WO2023210753A1

WO2023210753A1 - Driving assistance device and driving assistance method

Info

Publication number: WO2023210753A1
Application number: PCT/JP2023/016675
Authority: WO
Inventors: 修一青山
Original assignee: 株式会社Ｊｖｃケンウッド
Priority date: 2022-04-28
Filing date: 2023-04-27
Publication date: 2023-11-02

Abstract

A driving assistance device 10 comprises: a current position acquiring unit 11 that acquires a current position of a vehicle; a traffic-regulating object information acquiring unit 12 that acquires traffic-regulating object information related to a traffic-regulating object that is present in a travel direction of the vehicle; an image acquiring unit 13 that acquires an image taken of the surroundings of the vehicle, including at least the travel direction of the vehicle; an image recognition unit 14 that recognizes an object to be recognized captured in the image; a determination unit 15 that determines that the traffic-regulating object is present and that the object to be recognized, which is the traffic-regulating object, is not being recognized; and a notification control unit 16 that controls notification based on a result of the determination.

Description

Driving support device and driving support method

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

There is a known technology that detects deceleration objects such as traffic lights using images or radar and notifies vehicle occupants. (For example, Patent Document 1)

JP 2021-133777 Publication

The driving support device described in Patent Document 1 detects objects to be decelerated, such as traffic lights, and notifies the occupants of the vehicle. However, there are cases where the traffic light is in a blind spot due to a preceding vehicle or the like and cannot be detected by a camera or radar mounted on the vehicle. Furthermore, if the vehicle occupant can see the traffic light, unnecessary information will be output, which may be a nuisance to the vehicle occupant.

The present disclosure has been made in view of the above, and there are situations in which it is difficult for vehicle drivers to see traffic control objects that restrict vehicle travel, such as traffic lights, stop signs, railroad crossings, and crosswalks. The object of the present invention is to provide a driving support device and a driving support method that can appropriately notify a driver of the presence of a traffic regulating object when the traffic control object occurs.

In order to achieve the above object, a driving support device according to the present disclosure includes a current position acquisition unit that acquires the current position of a vehicle, and a traffic restriction that acquires traffic restriction object information regarding a traffic restriction object that exists in the direction of travel of the vehicle. an object information acquisition unit; an image acquisition unit that acquires an image of the surroundings of the vehicle including at least the traveling direction of the vehicle; an image recognition unit that recognizes a recognition target object photographed in the image; The vehicle is characterized by comprising: a determination unit that determines that the recognition target object that is present and is the traffic regulation object is not recognized; and a notification control unit that controls notification based on the result of the determination. shall be.

In order to achieve the above object, a driving support method according to the present disclosure includes a step in which a computer acquires the current position of a vehicle, and a step in which a computer acquires traffic restriction object information regarding a traffic restriction object existing in the traveling direction of the vehicle. , a step of acquiring an image of the surroundings of the vehicle including at least the traveling direction of the vehicle, a step of recognizing a recognition target object photographed in the image, and a step in which the traffic restriction object exists and the traffic restriction object The present invention is characterized by executing the steps of determining that the recognition target object is not recognized, and controlling notification based on the result of the determination.

According to the present disclosure, it is possible to provide a driving support device and a driving support method that can appropriately notify a driver of the existence of a traffic restriction object when the traffic restriction object is difficult to visually recognize.

FIG. 1 is a block diagram showing an example of the configuration of a driving support device according to a first embodiment. FIG. 2 is a flowchart illustrating an example of a processing procedure of the driving support device according to the first embodiment. FIG. 3 is a block diagram showing an example of the configuration of the driving support device according to the second embodiment. FIG. 4 is a block diagram showing an example of the configuration of a driving support device according to the third embodiment.

Hereinafter, the present invention will be explained through embodiments of the invention, but the claimed invention is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are essential as means for solving the problem. For clarity of explanation, the following description and drawings are omitted and simplified as appropriate.

