are centrally arranged within the host vehicle. It may also be arranged in a distributed manner. Further, the function of the determination model of the driving support device 1 may be provided in a SaaS (Software as a Service) format.

<Embodiment 2>
The second embodiment is a modification of the first embodiment described above, and relates to a driving support system that is an information system for supporting the driver of the own vehicle described above. FIG. 3 is a block diagram showing the configuration of a driving support system 2000 according to the second embodiment. The driving support system 2000 includes an in-vehicle device 1a and a server 2, each of which is connected via a network N. The network N is a communication network connected to the Internet line via a wireless communication network.

The in-vehicle device 1a is an example of a driving support device mounted on the own vehicle, and the same components as the driving support device 1 described above are denoted by the same reference numerals, and detailed description thereof will be omitted. The in-vehicle device 1a includes an acquisition section 11, a selection section 12, a collection section 13, a notification section 15, a transmission section 16, and a reception section 17. The transmitter 16 transmits the detailed information collected by the collector 13 to the server 2 via the network N. The receiving unit 17 receives the result of the determination as to whether or not the candidate vehicle is performing aggressive driving, which has been determined by the server 2 based on the detailed information. That is, it can be said that the receiving section 17 acquires (receives) the determination result from outside the device, and the above-mentioned determining section 14 acquires the determination result from inside the device. Note that when the determination result received from the server indicates that the candidate vehicle is driving aggressively, the notification unit 15 notifies the outside of notification information including detailed information. At this time, the notification unit 15 may make the notification via the network N, or may make the notification via a wireless telephone network (not shown) or the like. Alternatively, the notification unit 15 may be provided outside the vehicle (for example, on the server 2, etc.).

The server 2 is a computer system configured with one or more information processing devices, and can also be called a driving support device according to this embodiment. The server 2 includes a receiving section 21, a determining section 22, and a notifying section 23. The receiving unit 21 receives detailed information from the transmitting unit 16 via the network N. The determination unit 22 determines whether the candidate vehicle is performing aggressive driving based on the detailed information received from the on-vehicle device 1a. Here, the determination unit 22 inputs the detailed information collected this time to the "agitation driving determination model" learned in advance based on the detailed information, and uses the output of the determination model as the determination result. desirable. Thereby, it is possible to perform a more accurate determination that reflects past cases of aggressive driving. In this case, the determination model is typically held inside the server 2, and at least outside the vehicle-mounted device 1a. The notification unit 23 returns the determination result by the determination unit 22 to the in-vehicle device 1a via the network N. Therefore, the above-mentioned transmitter 16 can be said to transmit the detailed information collected by the collector 13 to the server 2 provided with the determination model. Further, the above-mentioned receiving unit 17 can be said to receive from the server 2 an output when detailed information is input to the determination model in the server 2 as a determination result.

FIG. 4 is a sequence diagram showing the flow of the driving support method according to the second embodiment. First, steps S11 to S13 are the same as those in FIG. 2 described above except that they are executed by the in-vehicle device 1a, so a detailed explanation will be omitted. Next, the transmitter 16 transmits the detailed information collected by the collector 13 to the server 2 via the network N (S21).

Subsequently, the receiving unit 21 of the server 2 receives detailed information from the transmitting unit 16 via the network N. Then, the determination unit 22 determines whether the candidate vehicle is performing aggressive driving based on the detailed information received from the in-vehicle device 1a (S22). Thereafter, the notification unit 23 returns the determination result to the in-vehicle device 1a via the network N (S23).

Then, the receiving unit 17 of the in-vehicle device 1a receives the determination result from the server 2. When the determination result received from the server indicates that the candidate vehicle is driving aggressively, the notification unit 15 notifies the outside of notification information including detailed information (S15).
Note that, as described above, the in-vehicle device 1a does not necessarily need to be provided with the notification section 15. In that case, for example, the notification unit 23 of the server 2 may execute steps equivalent to step S23 instead of step S23. That is, when the result of the determination indicates that the candidate vehicle is driving aggressively, the notification unit 23 of the server 2 notifies the outside of notification information including detailed information. Alternatively, in addition to the in-vehicle device 1a and the server 2, there may be a notification device that notifies the police or the like. In that case, the notification unit 23 of the server 2 may set the notification device as the transmission destination in step S23.

In this way, in this embodiment, since the server side can determine whether or not another vehicle is aggressively driving the host vehicle, the processing load on the in-vehicle device is reduced compared to Embodiment 1. can. Therefore, the server 2 can perform more advanced determination processing and improve the determination accuracy. Further, as in the first embodiment, since appropriate information can be notified, it is possible to support the driver of the own vehicle.

Note that the server 2 includes a processor, a memory, and a storage device (not shown). Further, the storage device stores a computer program in which the processing of the driving support method according to the present embodiment is implemented. Then, the processor reads a computer program from the storage device into the memory and executes the computer program. Thereby, the processor realizes the functions of the receiving section 21, the determining section 22, and the notifying section 23.

