Driver assistance devices, driver assistance methods, drive recorders, driver assistance control programs

Abstract

To analyze driving operation information and information derived by monitoring the surrounds of vehicle traveling in driving a vehicle and thereby provide advice that corresponds to the driving operation of each individual driver.SOLUTION: In a state recognition unit 36, each of information pieces about the traveling point of a vehicle 10 and the behavior of the vehicle 10 are sent to a risk event assessment unit 40 (transmission of essential information). In the state recognition unit 36, each of information pieces regarding the ambient environment of the vehicle 10 and the driving posture of a driver 24 are sent to the risk event assessment unit 40 (transmission of discretionary information) on the basis of a request from a risk event processing control unit 38. In the risk event assessment unit 40, the presence of risk during driving of the vehicle 10 is assessed. Advice is notified to the driver 24 on the basis of risk.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a driving support device, a driving support method, a drive recorder, and a driving support control program that provide advice to a driver regarding driving operations.

Background Art

[0002] In recent years, when driving a vehicle by a driver's operation, using acceleration and speed information, when there are actions such as sudden acceleration and deceleration caused by sudden acceleration and sudden braking, and driving operations that are problematic for predetermined safe driving operations such as exceeding the legal speed, etc., it has been put into practical use to send advice to correct the actions such as problematic driving operations to the driver.

[0003] In the above advice, it is not possible to identify a driver's difficult driving scenes (for example, when turning left, it is easy to be late in noticing pedestrians and perform a sudden braking operation, etc.) and characteristic driving operations of individual drivers, and there may be cases where appropriate and specific corrective advice cannot be provided for difficult driving scenes as described above.

[0004] Here, Patent Document 1 describes a vehicle safe driving promotion system that can improve a driver's safe driving awareness by giving a mental incentive to the driver.

[0005] More specifically, the in-vehicle device of Patent Document 1 determines a driver's driving situation from a safe driving threshold value and an economic driving threshold value stored in a storage means, driving state information acquired by a driving state acquisition means, safe driving evaluation history information, and economic driving evaluation history information, and when the driver's driving situation is within the determination threshold value stored in the storage means, a message praising the driver is notified to the driver via the notification means, and when the driver's driving situation is outside the determination threshold value, advice is given to the driver via the notification means.

[0006] This praise (message) can provide moral encouragement to drivers, which in turn can lead to improved awareness of safe driving practices and a reduction in traffic accidents. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2013-191230 [Overview of the project] [Problems that the invention aims to solve]

[0008] However, the advice provided is merely general, and does not take into account the individual driving style of each driver, such as how to drive in different situations.

[0009] The present invention aims to provide a driver assistance device, a driver assistance method, a drive recorder, and a driver assistance control program that can provide advice tailored to the individual driver's driving operations by analyzing driving operation information and information monitored around the vehicle during vehicle operation. [Means for solving the problem]

[0010] The driver assistance device according to the present invention includes: a situation recognition unit that acquires vehicle location information, vehicle behavior information, and image information of the vehicle's surroundings and interior as information sources and recognizes the vehicle's status based on the information sources; a determination unit that analyzes the recognition results from the situation recognition unit and determines whether or not there are any risk events that may occur while the vehicle is in motion; and a notification unit that, if the determination unit determines that there are risk events, notifies at least the driver operating the vehicle of advice on how to resolve the risk events.

[0011] The driving assistance method according to the present invention is characterized by acquiring vehicle location information, vehicle behavior information, and image information of the vehicle's surroundings and interior as information sources, recognizing the vehicle's status based on the information sources, analyzing the recognition results to determine whether or not there are any risk events that may occur while the vehicle is in motion, and, if it is determined that there are risk events, notifying at least the driver operating the vehicle of advice on how to resolve the risk events.

[0012] The drive recorder according to the present invention is mounted on a vehicle and includes a main control unit that captures the surrounding environment, including at least the area in front of the vehicle, records the captured images by overwriting the oldest images in order within a predetermined capacity, and saves images for a predetermined period before and after an emergency when an emergency is detected, and the above-mentioned driving support device.