<Embodiment 1>
Embodiment 1 of the present disclosure will be described using FIG. 1. FIG. 1 is a block diagram showing an example of the configuration of a driving support system 1 according to the first embodiment.

The driving support system 1 includes a driving support device 10, a GNSS (Global Navigation Satellite System) receiver 20, a map database 30, a camera 40, a monitor 50, and a speaker 60.

The GNSS receiver 20 receives a GNSS signal from a GNSS satellite (not shown). The GNSS receiver 20 outputs the received radio signal to the driving support device 10. Alternatively, the GNSS receiver 20 measures the current position using the received radio wave signal, and outputs information on the measured current position to the driving support device 10. The GNSS receiver 20 is a device that is implemented as a function of a mobile device owned by a vehicle occupant such as a driver or a passenger, and outputs received radio wave signals or measured current position information to the driving support device 10. There may be.

The map database 30 stores various types of map information. The map information includes location information of traffic control objects such as traffic lights, stop signs, railroad crossings, and crosswalks that require vehicles to stop or slow down and that restrict the movement of vehicles.

The camera 40 is mounted on the vehicle and photographs a range including the direction of travel of the vehicle. The camera 40 may be a single camera or may be configured as a group of multiple cameras. Further, the camera 40 may be a portable device held by a vehicle occupant such as a driver.

The monitor 50 is an image display device mounted on the vehicle. The monitor 50 is a display device specific to the driving support system 1 or a display device shared with other systems. The monitor 50 may be a display unit mounted on a portable device owned by a vehicle occupant such as a driver.

The speaker 60 is an audio output device mounted on the vehicle. The speaker 60 is an audio output device specific to the driving support system 1 or an audio output device shared with other systems. The speaker 60 may be a speaker mounted on a portable device owned by a vehicle occupant such as a driver.

The driving support device 10 includes a current position acquisition section 11, a traffic restriction information acquisition section 12, an image acquisition section 13, an image recognition section 14, a determination section 15, and a notification control section 16.

The current position acquisition unit 11 uses the radio wave signal received by the GNSS receiver 20 to measure and acquire the current position of the vehicle. Alternatively, the current position acquisition unit 11 acquires current position information of the vehicle that has been positioned by the GNSS receiver 20. The current position acquisition unit 11 may be configured to include a GNSS receiver 20. The current position acquisition unit 11 outputs the acquired current position of the vehicle to the traffic regulation object information acquisition unit 12.

Based on the current position acquired by the current position acquisition unit 11, the traffic regulation object information acquisition unit 12 refers to the map database 30 to identify traffic lights, stop signs, railroad crossings, and crosswalks that exist in the direction of travel of the vehicle. Obtains traffic regulation object information regarding traffic regulation objects that require vehicles to stop or decelerate, such as traffic regulation objects that restrict the movement of vehicles. The traffic regulation object information acquisition unit 12 also obtains traffic regulation object type information indicating which type of the acquired traffic regulation object is, such as a traffic light, a stop sign, a railroad crossing, or a crosswalk, and the current state of the vehicle. It is preferable to also acquire information regarding the distance from the location to the traffic control object.

The traffic regulation object information acquisition unit 12 obtains traffic regulation object information regarding traffic regulation objects that exist within a predetermined range that is visible to the driver, such as within 100 m of the vehicle's direction of travel. get.

The traffic restriction object information acquisition unit 12 outputs the acquired information regarding the traffic restriction object to the determination unit 15.

The image acquisition unit 13 acquires an image of the surroundings of the vehicle including at least the traveling direction of the vehicle from the camera 40. The image acquisition unit 13 may acquire a plurality of images from a plurality of camera groups 40. The image acquisition section 13 may include the camera 40, or may be an input interface section that is connected to the separate camera 40 and acquires an output signal output from the camera 40. The image acquisition unit 13 outputs the acquired image to the image recognition unit 14.