Alternatively, the receiving section 21, the determining section 22, and the notifying section 23 may each be realized by dedicated hardware. Further, a part or all of each component of each device may be realized by a general-purpose or dedicated circuit, a processor, etc., or a combination thereof. These may be configured by a single chip or multiple chips connected via a bus. A part or all of each component of each device may be realized by a combination of the circuits and the like described above and a program. Further, as the processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), an ECU (Electronic Control Unit), etc. can be used.

Further, in the case where a part or all of each component of the server 2 is realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be centrally arranged or distributed. may be done. For example, information processing devices, circuits, etc. may be realized as a client server system, a cloud computing system, or the like, in which each is connected via a communication network. Furthermore, the functions of the server 2 may be provided in a SaaS (Software as a Service) format.

The in-vehicle device 1a has the same hardware configuration as the driving support device 1 described above, and the processor reads a computer program from a storage device into the memory and executes the computer program. Thereby, the processor realizes the functions of the acquisition section 11, the selection section 12, the collection section 13, the notification section 15, the transmission section 16, and the reception section 17.

<Embodiment 3>
Here, the problem to be solved by this embodiment will be explained in detail.
In recent years, many drivers have fallen victim to aggressive driving, which has become a major stress factor. There have also been reports of malicious incidents where people are relentlessly chased, leading to major accidents. Although the police are tightening their crackdown on aggressive driving, they have not been able to catch all aggressive driving, so the damage caused by aggressive driving continues to be a social problem.

Typical responses that can be taken by a driver who has been victimized by aggressive driving include, for example, taking video evidence and reporting the incident to the police. However, it is difficult for a driver to make a report while driving in real time from the viewpoint of safety. Therefore, it is necessary to report again after stopping the own vehicle. However, it can be said that there is psychological resistance to reporting in the first place. Therefore, reporting is a heavy burden on drivers. Another problem is that there are few measures that drivers can take when they are victims of aggressive driving.

Therefore, it is possible to make a report immediately during or immediately after being a victim of aggressive driving, the driver can make a report without making any special movements while driving, and the driver can prepare just the right amount of valid information when making a report. etc. are required.

Therefore, the third embodiment is a specific example of the first embodiment described above, and a method that solves at least a part of the above-mentioned problems will be described below.

FIG. 5 is a diagram for explaining the concept of a driving support system 3000 according to the third embodiment. The driving support system 3000 shows a situation where the own vehicle 4 that is running is being bullied by another vehicle 5 behind it. Further, it is assumed that the host vehicle 4 is equipped with the in-vehicle device group 40 according to the present embodiment and is capable of communicating with the communication device 31 of the notification destination 3 via the communication network N1. It is assumed that the communication network N1 is a communication line including at least a mobile phone line network or a wireless communication network. It is assumed that the notification destination 3 is, for example, the police, and the operator 32 can receive notification information from the in-vehicle device group 40 through the communication device 31. In the following explanation, it is assumed that the own vehicle 4 is traveling on a predetermined road (for example, an expressway) at a predetermined speed or higher, for example, 60 km/h or higher, and is not repeatedly accelerating or decelerating excessively. It is assumed that the vehicle is traveling 0.3 m or more inside from the outside line.

FIG. 6 is a block diagram showing the configuration of the on-vehicle device group 40 mounted on the host vehicle according to the third embodiment. The in-vehicle device group 40 includes an illuminance sensor 41, a microphone 42, a reporting unit 43, a camera unit 44, a GPS (Global Positioning System) information receiver 45, a communication device 46, a speed measuring device 47, and a manual reporting device. button 48.

The illuminance sensor 41 is a sensor that detects illuminance indicating the brightness of light illuminating the surroundings of the host vehicle, and outputs the detected illuminance to the reporting unit 43. For example, the illuminance sensor 41 can detect that the vehicle has received passing light from another vehicle toward the vehicle.

The microphone 42 is a device that collects sounds around the host vehicle, and outputs the collected sound information to the reporting unit 43. For example, the microphone 42 can detect the sound of a horn from another vehicle.

The GPS information receiver 45 outputs position information (GPS information) based on GPS signals received from GPS satellites to the reporting unit 43.

The communication device 46 is a device for transmitting and receiving wireless signals to and from the outside, such as the communication network N1. The communication device 46 transmits a wireless signal to the communication network N1 or the like in response to an instruction from the notification unit 43, and outputs information based on the wireless signal received from the communication network N1 or the like to the notification unit 43.

The speed measuring device 47 is a device that measures the traveling speed of the own vehicle and outputs it to the reporting unit 43. Note that the speed measuring device 47 may be realized by a dedicated unit, or may use vehicle speed information used in a speedometer or the like inside the automobile.