[0013] The driver assistance control program according to the present invention is characterized in that it operates the computer as one of the components of the driver assistance device described above. [Effects of the Invention]

[0014] According to the present invention, in the operation of a vehicle, advice tailored to the driving operations of individual drivers can be provided by analyzing driving operation information and information monitored around the vehicle. [Brief explanation of the drawing]

[0015] [Figure 1] This is a schematic diagram of a driver assistance system that supports driving in the autonomous driving of a vehicle according to the first embodiment. [Figure 2] This is a functional block diagram of the driver assistance device in the drive recorder according to the first embodiment, showing the driver assistance control mainly classified by function. [Figure 3] This is a functional block diagram showing the detailed configuration of the situation recognition unit according to the first embodiment. [Figure 4] This is a table diagram classifying the items processed by the action-based scoring processing unit according to the first embodiment. [Figure 5] It is a table diagram classifying items processed by the location-based scoring processing unit according to the first embodiment. [Figure 6] (A) is a flowchart showing an operation support control analysis routine in the operation support system according to the first embodiment, and (B) is a flowchart showing an operation support control notification routine in the operation support system according to the first embodiment. [Figure 7] It is a time-CPU resource characteristic diagram of a drive recorder according to the first embodiment. [Figure 8] It is a functional block diagram showing the detailed configuration of a situation recognition unit according to a modification example of the first embodiment (CAN information addition). [Figure 9] It is a functional block diagram of an operation support device that mainly classifies operation support control by function in a drive recorder according to the second embodiment. [Figure 10] It is a flowchart showing an operation support control analysis routine in the operation support system according to the second embodiment. [Figure 11] It is a functional block diagram of an operation support device that mainly classifies operation support control by function in a drive recorder according to the third embodiment. [Figure 12] It is a flowchart showing an operation support control analysis routine in the operation support system according to the third embodiment. [Figure 13] It is a functional block diagram of an operation support device that mainly classifies operation support control by function in a drive recorder according to the fourth embodiment. [Figure 14] It is a flowchart showing an operation support control analysis routine in the operation support system according to the fourth embodiment. [Figure 15] It is a functional block diagram of an operation support device that mainly classifies operation support control by function in a drive recorder according to the fifth embodiment. [Figure 16] It is a flowchart showing an operation support control analysis routine in the operation support system according to the fifth embodiment. [Figure 17] This is a functional block diagram of the driver assistance device in the drive recorder according to the sixth embodiment, showing the driver assistance control mainly classified by function. [Figure 18] This is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the sixth embodiment. [Figure 19] This is a schematic diagram of a driver assistance system that supports driving in the autonomous driving of a vehicle according to the seventh embodiment. [Modes for carrying out the invention]

[0016] [First Embodiment]

[0017] Figure 1 is a plan view of a vehicle 10 to which the driver assistance system according to the first embodiment is applied.

[0018] Vehicle 10 is equipped with a vehicle control device 12 and a drive recorder 14. In addition to its original function as a drive recorder (monitoring by taking images of the outside and inside of the vehicle, and saving images in emergencies), the drive recorder 14 also has the function of a driver assistance device 14A according to the first embodiment (shown with a dotted frame in Figure 1).

[0019] The vehicle control device 14 performs control including the drive system (engine control, etc.) and the electrical system while the vehicle 10 is in motion.

[0020] The drive recorder 14 is connected to a gyro sensor 16 (labeled "Gyro" in Figure 1), an acceleration sensor (G sensor) 18 (labeled "G" in Figure 1), and a GPS receiver 20 (labeled "GPS" in Figure 1).

[0021] The gyro sensor 16 detects the direction of travel of the vehicle 10, the acceleration sensor 18 detects the acceleration and deceleration of the vehicle 10, and the GPS receiver 20 detects the location information of the vehicle 10.

[0022] Furthermore, the vehicle control device 12 is connected to a radar group 22 equipped with multiple millimeter-wave radars and LIDARs.

[0023] The radar group 22 detects obstacles and other objects in front of the vehicle 10.

[0024] The vehicle control device 12 uses the received information to execute control including the drive system and electrical system, or to inform the driver 24, who is driving, of the location information and the driving route to the destination. Figure 1 shows the driver 24 who has disembarked.

[0025] The drive recorder 14 is equipped with a group of cameras that capture images of the area around the vehicle 10 (in Figure 1, a forward-facing monitoring camera 26A and a rear-facing monitoring camera 26B are shown as an example). The drive recorder 14 of the first embodiment is also equipped with an interior monitoring camera 26C that captures images of the interior of the vehicle 10 (hereinafter, the forward-facing monitoring camera 26A, the rear-facing monitoring camera 26B, and the interior monitoring camera 26C are collectively referred to as the "camera group 26"). The camera group 26 may also include a right-facing monitoring camera 26D that captures images of the right side of the vehicle 10 and a left-facing monitoring camera 26E that captures images of the left side of the vehicle 10.

[0026] The drive recorder 14 is equipped with a driver assistance device 14A according to the first embodiment. In Figure 1, the inside of the drive recorder 14 is shown with a dotted line, but since it uses devices common to the original function of the drive recorder 14, from Figure 2 onward, it will be referred to as drive recorder 14(14A), and the explanation of the original function of the drive recorder 14 and the explanation of the function of the driver assistance device 14A will be used to distinguish between the two.