The image recognition unit 14 performs image recognition processing of a predetermined recognition target object photographed in the image acquired by the image acquisition unit 13. In the present embodiment, the image recognition unit 14 recognizes traffic control objects such as traffic lights, stop signs, railroad crossings, and crosswalks that require the vehicle to stop or slow down and that restrict the movement of the vehicle. , performs the recognition process. The image recognition unit 14 outputs the recognition result to the determination unit 15.

The image recognition unit 14 includes a trained model for traffic regulation object recognition as a trained model for image recognition. The image recognition unit 14 recognizes a traffic restriction object that restricts vehicle travel from the image acquired by the image acquisition unit 13 using an image recognition technique that uses a trained model for recognizing a traffic restriction object.

A trained model for image recognition is a learning model in which input data, which is a set of images and training data, is input to a neural network and subjected to machine learning. In this embodiment, for example, an image of a landscape taken by a camera mounted on a vehicle, or an image of a traffic light, a sign, a railroad crossing, a crosswalk, etc. is used as the image. In addition, as teacher data, teacher data is used which is set to 1 when a traffic regulating object is photographed in the image, and is set to 0 when a traffic regulating object is not photographed in the image.

For example, the neural network included in the image recognition unit 14 inputs the image acquired by the image acquisition unit 13 to a trained model for recognizing traffic restriction objects, and calculates the possibility that a traffic restriction object is photographed in the input image. , output as a value between 1 and 0. The closer the output value is to 1, the higher the possibility that a traffic restriction object is photographed in the input image, and the closer the output value is to 0, the higher the possibility that a traffic restriction object is photographed in the input image. low. If this output value is a predetermined threshold value, for example, 0.8 or more, the image recognition unit 14 adds a recognition result that a traffic regulation object is photographed to the image acquired by the image acquisition unit 13. , is output to the determination unit 15.

In addition to the above-mentioned configuration, the image recognition unit 14 may recognize the recognition target using a known technique such as pattern matching.

The determination unit 15 determines that the traffic regulation object information acquisition unit 12 has acquired the information that a traffic regulation object exists in the direction of travel of the vehicle, and the image recognition unit 14 has recognized the traffic regulation object that is the recognition target object. Determine that there is no such thing. In other words, even though there is a traffic restriction object in the direction of travel of the vehicle, the image recognition result does not recognize the traffic restriction object, indicating that there is a high possibility that the driver will not be able to recognize the traffic restriction object. In this case, it is determined that the driver should be notified. The determination unit 15 outputs the determined result to the notification control unit 16.

When the determination unit 15 determines to notify the driver, the notification control unit 16 controls the notification to the driver by display or audio. For example, informing the driver that there is a traffic control object in the direction of travel of the vehicle, such as "There is a traffic light ahead" or "There is a railroad crossing 50 meters ahead", is given via the monitor 50 or speaker 60. This is to notify the driver by display or audio presentation.

The notification control unit 16 controls at least one of outputting predetermined image data and text data to the monitor 50, and outputting predetermined warning sounds and audio data to the speaker 60.

The notification control unit 16 is not limited to notifying the driver using the monitor 50 or the speaker 60. The notification control unit 16 may notify the driver through, for example, a buzzer, an LED (light emitting diode), or a vibration device (not shown) in addition to the monitor 50 or the speaker 60.

Next, the processing procedure of the driving support device 10 according to the first embodiment described above will be explained with reference to the flowchart shown in FIG. 2. FIG. 2 is a flowchart illustrating an example of a processing procedure of the driving support device according to the first embodiment.

First, in step S10, the current position acquisition unit 11 acquires the current position of the vehicle based on the radio wave signal received by the GNSS receiver 20. The current position acquisition unit 11 outputs the acquired current position information to the traffic regulation object information acquisition unit 12. After that, the process advances to step S11.

In step S11, the traffic restriction object information acquisition unit 12 refers to the map information database 30 based on the acquired current position and acquires information on traffic restriction objects existing within a predetermined range in the direction of travel of the vehicle. The traffic regulation object information acquisition section 12 outputs the acquired traffic regulation object information to the determination section 15 when the traffic regulation object exists within a predetermined range in the traveling direction of the vehicle. After that, the process advances to step S12.