The manual notification button 48 is a button that can be pressed by a fellow passenger such as the driver of the own vehicle, and when the button is pressed, a signal indicating that fact is output to the notification unit 43. For example, if the driver of his/her own vehicle feels that he/she is being victimized by aggressive driving from another vehicle, he/she can start the process of collecting detailed information by pressing the manual report button 48. Therefore, it is possible to easily notify the destination 3 of the intention of the driver or the like.

The camera unit 44 includes front and rear cameras 441, a camera ECU 442, and an HDD (Hard Disk Drive) 443. The front and rear cameras 441 are a group of photographing devices that take images of at least the front and rear surroundings of the own vehicle, such as a first camera device that takes pictures of the front surroundings of the own vehicle, and a second camera device that takes pictures of the rear surroundings of the own vehicle. camera device. Furthermore, the front and rear cameras 441 may include a camera device that photographs the side (lateral direction) of the own vehicle. Alternatively, the front and rear cameras 441 may be a camera device capable of 360-degree photography.

The HDD 443 is a recording medium that records video data, which is a group of peripheral images continuously photographed by the front and rear cameras 441. Note that the recording medium is not limited to an HDD.

Camera ECU 442 is a control device that controls front and rear cameras 441 and HDD 443. The camera ECU 442 acquires peripheral images from the front and rear cameras 441 or the HDD 443 and outputs them to the reporting unit 43.

The notification unit 43 is an example of an in-vehicle device or a driving support device, and includes a storage section 430, an acquisition section 431, a primary determination section 432, a collection section 433, a secondary determination section 434, a notification information generation section 435, a mail function section 436, and A telephone function section 437 is provided.

The storage unit 430 is a storage device that stores a determination model 4301, map information 4302, and the like. The determination model 4301 is a program module or a model formula in which a process is implemented that receives detailed information regarding the candidate vehicle, performs a predetermined calculation using set parameters, and outputs the calculation result. For example, the determination model 4301 is a mathematical model that uses each data of detailed information as an element of input data and performs calculations using predetermined parameters (weighting coefficients) for each input data. Note that the judgment model 4301 may be one expressed by a neural network, a support vector machine, or the like. Furthermore, in this embodiment, the output result of the determination model 4301 is used as a secondary determination result of whether or not the candidate vehicle is aggressively driving with respect to the own vehicle. Map information 4302 is general map data including road information.

The acquisition unit 431 is an example of the acquisition unit 11, and acquires peripheral images from the camera ECU 442.

The primary determination unit 432 analyzes the surrounding image acquired by the acquisition unit 431 and performs a primary determination as to whether there is a possibility that another vehicle included in the surrounding image is driving aggressively. The primary determination unit 432 is an example of the selection unit 12, and may select candidate vehicles using the selection method described above in the first embodiment. Here, it is assumed that a boundary line on the own vehicle side in the surrounding image and a threshold value for a predetermined distance are determined in advance. In that case, for example, the primary determination unit 432 first analyzes the surrounding image to identify one or more other vehicle areas. The primary determination unit 432 then calculates the distance between each identified area and the boundary line as an inter-vehicle distance, and determines that the other vehicle is a candidate vehicle when the inter-vehicle distance is less than or equal to a predetermined distance. In other words, the primary determination unit 432 performs a primary determination that there is a possibility that the other vehicle is driving aggressively toward the own vehicle.

Further, the primary determination unit 432 selects the other vehicle as a candidate vehicle when the inter-vehicle distance between the other vehicle and the own vehicle becomes less than or equal to a predetermined distance after the other vehicle cuts in front of the own vehicle. You may also do so. Thereby, it is possible to prevent candidate vehicles that are likely to be involved in aggressive driving from being omitted. Alternatively, the primary determination unit 432 may select the other vehicle as a candidate vehicle when the lateral inter-vehicle distance between the other vehicle and the own vehicle continues to be less than or equal to a predetermined distance for a certain period of time. This also makes it possible to prevent candidate vehicles that are likely to be involved in aggressive driving from being omitted. Note that the lateral inter-vehicle distance is calculated when the front and rear cameras 441 include a camera device that photographs the lateral surroundings of the own vehicle, or when a part of the surrounding image photographed from the front or rear (for example, a side mirror) is used. It can be calculated from the area of other vehicles.

The collection unit 433 is an example of the collection unit 13, and collects and generates collected information regarding the candidate vehicle when the primary determination unit 432 determines that there is a possibility of aggressive driving. For example, the collection unit 433 collects information related to the position of the own vehicle. The location-related information includes, for example, GPS information (coordinates, etc.) indicating the current location of the vehicle, the name of the road on which the vehicle is traveling, the distance from the nearest IC (InterChange), etc. For example, the collection unit 433 acquires GPS information from the GPS information receiver 45, refers to the map information 4302 in the storage unit 430, and collects the information by identifying road names and the like.