[0027] Figure 2 is a functional block diagram of the driver assistance device 14A, which primarily classifies the driver assistance control functions in the drive recorder 14 by function. Note that each block does not limit the hardware configuration of the driver assistance device 14A. If necessary, some or all of the blocks may be operated by a microcomputer as a driver assistance program.

[0028] As shown in Figure 2, the drive recorder 14 is equipped with a drive recorder main control unit 30. A group of cameras 26 (front monitoring camera 26A, rear monitoring camera 26B, and in-vehicle monitoring camera 28) are connected to the drive recorder main control unit 30, and the group of cameras continuously records, at least while driving.

[0029] (The original function of the Drive Recorder 14)

[0030] The drive recorder main control unit 30, as part of the drive recorder 14's primary function, captures images using the camera group 26 and overwrites the captured images sequentially from oldest to newest, within a predetermined capacity (for example, about one hour). In other words, the camera group 26 continuously captures images, recording them at predetermined intervals.

[0031] Here, an emergency period (for example, sudden deceleration such as emergency braking) is detected (or a signal is received from the vehicle control device 12), and images for a predetermined period before and after the emergency period (for example, 15 minutes before and after) are saved. In addition, the pass-through image (image being recorded) can be viewed by the driver 24 via the monitor unit 32.

[0032] Images taken before and after an emergency can be used, for example, to analyze the factors that led to the emergency. The monitor unit 30 can also be used to play back recorded images.

[0033] (Driving assistance functions)

[0034] In this embodiment, the drive recorder 14 also functions as a driver assistance device 14A. The driver assistance device 14A analyzes the driver's driving situation based on information from the gyro sensor 16, acceleration sensor 18, GPS receiver 20, and camera group 26, determines whether there are any dangerous actions unsuitable for driving (hereinafter referred to as dangerous events), and notifies the driver of advice to mitigate such dangerous events for the next drive. It is also possible to acquire information from the radar group 22 connected to the vehicle control device 12.

[0035] The driver assistance system 14A is equipped with a sensor information acquisition unit 34, which acquires Gryo information (direction information), G information (acceleration / deceleration information), GPS information (position information), and radar group analysis information (obstacle information).

[0036] The sensor information acquisition unit 34 is connected to the situation recognition unit 36 ​​and sends the acquired gyro information, G information, GPS information, and obstacle detection information to the situation recognition unit 36.

[0037] The situation recognition unit 36 ​​is connected to the drive recorder main control unit 30. The situation recognition unit 36 ​​acquires the image capture information from the camera group 26, which is used by the drive recorder main control unit 30.

[0038] As a result, the situation recognition unit 36 ​​can collect the vehicle 10's driving history, behavior, and external and internal conditions (image information) while the driver 24 is driving, and analyze and recognize the driving situation.

[0039] (Detailed configuration of the situation recognition unit 36)

[0040] Figure 3 is a functional block diagram showing the detailed configuration of the situation recognition unit 36.

[0041] The situation recognition unit 36 ​​includes a driving location analysis unit 36A, a behavior analysis unit 36B, a surrounding environment recognition unit 36C, and a driver situation recognition unit 36D.

[0042] The driving location analysis unit 36A acquires GPS information from the sensor information acquisition unit 34 and analyzes the location where the vehicle 10 is driving, such as an intersection, parking lot or indoors, or a narrow road.

[0043] The behavior analysis unit 36B acquires G information (acceleration information) and Gyro information (direction information) from the sensor information acquisition unit 34 and analyzes the behavior of the vehicle 10, such as turning left or right, starting, stopping, vehicle speed, steering angle, etc.

[0044] The surrounding environment recognition unit 36C acquires external image information from the drive recorder main control unit 30 and, if necessary, obstacle information from the sensor information acquisition unit 34, and analyzes the surrounding environment of the vehicle 10, such as the position and movement of people, preceding vehicles, oncoming vehicles, etc. around the vehicle, white and yellow lines on the roadway, and the distance between vehicles.

[0045] The driver status recognition unit 36D acquires in-vehicle image information from the drive recorder main control unit 30 and analyzes the driving posture of the driver 24 operating the vehicle 10, such as gaze, face direction, degree of eye opening / closing, skeletal structure, and the state of objects being held.

[0046] The situation recognition unit 36 ​​sends information on the vehicle 10's travel location, analyzed by the travel location analysis unit 36A, and the vehicle 10's behavior, analyzed by the behavior analysis unit 36B, to the risk event processing control unit 38 (sending of essential information).