In step S12, the image acquisition unit 13 acquires an image taken by the camera 40. The image acquisition unit 13 outputs the acquired image to the image recognition unit 14. After that, the process advances to step S13.

In step S13, the image recognition unit 14 performs image recognition processing on the acquired image and recognizes the traffic regulation object that is the recognition target. The image recognition unit 14 outputs the recognition result, in other words, the result of whether or not the traffic restriction object has been recognized, to the determination unit 15. After that, the process advances to step S14.

In step S14, the determination unit 15 determines that the traffic restriction object information acquisition unit 12 has acquired information that the traffic restriction object exists within a predetermined range in the traveling direction of the vehicle, and that the image recognition unit 14 performs image recognition. If the result indicates that there is a high possibility that the driver will not be able to recognize the traffic control object, it is determined that the driver should be notified. When the determination unit 15 determines to notify the driver (Yes in S14), the process proceeds to step S15. If the determination unit 15 does not determine that the driver should be notified (No in S14), the process returns to step S10 and the process is executed again.

In step S15, the notification control unit 16 controls notification to the driver by display or audio. The notification control unit 16 outputs notification to the driver as image data or text data to the monitor 50, or outputs it as audio data to the speaker 60. Then end the flow.

As described above, according to the first embodiment, the driving support device 10 installs traffic control objects such as traffic lights, stop signs, railroad crossings, and crosswalks that restrict the movement of vehicles within a predetermined range in the direction of travel of the vehicle. , and the relevant traffic restriction object is not recognized in the image taken by the camera mounted on the vehicle, it is determined that there is a high possibility that the driver is unable to see the traffic restriction object, and the relevant traffic restriction object is not recognized in the image taken by the camera mounted on the vehicle. Information regarding regulated objects can be notified to the driver. By adopting such a configuration, while suppressing the notification when there is a high possibility that the driver can see the object, when there is a low possibility that the driver cannot see the traffic regulating object, it is It is possible to appropriately notify the presence of the vehicle, thereby increasing the safety of vehicle driving.

Here are some examples of factors that make it difficult for drivers to see traffic control objects. For example, if an obstacle obstructs the view, it becomes difficult to see. For example, if it is difficult to obtain a clear image due to bad weather such as nighttime or fog, and the accuracy of image recognition is low, in other words, visibility to the driver is low, it becomes difficult to visually recognize the image. For example, when the driver is stopped close to a traffic light, the angle of view of the camera and the driver's field of view may vary depending on the positional relationship with the traffic control object, such as when the traffic light is located at a high position out of the driver's field of view. If it is difficult to see, it becomes difficult to see. According to the first embodiment, it is possible to notify the driver of information regarding the traffic regulating object in a state where it becomes difficult for the driver to visually recognize the traffic regulating object.

<Embodiment 2>
Embodiment 2 of the present disclosure will be described using FIG. 3. FIG. 3 is a block diagram showing an example of the configuration of the driving support system 1 according to the second embodiment. The driving support device 10a according to the second embodiment has a different configuration from the driving support device 10 according to the first embodiment in the following points.

The image recognition unit 14a has a function of recognizing obstacles existing in front of the vehicle using images.

The determination unit 15a determines whether the size of the obstacle recognized by the image recognition unit 14a on the image is equal to or larger than a predetermined value, and determines whether the traffic regulating object is within a predetermined range in the direction of travel of the vehicle. It has a function of determining that the driver should be notified if an obstacle exists and the size of the obstacle on the image is equal to or larger than a predetermined value.

In the driving support device 10a, the current position acquisition unit 11, the traffic regulation object information acquisition unit 12, the image acquisition unit 13, and the notification control unit 16 have the same configuration and function as the driving support device 10 according to the first embodiment. A detailed explanation thereof will be omitted.