The collection unit 433 also acquires and analyzes detailed images of candidate vehicles. In other words, the collection unit 433 collects an image taken by enlarging a specific area of the candidate vehicle among the surrounding images as detailed information. For example, the collection unit 433 identifies the area of the license plate of the candidate vehicle from the surrounding image, and instructs the camera ECU 442 to focus on the identified area. The camera ECU 442 causes the front and rear cameras 441 to focus in accordance with the instruction, and shoot a detailed image (enlarged image) of the license plate. The collection unit 433 analyzes the photographed detailed image of the license plate and converts the number into text to provide detailed information. Alternatively, the collection unit 433 may specify the face area of the driver of the candidate vehicle from the surrounding images and instruct the camera ECU 442 to focus on the specified face area. In that case, the collection unit 433 uses the photographed face image of the driver of the candidate vehicle as detailed information. Note that the collection unit 433 may set another area as the specific area. With these, it is possible to provide a sufficient amount of information to the notification destination 3 while improving the accuracy of the secondary determination.

Additionally, the collection unit 433 measures information related to the inter-vehicle distance. For example, the collection unit 433 counts (measures) the number of times the inter-vehicle distance between the candidate vehicle and the host vehicle becomes less than or equal to a predetermined distance within a predetermined period from a plurality of surrounding images during a predetermined period, and collects the count as detailed information. Alternatively, the collection unit 433 collects, as detailed information, information that measures the duration of time during which the inter-vehicle distance becomes less than or equal to a predetermined distance. Alternatively, the collection unit 433 may measure both the number of times and the duration. Further, the collection unit 433 may determine the inter-vehicle distance and relative speed using a white line or the like in the surrounding image, and use the information as information related to the inter-vehicle distance. Here, a TOF (Time-Of-Flight) camera, LiDAR (Light Detection And Ranging), or the like may be used for the measurement.

Furthermore, the collection unit 433 collects at least one of light and sound detected from around the host vehicle as detailed information. For example, the collection unit 433 may measure the number of times the own vehicle has received passing from other vehicles based on the output from the illuminance sensor 41, and may use this as detailed information. Further, the collection unit 433 may measure the volume and number of times the host vehicle is honked by another vehicle based on the output from the microphone 42, and may use this information as detailed information.

Furthermore, if the phone number, driver name, etc. of the driver of the own vehicle, or identification information of the driver or the own vehicle is registered in advance in the storage unit 430, the collection unit 433 collects these information from the storage unit 430. It may be collected and included in detailed information. Thereby, more accurate information can be conveyed to the notification destination 3.

Note that the collection unit 433 performs the same collection process as described above also when the manual report button 48 is pressed.

The secondary determination unit 434 inputs detailed information to the aggressive driving determination model 4301 learned in advance based on past detailed information, and acquires the output of the determination model as a (secondary) determination result. In other words, the secondary determination unit 434 performs a secondary determination of whether or not the candidate vehicle is aggressively driving the host vehicle, based on detailed information about the candidate vehicle. It is preferable that the determination model 4301 is subjected to machine learning in advance. In other words, the learned determination model 4301 performs a secondary determination by comprehensively considering information related to the position of the host vehicle, detailed images of candidate vehicles, measured values related to the inter-vehicle distance, and the like. Therefore, the determination accuracy is further improved.

Note that the secondary determination unit 434 may use a determination model in which at least a portion of the following algorithm is implemented. For example, the secondary determination unit 434 determines that if the host vehicle 4 maintains a distance of less than 5 meters from the other vehicle 5 for more than 3 minutes, or if the vehicle 4 approaches the distance of less than 5 meters and leaves the other vehicle 5 within 5 minutes. If the process is repeated five or more times, it may be determined that the other vehicle 5 is driving in a teasing manner. Further, the secondary determination unit 434 determines that the other vehicle 5 is driving in a vehement manner when the own vehicle 4 is maintained in a state of less than 0.5 m in the lateral direction from the other vehicle 5 for more than 1 minute. Good too. Further, the secondary determination unit 434 may determine that the other vehicle 5 is driving aggressively when the host vehicle 4 receives passing from the other vehicle 5 five or more times within one minute. Further, the secondary determination unit 434 may determine that the other vehicle 5 is driving aggressively when the host vehicle 4 is honked by the other vehicle 5 three or more times within one minute. . The determination model can be set using the speed, distance, time, and number of times in the secondary determination as parameters, and the settings may be changed arbitrarily by the user, or the parameters may be updated by machine learning.