[0047] Furthermore, the situation recognition unit 36 ​​sends information to the risk event processing control unit 38, based on a request from the risk event processing control unit 38, regarding the surrounding environment of the vehicle 10 analyzed by the surrounding environment recognition unit 36C, and the driving posture of the driver 24 analyzed by the driver situation recognition unit 36D (sending of arbitrary information).

[0048] As shown in Figure 2, the risk event processing control unit 38 includes a risk event determination unit 40. This risk event determination unit 40 aggregates information sent from the situation recognition unit 36, including essential information such as the vehicle 10's location and behavior, as well as optional information such as the vehicle 10's surrounding environment and the driver's 24's driving posture.

[0049] The risk event determination unit 40 is responsible for determining whether or not there is a risk while the vehicle 10 is in operation.

[0050] The risks while driving refer to the degree of danger of situations that could hinder safe driving, based on behavioral patterns determined by comparison with the Road Traffic Act, etc., and location patterns determined by the driving locations and driving conditions of the vehicle 10. In the first embodiment, this risk is quantified (scored).

[0051] Here, the risk event determination unit 40 performs a two-stage determination of whether or not there is a risk.

[0052] The risk event determination unit 40 determines the presence or absence of risks for conceivable items based on essential information (the location where the vehicle 10 is traveling and the behavior of the vehicle 10) and optional information (the surrounding environment of the vehicle 10 and the driving posture of the driver 24). The conceivable items can be selected from, for example, risks that have occurred in the past and have been registered in advance. For example, in relation to processing capacity, it is sufficient to anticipate 100 to 200 risk items, but this number is not limited. Each determination item is determined by a scene search formula and a determination formula.

[0053] Scene search formulas include search conditions based on location such as intersections without traffic lights, intersections with traffic lights, and parking lots; search conditions based on behavior such as turning right, turning left, going straight, and stopping; search conditions based on the surrounding environment such as preceding vehicles, pedestrians on the left shoulder, and bicycles stopped at intersections; and search conditions based on the driver's gaze, drowsiness, and smartphone use. Each of these can be used individually or in combination. For scenes that match the scene search formula, a judgment formula is used to determine whether there is a risk or not.

[0054] The judgment formulas include determining whether only sudden braking occurs (specifically, whether acceleration exceeds a predetermined value (e.g., 0.35G)) and whether the distance to the preceding vehicle becomes too short (specifically, if the distance between vehicles < 1.5 × (vehicle speed)). 2 Examples include / 9.8), etc.

[0055] The vehicle's own speed can be calculated using the integrated value of G-sensor information (corresponding to the first recognition state), and the distance to the preceding vehicle can be calculated from the size of the preceding vehicle recognized in the image captured by the forward-facing camera 26A and the hardware parameters of the camera group 26 (corresponding to the second recognition state).

[0056] In the first stage of the risk event determination unit 40, the presence or absence of risks for conceivable items is determined based on essential information (the location where the vehicle 10 is traveling and the behavior of the vehicle 10).

[0057] The first stage of scene search includes search conditions based on location, such as intersections without traffic lights and intersections with traffic lights, as well as search conditions based on behavior, such as turning right, turning left, going straight, and stopping. These can be used individually or in combination.

[0058] The first stage of the judgment formula includes cases where only sudden braking occurs (specifically, whether the acceleration exceeds a predetermined value (for example, 0.35G)), and cases where a vehicle fails to stop at a stop sign (specifically, when a vehicle passes through an intersection with a stop sign, excluding cases where the vehicle speed is 0 km / h).

[0059] The vehicle's own speed can be calculated using the integrated value of G-sensor information (corresponding to the first recognition state), and the distance to the preceding vehicle can be calculated from the size of the preceding vehicle recognized in the image captured by the forward-facing camera 26A and the hardware parameters of the camera group 26 (corresponding to the second recognition state).

[0060] Here, there is no problem if the presence or absence of risk can be determined using only the essential information, but there are cases where it is difficult to determine the risk due to insufficient information. In such cases, the image request unit 42 requests the drive recorder main control unit 30 to send information from the camera group 26 to the situation recognition unit 36.

[0061] The situation recognition unit 36 ​​acquires information from the camera group 26 and, as arbitrary information, sends the surrounding environment of the vehicle 10 from the surrounding environment recognition unit 36C (see Figure 2) to the risk event determination unit 40, and also sends the driving posture of the driver 24 from the driver situation recognition unit 36D (see Figure 2) to the risk event determination unit 40.