The image recognition unit 14a performs image recognition processing of a predetermined recognition target object photographed in the image acquired by the image acquisition unit 13. In this embodiment, the image recognition unit 14a recognizes an obstacle as a recognition target object. The image recognition section 14a outputs the recognition result to the determination section 15a.

The obstacles may be, for example, a vehicle traveling in front of the vehicle, a vehicle parked on the road, a vehicle traveling in the opposite lane, a signboard, a tree such as a garden tree or a street tree, a telephone pole, or the like.

In the present embodiment, the image recognition unit 14a performs machine learning on the following trained models for image recognition, such as vehicles traveling ahead, vehicles parked on the road, vehicles traveling in the opposite lane, signboards, garden trees, and street trees. A trained model for recognizing obstacles such as trees and telephone poles is used. In other words, if the image is an image of a landscape taken by a camera mounted on a vehicle or an image of various obstacles, and if an obstacle is photographed in the image as training data, 1. Data is used that is set to 0 if no obstacle is photographed in the image.

For example, the image recognition unit 14a inputs an image to a trained model for obstacle recognition, and outputs the probability that an obstacle is photographed in the input image as a value between 1 and 0. The closer the output value is to 1, the higher the possibility that an obstacle is photographed in the input image, and the closer the output value is to 0, the lower the possibility that an obstacle is photographed in the input image. If this output value is a predetermined threshold value, for example, 0.8 or more, the image recognition unit 13 determines that an obstacle is photographed in the image acquired by the image acquisition unit 12.

In addition to the above-mentioned configuration, the image recognition unit 14a may recognize the recognition target using a known technique such as pattern matching.

The determination unit 15a measures the size of the obstacle recognized by the image recognition unit 14a on the image. For example, the determination unit 15a determines the size of the obstacle recognized by the image recognition unit 14a on the image by pixels indicating at least one of the length and width of the image of the obstacle recognized on the image. It is measured as the number of pixels or the area of the area of the image of the obstacle that is recognized on the image.

The determination unit 15a determines that the traffic restriction object information acquisition unit 12 has acquired the information that a traffic restriction object exists in the direction of travel of the vehicle, and that the obstacle, which is the recognition target object recognized by the image recognition unit 14a, is included in the image. It is determined that the occupied recognition area is larger than a predetermined value. The recognition area occupied by the obstacle in the image is larger than a predetermined value, which means that the number of pixels in the vertical length of the recognition area where the obstacle is recognized is larger than the predetermined value, for example, the entire image. This is a case where the number of pixels is 1/2 or more of the number of pixels in the vertical length of . If the image recognition result indicates that the obstacle running in front of the vehicle occupies a predetermined area or more of the image and there is a high possibility that the driver will not be able to recognize the traffic regulating object, the determination unit 15a determines that It is determined that the driver is to be notified. The determination unit 15a outputs the determined result to the notification control unit 16.

When the size of the obstacle on the image is equal to or larger than a predetermined value, the determination unit 15a determines the number of pixels in the horizontal direction where the obstacle is recognized and the area of the area where the obstacle is recognized. The determination may be made based on the number of pixels showing . Further, it is preferable that these predetermined values can be changed according to the user's designation or the driving environment.

The determination unit 15a may set a predetermined value for each type of traffic regulation information acquired by the traffic regulation object information acquisition unit 12. This is because the size on the image differs depending on the type of traffic regulation information. For example, for each type of traffic regulation information, a threshold value for the number of pixels in the horizontal length of the recognized obstacle or the number of pixels indicating the area is determined in advance as a predetermined value. The determination unit 15a determines, for each type of traffic regulation information, whether the number of pixels representing the horizontal length or the number of pixels representing the area of the obstacle recognized by the image recognition unit 14a is greater than or equal to a predetermined value. judge. Specifically, the determination unit 15a determines that the traffic regulation object information acquisition unit 12 has acquired the information that a stop sign exists in the direction of travel of the vehicle, and the number of pixels in the horizontal direction in which the obstacle has been recognized. , or when the number of pixels indicating the area is greater than or equal to a predetermined value corresponding to a stop sign, the determination unit 15a sends an output to the notification control unit 16 indicating that there is a high possibility that the driver will not be able to recognize the traffic regulation object. Output to. Similarly, predetermined values may be determined for traffic lights, railroad crossings, pedestrian crossings, and the like.