The notification information generation unit 435 generates notification information including detailed information when the determination result of the secondary determination unit 434 indicates that the other vehicle 5 is driving. For example, the notification information generation unit 435 includes, in the notification information, a message to the effect that the driver has been a victim of aggressive driving and that the video data has been saved, along with the detailed information described above. If the notification method is e-mail, the notification information generation unit 435 outputs the notification information converted into text to the mail function unit 436. At this time, the e-mail address of the notification destination may be specified. Note that the e-mail address of the notification destination is stored in advance in the storage unit 430, and may be all or an arbitrarily selected part of the plurality of notification destinations. Further, when the notification method is a telephone, the notification information generation unit 435 converts the notification information into voice information by voice synthesis and outputs the voice information to the telephone function unit 437. At this time, a telephone number of the notification destination may be specified. Note that the telephone number of the notification destination is stored in advance in the storage unit 430, and may be one arbitrarily selected from a plurality of notification destinations. Note that the notification information generation unit 435 does not necessarily have to output all of the notification information to the telephone function unit 437 at once. For example, the notification information generation unit 435 initially instructs the telephone function unit 437 to make a call to a predetermined notification destination telephone number, and in response to an inquiry from the operator 32 received by the communication device 31, the notification information generation unit 435 may convert the corresponding information from the notification information into voice and output it via the telephone function section 437.

The mail function unit 436 uses the notification information output from the notification information generation unit 435 as the body of the email, and sends the email to the designated email address of the notification destination via the communication network N1 using the communication device 46. .

The telephone function section 437 uses the communication device 46 to make a call to the telephone number of the notification destination instructed by the notification information generation section 435 via the communication network N1, and vocalizes the audio information of the notification information. Further, the telephone function section 437 outputs the contents received from the operator 32 via the communication device 31, the communication network N1, and the communication device 46 to the notification information generation section 435.

FIG. 7 is a block diagram showing the hardware configuration of the reporting unit 43 according to the third embodiment. The reporting unit 43 includes a storage device 401 , a control section 402 , a memory 403 , and an IF (InterFace) section 404 . The storage device 401 is a nonvolatile storage device such as a hard disk or flash memory. The storage device 401 stores a determination model 4011 and a driving support program 4012. The judgment model 4011 corresponds to the judgment model 4301 described above, and the settings of the parameters 40111 can be changed from the outside. The driving support program 4012 is a computer program in which the processing of the driving support method according to this embodiment is implemented.

The memory 403 is a volatile storage device such as a RAM (Random Access Memory), and is a storage area for temporarily holding information when the control unit 402 operates. The IF section 404 is an interface that performs input/output between the reporting unit 43 and the outside. For example, the IF unit 404 outputs input data from the outside to the control unit 402, and outputs data received from the control unit 402 to the outside.

The control unit 402 is a processor that controls each component of the notification unit 43, that is, a control device. The control unit 402 reads the driving support program 4012 from the storage device 401 into the memory 403 and executes the driving support program 4012. Further, the control unit 402 appropriately loads the determination model 4011 from the storage device 401 into the memory 403 and executes it. Thereby, the control unit 402 realizes an acquisition unit 431, a primary determination unit 432, a collection unit 433, a secondary determination unit 434, a notification information generation unit 435, a mail function unit 436, and a telephone function unit 437.

FIG. 8 is a sequence diagram showing the flow of the driving support method according to the third embodiment. First, it is assumed that the front and rear cameras 441 continuously capture peripheral images including the other vehicle 5 while the host vehicle 4 is traveling. At this time, the acquisition unit 431 acquires a peripheral image from the camera ECU 442 (S301). Next, the primary determination unit 432 analyzes the surrounding image (S302). Then, the primary determination unit 432 performs a primary determination of the driving driving (S303).

If a candidate vehicle is selected in the primary determination result of aggressive driving (YES in step S303), steps S304 to S306 are executed. That is, the collection unit 433 collects location-related information (S304). The collection unit 433 also acquires and analyzes detailed images of the candidate vehicle (S305). The collection unit 433 also measures information related to the inter-vehicle distance (S306).

On the other hand, if the candidate vehicle is not selected in the primary determination result of the aggressive driving (NO in step S303), the process returns to step S301 and continues.

After steps S304 to S306, the secondary determination unit 434 performs a secondary determination of turbulent driving (S307). For example, the secondary determination unit 434 inputs detailed information to the determination model 4301 and outputs a determination result.

If it is determined that the candidate vehicle is driving aggressively in the secondary determination result of aggressive driving (YES in step S307), the notification information generation unit 435 generates notification information (S308), and sends the notification information to the mail function unit 436 or The telephone function unit 437 transmits the notification information to the communication device 31 via the communication device 46 and the communication network N1 (S309). Note that if the determination in step S307 is NO, the process returns to step S301 and continues.

Note that the notification unit 43 determines whether or not the manual notification button 48 has been pressed by the driver or the like at an arbitrary timing. For example, if the candidate vehicle is not selected in the primary determination result of aggressive driving (NO in step S303), or if it is not determined that the candidate vehicle is performing aggressive driving in the secondary determination result (NO in step S307) These include, but are not limited to: If it is determined that the manual notification button 48 has been pressed, the closest vehicle among the other vehicles in the surrounding image is identified as a candidate vehicle for aggressive driving. In that case, steps S309 and S310 are executed. In particular, in step S309, it is desirable that the notification information generation unit 435 generates the notification information further including the fact that the notification is based on the driver's subjective judgment rather than the system. In this way, for example, even if the primary determination does not meet the uniform judgment criteria for aggressive driving, if the driver or passenger of the own vehicle 4 feels that aggressive driving is occurring, the manual notification button 48 can be pressed. You can notify by pressing it. This allows the driver and the like to be notified easily and quickly.