[0062] In the second stage of the risk event determination unit 40, the presence or absence of risks for conceivable items is determined based on essential information (the location where the vehicle 10 is traveling and the behavior of the vehicle 10) and optional information (the surrounding environment of the vehicle 10 and the driving posture of the driver 24).

[0063] The scene search formula searches for [Location] intersection without traffic lights, [Behavior] going straight, [Surrounding environment] vehicle ahead, and [Driver] looking ahead. Next, the judgment formula checks whether there was insufficient following distance in the matching scene, calculated as follows: following distance < 1.5 × (vehicle speed) 2 The system determines whether the condition of / 9.8 is met. The following distance is calculated based on the size of the preceding vehicle obtained from the optional image information and the hardware parameters. The vehicle's speed is calculated based on the integral value of the G-force obtained from the required information. These values ​​are input into the judgment formula; if the condition is met, it is determined that there is a risk, and if it is not met, it is determined that there is no risk.

[0064] In other words, by not using image information, which contains a relatively large amount of information and takes a long time to process, from the outset, and instead determining the presence or absence of risk based on sensor information, which contains a relatively small amount of information and does not take a long time to process, it is possible to realize the function of a driving assistance device 14A without impairing the original function of a drive recorder 14.

[0065] The risk event determination unit 40 is connected to the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, and sends the determination results of whether or not each item is a risk to the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46.

[0066] It is not necessary to send the risk assessment results for all items to the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46; it is possible to select which items to send based on the concepts of behavior and location. For example, out of a total of 160 items, it may be possible to send 130 items each to the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46.

[0067] Figure 4 is a table diagram classifying the items processed by the behavior-based scoring processing unit 44. As shown in Figure 4, the behavior-based items are classified into major items, medium items, and minor items.

[0068] Major categories include classifications based on the Road Traffic Act, classifications based on the duty of safe driving, and classifications based on the driver's condition.

[0069] Examples of subcategories include classifications related to road signs, classifications related to driver behavior, and classifications related to driver physical condition.

[0070] Subcategories include classifications by road sign, by driver behavior, and by driver's physical condition.

[0071] Major, medium, and minor items are each assigned a unique ID, and these IDs are aggregated into a single minor item ID. By looking at this minor item ID, it becomes possible to identify the type of major, medium, and minor item.

[0072] The behavior-based scoring processing unit 44 scores each sub-item based on a predetermined calculation formula and evaluates based on the total value. For example, in terms of behavior, a driver 24 who drives at an average level may be given 50 points out of 100, with points deducted for risky behavior and points added if the risk-free state continues.

[0073] Figure 5 is a table diagram classifying the items processed by the location-based scoring processing unit 46. As shown in Figure 5, location-based items are classified into vehicle location conditions and vehicle driving conditions, and scenes are set based on combinations of these two.

[0074] Vehicle location conditions include, for example, the presence or absence of facilities such as traffic lights, the shape of the road, and specific locations.

[0075] Vehicle driving conditions include, for example, speed, acceleration / deceleration, location, and weather.

[0076] The combination of vehicle location conditions and vehicle driving conditions results in a number of scenes equal to the number of vehicle location conditions multiplied by the number of vehicle driving conditions. Each scene is assigned an ID to identify it, and by looking at the ID, the scene can be identified.

[0077] The location-based scoring processing unit 46 scores each scene based on a predetermined calculation formula and evaluates based on the total value. For example, a calculation formula may be constructed such that a driver 24 who drives at an average level in a given location is given 50 points out of 100, with points deducted for risks and added for maintaining a risk-free state.

[0078] As shown in Figure 2, the action-based scoring processing unit 44 and the location-based scoring processing unit 46 are each connected to the priority determination unit 48.

[0079] The priority determination unit 48 extracts risks to be notified to the driver 24 based on the scoring results of the action-based scoring processing unit 44 and the location-based scoring processing unit 46, and sets a priority for the extracted risks. The premise is that the risks will be notified to the driver 24, but if there are notification restrictions, it is necessary to notify them in order of priority, and a predetermined number of risk notifications are sent to the advice notification unit 50.

[0080] The advice notification unit 50 performs specific risk consulting based on the received risks and notifies the driver 24 of the mobile terminal device 24A, etc. Notifications to the mobile terminal device 24A can be sent via the mobile terminal device 24A using a web application or native application. Furthermore, notifications to the driver 24 may be made not only via the mobile terminal device 24A, but also using the drive recorder 14 or the voice notification function of the vehicle 10, or via the cockpit or display of the vehicle 10.

[0081] The operation of the first embodiment will be described below with reference to the flowchart in Figure 6.