As described above, according to the second embodiment, the driving support device 10a includes traffic control objects such as traffic lights, stop signs, railroad crossings, and crosswalks that restrict the movement of vehicles within a predetermined range in the direction of travel of the vehicle. , and an obstacle larger than a predetermined value is recognized in the image taken by the camera mounted on the vehicle, the driver's field of vision is narrowed by the obstacle, and the driver It is possible to determine that there is a high possibility that the traffic regulating object is not visible, and to notify the driver of information regarding the traffic regulating object. By adopting such a configuration, while suppressing the notification when there is a high possibility that the driver can see the object, when there is a low possibility that the driver cannot see the traffic regulating object, it is It is possible to appropriately notify the presence of the vehicle, thereby increasing the safety of vehicle driving.

According to the second embodiment, the predetermined value is determined based on the type of traffic regulating object. Through this, information is obtained that a predetermined traffic restriction object exists in the direction of travel of the vehicle, and the image taken by the camera has a size larger than a predetermined value determined corresponding to the type of traffic restriction object. When an obstacle is recognized, it can be determined that the driver's field of view is narrowed by the obstacle and there is a high possibility that the driver cannot see the traffic regulating object. Embodiment 2 allows more appropriate determination.

<Embodiment 3>
Embodiment 3 of the present disclosure will be described using FIG. 4. FIG. 4 is a block diagram showing an example of the configuration of the driving support system 1 according to the third embodiment. The driving support device 10b according to the third embodiment has a different configuration from the driving support device 10a according to the second embodiment in the following points.

The determining unit 15b determines whether the traffic regulating object exists within a predetermined range in the traveling direction of the vehicle, and whether the position of the recognition target object recognized by the image recognition unit 14a on the image includes a predetermined area. If the traffic regulating object exists within a predetermined range in the direction of travel of the vehicle and the position occupied by the recognition target object on the image includes a predetermined region, the driver is notified. It has a function to determine if it is done.

In the driving support device 10b, the current position acquisition unit 11, traffic regulation object information acquisition unit 12, image acquisition unit 13, image recognition unit 14a, and notification control unit 16 have the same configuration as the driving support device 10a according to the second embodiment. Since it has a function, its detailed explanation will be omitted.

The determination unit 15b determines the position on the image where the obstacle, which is the recognition target recognized by the image recognition unit 14a, is recognized, and determines whether each pixel or each small area including a plurality of pixels constituting the image is included in the recognition area. In other words, each pixel or each small area is determined as information on whether or not an obstacle is recognized.

The determining unit 15b determines that a traffic regulating object exists and that the position occupied by the recognition target object on the image includes a predetermined area. The position of the recognition target object on the image includes a predetermined area defined in advance, which means that the position of a pixel or small area in the image area where there is a high possibility that a traffic control object exists, and the determined obstacle. This means that the area where the object is recognized coincides with the area where the object is recognized. The determination unit 15b determines that the image recognition result indicates that the driver cannot recognize the traffic restriction object when a traffic restriction object exists and the position occupied by the recognition target object on the image includes a predetermined area. It is determined that the driver is to be notified as this indicates that there is a high possibility. The determination unit 15b outputs the determined result to the notification control unit 16.