In this way, in this embodiment, a variety of detailed information is collected to comprehensively perform the secondary judgment, so it is possible to exclude cases where the uniform primary judgment criteria alone is not appropriate, and to prevent aggressive driving. Judgment accuracy can be improved. Moreover, since the collection process of the collection unit 433 is not executed when the primary determination is not satisfied, the processing load on the reporting unit 43 can be reduced, and unnecessary communication and use of storage area can be suppressed. Furthermore, by using multiple notification methods, the degree of freedom in notification is high.

<Embodiment 4>
The fourth embodiment is a specific example of the second embodiment described above. Further, the fourth embodiment may be a modification of the third embodiment described above.

FIG. 9 is a block diagram showing the configuration of a driving support system 4000 according to the fourth embodiment. The driving support system 4000 includes in-vehicle devices 1b, 1c, . . . 1n and a server 2a, each of which is connected via a network N. In the following description, the same components as in each of the embodiments described above will be denoted by the same reference numerals, and the description will be omitted as appropriate. Note that the notification unit 15 may be provided outside the vehicle (for example, on the server 2a, etc.).

The in-vehicle device 1b is the in-vehicle device 1a of FIG. 3 in which the transmitter 16 is replaced with a transmitter 16b. The transmitter 16b transmits the collected detailed information to the server 2a as learning data for the determination model 25. In particular, when the determination result indicates that the candidate vehicle is driving aggressively, the transmitter 16b may transmit the collected detailed information to the server 2a as learning data for the determination model 25. Note that the in-vehicle devices 1c to 1n have the same configuration as the in-vehicle device 1b, and are installed in different vehicles.

The server 2a is obtained by adding a learning section 24 and a determination model 25 to the server 2 shown in FIG. The determination model 25 corresponds to the determination model 4301 in the third embodiment described above, and determines whether the candidate vehicle is performing aggressive driving based on detailed information. The learning unit 24 learns the determination model 25 using previously received detailed information as learning data. For example, the learning unit 24 performs machine learning using the learning data and updates the parameters of the determination model 25. Therefore, the determination unit 22 inputs the received detailed information to the learned determination model 25 and takes the output of the determination model 25 as the determination result.

FIG. 10 is a sequence diagram illustrating the flow of collection of learning data and learning processing for a judgment model and subsequent judgment processing according to the fourth embodiment. For example, assume that the in-vehicle device 1c has collected detailed information regarding the candidate vehicle in step S13. Then, the transmitter 16b of the in-vehicle device 1c transmits the collected detailed information to the server 2a via the network N (S41).

Further, it is assumed that the in-vehicle device 1n collects detailed information regarding the candidate vehicle in step S13, and then determines that the candidate vehicle is driving aggressively, and then notifies the candidate vehicle in step S15. Then, the transmitter 16b of the in-vehicle device 1n transmits the collected detailed information to the server 2a via the network N (S42).

After steps S41 and S42, the server 2a trains the determination model 25 using the detailed information received as learning data (S43). For example, the detailed information received in step S42 is given a label indicating that aggressive driving is being performed as a result of the secondary determination, and the detailed information in step S41 is given a different label for learning. Also good.

Thereafter, the in-vehicle device 1b performs steps S11 to S13 similarly to FIG. 4, and the transmitter 16b transmits the detailed information collected by the collector 13 to the server 2a via the network N (S21).

Subsequently, the receiving unit 21 of the server 2a receives detailed information from the transmitting unit 16b via the network N. Then, the determination unit 22 determines whether the candidate vehicle is performing aggressive driving based on the detailed information received from the in-vehicle device 1b (S22). At this time, the determination unit 22 uses the learned determination model 25. Thereafter, the notification unit 23 returns the determination result to the in-vehicle device 1b via the network N (S23). Thereby, the in-vehicle device 1b can obtain highly accurate determination results based on the learned determination model, and can perform appropriate notification (S15).
Note that, as described above, the notification unit 15 does not necessarily need to be provided in the in-vehicle devices 1a to 1n. In that case, for example, the notification unit 23 of the server 2a may execute steps equivalent to step S23 instead of step S23. Alternatively, in addition to the in-vehicle device 1a and the server 2, there may be a notification device that notifies the police or the like. In that case, the notification unit 23 of the server 2a may set the notification device as the transmission destination in step S23.

Note that since the server 2a can collect detailed information from the plurality of in-vehicle devices 1b to 1n, it can hold this information as historical information regarding aggressive driving. Further, the history information may be used as a blacklist for aggressive driving.