[0082] Figure 6(A) is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the first embodiment, and Figure 6(B) is a flowchart showing the driver assistance control notification routine in the driver assistance system according to the first embodiment.

[0083] First, the driver assistance control analysis routine will be explained according to Figure 6(A).

[0084] Step 100 determines whether or not it is time to analyze the information. The timing of the information analysis can be either regular or irregular.

[0085] Furthermore, when performing image information processing, it is preferable to set predetermined conditions, for example. These predetermined conditions are set based on the availability of hardware (CPU resources) installed in the drive recorder 14, as shown in Figure 7.

[0086] In Figure 7, the horizontal axis represents time, and the vertical axis represents CPU resources (utilization), with the utilization rate at which the function locks up set at 95%. Under these conditions, CPU resources fluctuate over time, but the system operates while maintaining a utilization rate of 5% or less.

[0087] Here, the driving assistance device 14A according to the first embodiment is defined as being in a time frame during which image processing is performed when it is below a predetermined threshold (90% in Figure 7). In other words, image processing does not need to be performed in real time; it is sufficient that the image processing is performed by the time of notification to the driver 14 and appropriate advice is generated. The notification may be given until the time of exiting the vehicle for the current drive, or until the time of exiting the vehicle for the next drive. As a means of recognizing the timing of communication, the drive recorder 14 may detect the on / off state of the ignition switch and the locked / unlocked state of the doors, or the distance may be obtained from the short-range communication function between the portable terminal device 24A held by the driver 24 and the drive recorder 14.

[0088] Furthermore, the threshold is not limited to 90%, but should be set to a level that does not interfere with the original function of the drive recorder 14.

[0089] If a negative result is obtained in step 100 of Figure 6(A), proceed to step 126 to decide whether to continue the analysis. If a negative result is obtained in step 126, return to step 100.

[0090] If a positive result is obtained in step 100, the process proceeds to step 1002 to acquire various sensor information, then to step 104 to analyze the driving location from the GPS information, and finally to step 106.

[0091] In step 106, the vehicle behavior is analyzed from GPS information, G-force information, and gyroscopic information, and then the process proceeds to step 108.

[0092] In step 108, the first stage, i.e., the risk event is determined based on the required information, and then the process moves to step 110 to determine whether there is sufficient input information for the risk event determination formula.

[0093] If step 110 determines that the result is negative or that there is insufficient input information for the risk event determination formula, the process proceeds from step 110 to step 112 to request image information of the exterior and interior of the vehicle.

[0094] In the next step 114, image information is acquired from the drive recorder main control unit 30, and the process proceeds to step 116.

[0095] In step 116, the second stage, i.e., the risk event including optional information in addition to the required information, is determined, and the process proceeds to step 118. Also, if the determination in step 110 is positive, it is determined that the second stage risk determination considering the optional information is unnecessary, and the process proceeds to step 118.

[0096] In step 118, an action-based scoring process is performed for each determined risk event (see Figure 4), then the process moves to step 120, where a location-based scoring process is performed for each determined risk event (see Figure 5), and then the process moves to step 122. Although the process is performed in the order of step 118 and step 120, the order can also be step 120 → step 118, or steps 118 and 120 can be processed simultaneously (parallel processing).

[0097] In step 122, the priority for notifying risk events is determined based on the scoring results, and the process proceeds to step 124. In step 124, the result storage process is executed, and the process proceeds to step 126.

[0098] In step 126, a decision is made as to whether or not to continue the analysis. If the result is positive, the process returns to step 100 as described above; if the result is negative, this routine terminates.

[0099] do.

[0100] Next, the driver assistance control notification routine will be explained according to Figure 6(B).

[0101] Step 150 determines whether or not it is time to notify of a risk event. If the result in Step 150 is negative, this routine ends. If the result in Step 150 is positive, the process proceeds to Step 152.

[0102] In the first embodiment, the notification timing is set to when the ignition key is turned off, and as shown in Figure 1, the notification is sent when the driver 24 turns off the vehicle 10.

[0103] Furthermore, the notification timing is not limited to the latter time of vehicle 10, but may be, for example, when the next ignition key is turned on. Also, other notification timings are possible, such as using the short-range communication function to notify the driver 24 when they move out of a predetermined range and then return to it. In addition, even when the driver is not around the vehicle, notifications may be sent via a web application or native application at any time.

[0104] In step 152, the risk event stored in step 124 in Figure 6(A) is read, the process moves to step 154, a notification is sent to the mobile terminal device 24A or the like held by the driver 24, and the process moves to step 156.

[0105] Step 156 executes the archiving process for the notified risk events, and this routine then terminates. Note that it is not necessary to save all risk events in the history; you may select which ones to keep.