The determination unit 15b may set a predetermined area as a predetermined area for each type of traffic regulation information acquired by the traffic regulation object information acquisition unit 12. This is because the position occupied on the image differs depending on the type of traffic regulation information. For example, a specific area on the upper left side of the image is predetermined as a predetermined area where a stop sign is likely to be image recognized. A specific area on the upper left side of the image is a predetermined area corresponding to a stop sign. The determination unit 15b determines whether the recognized position of the obstacle recognized by the image recognition unit 14a matches a specific area on the upper left side of the image. The determination unit 15b determines that when the traffic regulation object information acquisition unit 12 has acquired information that a stop sign exists in the direction of travel of the vehicle and an obstacle is recognized in a specific area on the upper left side of the image, The determination unit 15b outputs to the notification control unit 16 an output indicating that there is a high possibility that the driver will not be able to recognize the traffic regulating object. Similarly, traffic lights, railroad crossings, pedestrian crossings, etc. may be defined as corresponding predetermined areas.

As described above, according to the third embodiment, the driving support device 10b installs traffic control objects such as traffic lights, stop signs, railroad crossings, and crosswalks that restrict the movement of vehicles within a predetermined range in the direction of travel of the vehicle. and an obstacle is recognized at a specific position on the image taken by the camera mounted on the vehicle, the area on the image where there is a high possibility that a traffic restriction object exists is blocked by the obstacle. It is possible to determine that there is a high possibility that the driver cannot see the traffic regulating object, and to notify the driver of information regarding the traffic regulating object. By adopting such a configuration, while suppressing the notification when there is a high possibility that the driver can see the object, when there is a low possibility that the driver cannot see the traffic regulating object, it is It is possible to appropriately notify the presence of the vehicle, thereby increasing the safety of vehicle driving.

According to the third embodiment, the predetermined area is determined based on the type of traffic regulating object. This obtains information on the presence of a predetermined traffic regulation object in the direction of travel of the vehicle, and if the obstacle is recognized in a specific area corresponding to the predetermined traffic regulation object, the driver's field of vision becomes obstructed. It can be determined that there is a high possibility that the driver cannot see the traffic restriction object because the road is narrowed by an object. Embodiment 3 allows more appropriate determination.

<Other embodiments>
The specific examples shown in Embodiments 1 to 3 described above in the present disclosure are merely illustrative to facilitate understanding of the invention, and do not limit the invention unless otherwise specified.

Note that the present disclosure is not limited to Embodiments 1 to 3, and can be modified as appropriate without departing from the spirit.

The driving support device 10a of the second embodiment may include an embodiment of the driving support device 10 of the first embodiment. That is, the image recognition unit 14a in the driving support device 10a simultaneously recognizes the traffic restriction object and the obstacle, and the determination unit 15a in the driving support device 10a determines that the traffic restriction object cannot be recognized and the obstacle occupies the image. It may be determined that the recognition area is equal to or larger than a predetermined value, and outputs to the notification control unit 16 an output indicating that there is a high possibility that the driver will not be able to recognize the traffic regulating object.

Similarly, the driving support device 10b of the third embodiment may include an embodiment of the driving support device 10 of the first embodiment or the driving support device 10a of the second embodiment. That is, the determination unit 15b in the driving support device 10b of the third embodiment determines that the traffic regulating object cannot be recognized and the position on the image includes a predetermined area, or that the obstacle occupies the image. Determines that the recognition area is greater than or equal to a predetermined value and that the position on the image includes the predetermined area, indicating that there is a high possibility that the driver will not be able to recognize the traffic regulation object. The output may be output to the notification control section 16.

The driving support devices of Embodiments 1 to 3 may include at least one of a recording control section (not shown) and a communication control section (not shown). At this time, the traffic restriction object information acquisition unit 12 has acquired the information that there is a traffic restriction object in the direction of travel of the vehicle, and the

image recognition units

14 and 14a have recognized the recognition target object. When it is indicated that there is a high possibility that the traffic regulating object cannot be recognized, the recording control section controls recording the image acquired by the image acquisition section 13 in a recording section (not shown). Alternatively, the traffic restriction object information acquisition unit 12 has acquired information on the presence of a traffic restriction object in the direction of travel of the vehicle, and the

image recognition units

14 and 14a have recognized the recognition object, and the result is that the driver When it is determined that there is a high possibility that the restricted object cannot be recognized, the communication control unit controls the transmission of the image acquired by the image acquisition unit 13 to an external server (not shown) or a mobile terminal owned by the driver. A recording control section (not shown) and a communication control section (not shown) may perform recording control and communication control based on the determination results of the

determination sections

15, 15a, and 15b, respectively.