<Other embodiments>
In addition, although the above-mentioned embodiment was explained as a hardware configuration, it is not limited to this. The present disclosure can also realize arbitrary processing by causing the CPU to execute a computer program.

In the examples above, the program can be stored and delivered to a computer using various types of non-transitory computer readable media. Non-transitory computer-readable media includes various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, Includes CD-R/W, DVD (Digital Versatile Disc), and semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (Random Access Memory)). The program may also be supplied to the computer on various types of transitory computer readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can provide the program to the computer via wired communication channels, such as electrical wires and optical fibers, or wireless communication channels.

Note that the present disclosure is not limited to the above embodiments, and can be modified as appropriate without departing from the spirit. Further, the present disclosure may be implemented by appropriately combining the respective embodiments.

Part or all of the above embodiments may be described as in the following additional notes, but are not limited to the following.
(Appendix A1)
an acquisition unit that acquires surrounding images taken from the own vehicle while it is running;
a selection unit that selects candidate vehicles that may be driving aggressively toward the own vehicle from among other vehicles included in the surrounding image;
a collection unit that collects detailed information regarding the candidate vehicle;
a determination unit that obtains a determination result as to whether or not the candidate vehicle is driving aggressively based on the detailed information;
a notification unit that notifies outside of notification information including the detailed information when the determination result indicates that the candidate vehicle is driving aggressively;
A driving support device equipped with.
(Appendix A2)
The driving support device according to appendix A1, wherein the determination unit inputs the detailed information to the aggressive driving determination model learned based on the detailed information, and obtains an output of the determination model as the determination result.
(Appendix A3)
The driving support device includes:
further comprising a transmitter that transmits the detailed information to a server equipped with the determination model,
The determination unit includes:
The driving support device according to appendix A2, wherein the output when the detailed information is input to the determination model in the server is received from the server as the determination result.
(Appendix A4)
The transmitter includes:
The driving support device according to appendix A3, wherein the collected detailed information is transmitted to the server as learning data for the determination model.
(Appendix A5)
The transmitter includes:
If the determination result indicates that the candidate vehicle is driving aggressively, the collected detailed information is transmitted to the server as learning data for the determination model. Driving support according to appendix A4. Device.
(Appendix A6)
The collection unit includes:
From the plurality of surrounding images for a predetermined period, at least one of the number of times the inter-vehicle distance between the candidate vehicle and the own vehicle became less than a predetermined distance within a predetermined period, or the length of time that the inter-vehicle distance remained less than a predetermined distance. The driving support device according to any one of Supplementary Notes A1 to A5, wherein information on the measured amount is collected as the detailed information.
(Appendix A7)
The collection unit includes:
The driving support device according to any one of appendices A1 to A6, wherein an image taken by enlarging a specific area of the candidate vehicle among the surrounding images is collected as the detailed information.
(Appendix A8)
The collection unit includes:
The driving support device according to any one of Supplementary Notes A1 to A7, wherein at least one of light or sound detected from the vicinity of the own vehicle is collected as the detailed information.
(Appendix A9)
The selection department is
After the other vehicle cuts in front of the own vehicle, if the inter-vehicle distance between the other vehicle and the own vehicle becomes less than or equal to a predetermined distance, the other vehicle is selected as the candidate vehicle. The driving support device according to item 1.
(Appendix A10)
The selection department is
If the lateral inter-vehicle distance between the other vehicle and the host vehicle continues to be less than or equal to a predetermined distance for a certain period of time or more, the other vehicle is selected as the candidate vehicle. Driving assistance device as described.
(Appendix B1)
The computer is
Obtain surrounding images taken from the own vehicle while driving,
Selecting candidate vehicles that are likely to be driving aggressively toward the host vehicle from among other vehicles included in the surrounding image;
collecting detailed information about the candidate vehicle;
Obtaining a determination result as to whether the candidate vehicle is driving aggressively based on the detailed information;
When the determination result indicates that the candidate vehicle is driving aggressively, notification information including the detailed information is notified to the outside.
(Appendix C1)
Acquisition processing that acquires surrounding images taken from the own vehicle while driving;
Selection processing for selecting candidate vehicles that may be driving aggressively toward the host vehicle from among other vehicles included in the surrounding image;
a collection process of collecting detailed information regarding the candidate vehicle;
a determination process that obtains a determination result as to whether or not the candidate vehicle is driving aggressively based on the detailed information;
If the determination result indicates that the candidate vehicle is driving aggressively, a notification process that notifies an external party of notification information including the detailed information;
A driving assistance program that causes a computer to execute.
(Appendix D1)
an acquisition unit that acquires surrounding images taken from the own vehicle while it is running;
a selection unit that selects candidate vehicles that may be driving aggressively toward the own vehicle from among other vehicles included in the surrounding image;
a collection unit that collects detailed information regarding the candidate vehicle;
an in-vehicle device having;
a server connected to the in-vehicle device via a network;
Equipped with
The in-vehicle device transmits the collected detailed information to the server via the network,
The server is
Determining whether the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
A driving support system that notifies information based on the result of the determination to the outside via the network.
(Appendix D2)
The server is
comprising a determination model that determines whether the candidate vehicle is driving aggressively based on the detailed information,
learning the judgment model using the detailed information received in the past as learning data;
The driving support system according to appendix D1, wherein the received detailed information is input to the learned determination model, and the output of the determination model is used as the determination result.
(Appendix E1)
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an on-vehicle device. a receiving unit that receives from the in-vehicle device via a network;
a determination unit that determines whether the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
a notification section that notifies the outside via the network of information based on the determination result by the determination section;
A driving support device equipped with.
(Appendix E2)
a determination model that determines whether the candidate vehicle is driving aggressively based on the detailed information;
a learning unit that learns the determination model using detailed information received in the past as learning data;
Furthermore,
The driving support device according to appendix E1, wherein the determination unit inputs the received detailed information to the learned determination model, and sets the output of the determination model as the determination result.
(Appendix F1)
The computer is
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an in-vehicle device. is received from the in-vehicle device via the network,
Determining whether or not the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
A driving support method, wherein information based on the result of the determination is notified to the outside via the network.
(Appendix G1)
Detailed information collected on a candidate vehicle selected as a candidate vehicle that is likely to be driving aggressively toward the own vehicle from among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running using an in-vehicle device. from the in-vehicle device via a network;
A process of determining whether the candidate vehicle is driving aggressively based on detailed information received from the in-vehicle device;
a process of notifying information based on the result of the determination to the outside via the network;
A driving assistance program that causes a computer to execute.

Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above embodiments (and examples). The configuration and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention.

1 Driving support device 1a On-vehicle device 1b On-vehicle device 1c On-vehicle device 1n On-vehicle device 11 Acquisition unit 12 Selection unit 13 Collection unit 14 Judgment unit 15 Notification unit 16 Transmission unit 16b Transmission unit 17 Receiving unit 2 Server 2a Server 21 Receiving unit 22 Judgment unit 23 Notification unit 24 Learning unit 25 Judgment model 2000 Driving support system N Network 3000 Driving support system N1 Communication network 3 Notification destination 31 Communication device 32 Operator 4 Own vehicle 40 On-vehicle device group 41 Illuminance sensor 42 Microphone 43 Notification unit 430 Storage unit 4301 Judgment Model 4302 Map information 431 Acquisition unit 432 Primary determination unit 433 Collection unit 434 Secondary determination unit 435 Notification information generation unit 436 Mail function unit 437 Telephone function unit 44 Camera unit 441 Front and rear cameras 442 Camera ECU
443 HDD
45 GPS information receiver 46 Communication device 47 Speed measuring device 48 Manual report button 5 Other vehicle 401 Storage device 4011 Judgment model 40111 Parameter 4012 Driving support program 402 Control unit 403 Memory 404 IF unit 4000 Driving support system

Claims (4)

Driving behavior collected by an on-vehicle device regarding candidate vehicles selected as being likely to be driving aggressively toward the own vehicle among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running. a receiving unit that receives detailed information including a face image of a person from the in-vehicle device via a network;
Determining whether or not the candidate vehicle is driving aggressively based on the detailed information received from the in-vehicle device and a face image of another driver who is driving aggressively, collected from another in-vehicle device. A determination section;
a notification unit that notifies the outside via the network of information based on the determination result by the determination unit;
A driving support device equipped with. a determination model that determines whether the candidate vehicle is driving aggressively based on the detailed information;
a learning unit that learns the determination model using detailed information received in the past as learning data;
Furthermore,
The driving support device according to claim 1, wherein the determination unit inputs the received detailed information to the learned determination model and uses an output of the determination model as the determination result. The computer is
Driving behavior collected by an on-vehicle device regarding candidate vehicles selected as being likely to be driving aggressively toward the own vehicle among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running. receiving detailed information including a face image of the person from the in-vehicle device via a network;
Determining whether or not the candidate vehicle is driving aggressively based on the detailed information received from the in-vehicle device and a face image of another driver who has engaged in aggressive driving collected from another in-vehicle device. ,
A driving support method, wherein information based on the result of the determination is notified to the outside via the network. Driving behavior collected by an on-vehicle device regarding candidate vehicles selected as being likely to be driving aggressively toward the own vehicle among other vehicles included in surrounding images taken from the own vehicle while the vehicle is running. a process of receiving detailed information including a facial image of a person from the in-vehicle device via a network;
Determining whether or not the candidate vehicle is driving aggressively based on the detailed information received from the in-vehicle device and a face image of another driver who is driving aggressively, collected from another in-vehicle device. processing and
a process of notifying information based on the result of the determination to the outside via the network;
A driving assistance program that causes a computer to execute.

Images