[0106] (Modified version of the first embodiment)

[0107] In the first embodiment, as shown in Figure 3, the situation recognition unit 36 ​​recognizes the situation using the driving location analysis unit 36A, the behavior analysis unit 36B, the surrounding environment recognition unit 36C, and the driver situation recognition unit 36D. However, as shown in Figure 8, a vehicle operation mode recognition unit 36E may be added to recognize the vehicle operation mode based on the CAN data of the vehicle 10. This allows for a more detailed recognition of the behavior of the vehicle (vehicle 10).

[0108] (Example of the first embodiment, "Example 1")

[0109] The risk event processing is performed using the following steps (a) to (c).

[0110] (a) Based on GPS information and acceleration information, the vehicle's (vehicle 10) actions and location information are derived. For example, the vehicle turns left at an intersection with traffic lights.

[0111] (b) Obtain the image processing results.

[0112] • The system analyzes image information from camera group 26 (outside the vehicle) to estimate the surrounding situation. For example, it might analyze that there was a bicycle to the left of the vehicle (vehicle 10) during the 5 seconds it takes to turn left at a green light.

[0113] • Analyze image information from camera group 26 (inside the vehicle) to estimate the state of the driver 24. For example, if the driver did not check for safety within 5 seconds before making a left turn.

[0114] (c) The risk event is determined using only the data from (a) and (b) for any time period before and after the scene in which the vehicle makes a left turn.

[0115] Case 1: If you apply the brakes suddenly when turning left in (b)

[0116] This is a risky scenario where the driver reacted too late and slammed on the brakes, which constitutes inadequate safe driving.

[0117] Case 2: (b) If no braking was performed at all when turning left

[0118] This is a risky scenario where the person passed by without noticing, and it constitutes obstruction of pedestrians or other pedestrians.

[0119] Based on the assessment results for Case 3:(c), provide specific advice.

[0120] In Case 1, the notification reads, "Always check for safety before turning left at an intersection." In Case 2, the notification reads, "Always slow down to a speed at which you can stop completely, and then check for safety before turning left."

[0121] (Example 2 of the first embodiment)

[0122] After analyzing the location and the vehicle's (vehicle 10) behavior, additional images are analyzed only when necessary for risk scenes requiring image analysis (using arbitrary information).

[0123] An example of an event that does not require image analysis (an event that can be analyzed with only essential information) is an event where a vehicle exceeds the speed limit while driving straight on a main road.

[0124] In this case, assuming the location is a main road, the vehicle (vehicle 10) is moving straight, and the vehicle's speed is compared to the main road's speed limit to detect if it is exceeding the speed limit, image information becomes unnecessary.

[0125] According to Embodiment 2 of the first embodiment, since a timestamp for image analysis is specified, it becomes possible to reduce the CPU resources required for image analysis.

[0126] (Example 3 of the first embodiment)

[0127] The detected risk events are classified by location and behavior, and scored to select the scene with the lowest score, thereby determining the priority of risk events that should be prioritized for advice.

[0128] According to Example 3 of the first embodiment, among the many risky driving scenarios, particularly problematic driving scenarios can be identified and notified on a priority basis, enabling rapid correction of problematic driving scenarios.

[0129] [Second Embodiment]

[0130] A second embodiment of the present invention will be described below with reference to Figures 9 and 10. Note that components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0131] The second embodiment is characterized by the addition of a function to edit (add, delete, change, etc.) the judgment threshold and risk event judgment items when the judgment result in the risk event judgment unit 40 deviates from the judgment that was previously assumed, or when a new risk is identified that does not fall under any of the pre-set risk event items.

[0132] Figure 9 is a functional block diagram of the driver assistance device 14A, which mainly shows the driver assistance control functions of the drive recorder 14 according to the second embodiment of the present invention, classified by function.

[0133] A user interface (UI) 52 is connected to the driver assistance device 14A. The UI 52 is a device that can be operated by an operator, for example, installed in a management department that remotely supports the driver assistance device 14A. In addition to the operator, the driver 24 may also be connected.

[0134] The risk event determination unit 40 sends information regarding the determination result to the UI 52. The UI 52 analyzes the determination result and determines whether threshold adjustment and determination level adjustment are necessary.

[0135] If the operator determines that threshold adjustment is necessary, they operate the UI 52 to send threshold adjustment information to the threshold adjustment unit 54. The threshold adjustment unit 54 is connected to the situation recognition unit 36 ​​and adjusts the threshold value to be compared with the sensor information, which is performed by the situation recognition unit 36.