Furthermore, either the recording control section (not shown) or the communication control section (not shown) may be provided in place of the notification control section of the driving support device of the first to third embodiments. At this time, the driving support device is configured to perform only recording control or communication control without notifying the driver.

In the embodiments described above, the present disclosure has been described as a hardware configuration, but the present disclosure is not limited to this. The present disclosure can also implement arbitrary processing by causing a processor to execute a computer program.

In the examples described above, the program may be stored and provided to the computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media, including, for example, magnetic recording media such as hard disk drives, optical recording media, magneto-optical recording media, and semiconductor memory. Semiconductor memory can be various types of rewritable ROM (Read Only Memory) and RAM (Random Access Memory), and also includes those provided as SSD (Solid State Drive). The program may also be delivered to the computer via various types of temporary computer-readable media, such as electrical signals, optical signals, , and electromagnetic waves.

The execution order of each process in the apparatus and method shown in the claims, specification, and drawings can be realized in any order. Even if the claims, specification, and operational flows in the drawings are explained using "first", "next", etc. for convenience, this does not mean that it is essential to perform them in this order. do not have.

The driving support device and driving support method of the present disclosure can be used, for example, in a drive recorder.

1 Driving support system 10 Driving support device 11 Current position acquisition unit 12 Traffic control object information acquisition unit 13

Image acquisition unit

14, 14a

Image recognition unit

15, 15a, 15b Judgment unit 16 Notification control unit 20 GNSS receiver 30 Map database 40 Camera 50 Monitor 60 Speaker

Claims

a current position acquisition unit that acquires the current position of the vehicle;
a traffic regulation object information acquisition unit that obtains traffic regulation object information regarding traffic regulation objects existing in the direction of travel of the vehicle;
an image acquisition unit that acquires an image of the surroundings of the vehicle including at least the traveling direction of the vehicle;
an image recognition unit that recognizes a recognition target captured in the image;
a determination unit that determines that the traffic restriction object exists and the recognition target object that is the traffic restriction object is not recognized;
a notification control unit that controls notification based on the result of the determination;
A driving support device equipped with.
The recognition target includes an obstacle existing in the direction of travel of the vehicle,
The determining unit determines that when the traffic regulating object exists and the obstacle is recognized, an area in the image where the obstacle is recognized is larger than a predetermined value. further determine ,
The driving support device according to claim 1.
The recognition target includes an obstacle existing in the direction of travel of the vehicle,
The determining unit is configured to determine, when the traffic regulating object exists and the obstacle is recognized, the position of the area occupied by the obstacle in the image includes a predetermined area. further determine that
The driving support device according to claim 1.
The traffic regulation object information includes traffic regulation object type information regarding the type of the traffic regulation object,
The driving support device according to claim 2, wherein the predetermined value is determined based on the type of the traffic regulating object.
The traffic regulation object information includes traffic regulation object type information regarding the type of the traffic regulation object,
The driving support device according to claim 3, wherein the predetermined area is determined based on the type of the traffic regulating object.
further comprising at least one of a recording control unit that controls recording of the image acquired by the image acquisition unit, and a communication control unit that controls transmission of the image acquired by the image acquisition unit to the outside;
The driving support device according to any one of claims 1 to 3.
The computer is
obtaining the current location of the vehicle;
acquiring traffic regulation object information regarding traffic regulation objects existing in the direction of travel of the vehicle;
acquiring an image of the surroundings of the vehicle including at least the traveling direction of the vehicle;
a step of recognizing a recognition target captured in the image;
determining that the traffic restriction object exists and the recognition target object that is the traffic restriction object is not recognized;
a step of controlling notification based on the result of the determination;
A driving assistance method that performs.