[0136] Furthermore, if the operator determines that an adjustment of the judgment level is necessary, they operate the UI 52 to send judgment level adjustment information to the judgment level adjustment unit 56. The judgment level adjustment unit 56 is connected to the risk event judgment unit 40 and performs adjustments to the judgment criteria and other factors for risk event judgment that are executed in the risk event judgment unit 40.

[0137] The operation of the second embodiment will be described below.

[0138] Figure 10 is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the second embodiment. Steps identical to those in the first embodiment (see Figure 6(A)) are given the same step numbers, and the explanation of their processing is omitted.

[0139] In step 110, after it is determined that there is sufficient input information for the risk event determination formula, or in step 116, after the determination of the second-stage risk event is performed, in step 128 the determination result is sent to UI52.

[0140] In the next step, 130, UI52 determines whether adjustments to the judgment result (threshold adjustment, judgment level adjustment) are necessary. If adjustments are deemed necessary in step 130, the process proceeds to step 132, where the judgment level adjustment process and threshold adjustment process are executed, and the process returns to step 108 to repeat the above steps.

[0141] Furthermore, if a negative result is obtained in step 132, it is determined that no adjustment to the judgment result is necessary, and the process proceeds to step 118.

[0142] According to the second embodiment, for example, if general traffic manners change due to changes in laws or social conditions, advanced advice can be continuously provided without new development by editing the threshold and judgment level adjustments for determining risk events.

[0143] (Example 3 of the second embodiment)

[0144] The output of the risk event determination unit 40 is presented to the operator via the UI 52.

[0145] If there is an error in the judgment, threshold adjustments and judgment level adjustments will be performed according to the following cases.

[0146] Case 1: When it is determined that there is no risk.

[0147] If the criteria for determining a risk event match (combination of location, vehicle behavior, etc.), but the actual level of risk does not match the determination threshold, adjust the determination threshold (for example, thresholds for following distance or relative speed).

[0148] Case 2: When the criteria for determining a risk event are incorrect and it is determined that a different rule should be used, as previously designed.

[0149] For example, if there is an error in the detection results of a location or other element targeted for risk event determination, the following processes 1 and 2 will be executed.

[0150] • Process 1: Modify the detection results, such as location, so that the results for determining the relevant dangerous event are output.

[0151] Process 2: The group of judgment thresholds is modified so that the output of the state recognition unit 36 ​​is consistent with the correction results from Process 1.

[0152] Case 3: The risk event is incorrectly identified and does not fall under any of the pre-designed rules.

[0153] Add a new risk event determination rule.

[0154] The above actions may be performed manually by the operator (driver 24), processed according to a predetermined program, or decided using AI based on a vast amount of historical data (so-called big data) through machine learning.

[0155] [Third Embodiment]

[0156] A third embodiment of the present invention will be described below with reference to Figures 11 and 12. Note that components identical to those in the first and second embodiments are denoted by the same reference numerals, and their descriptions are omitted.

[0157] The third embodiment is characterized by the addition of a function to edit (add, delete, change, etc.) the judgment threshold and risk event judgment items when the judgment result and judgment accuracy of the risk event judgment unit 40 deviate from the judgment expected in advance, or when a new risk is identified that does not fall under any of the pre-set risk event items.

[0158] Figure 11 is a functional block diagram of the driver assistance device 14A in the drive recorder 14 according to the second embodiment of the present invention, which mainly shows the driver assistance control classified by function.

[0159] A user interface (UI) 52 is connected to the driver assistance device 14A. The UI 52 is a device that can be operated by an operator, for example, installed in a management department that remotely supports the driver assistance device 14A. In addition to the operator, the driver 24 may also be connected.

[0160] The risk event determination unit 40 sends information regarding the determination result and determination accuracy to the UI 52. The UI 52 analyzes the determination result and determination accuracy and determines whether threshold adjustment and determination level adjustment are necessary.

[0161] If the operator determines that threshold adjustment is necessary, they operate the UI 52 to send threshold adjustment information to the threshold adjustment unit 54. The threshold adjustment unit 54 is connected to the situation recognition unit 36 ​​and adjusts the threshold value to be compared with the sensor information, which is performed by the situation recognition unit 36.

[0162] Furthermore, if the operator determines that an adjustment of the judgment level is necessary, they operate the UI 52 to send judgment level adjustment information to the judgment level adjustment unit 56. The judgment level adjustment unit 56 is connected to the risk event judgment unit 40 and performs adjustments to the judgment criteria and other factors for risk event judgment that are executed in the risk event judgment unit 40.

[0163] The operation of the third embodiment will be described below.

[0164] Figure 12 is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the third embodiment. Steps identical to those in the first embodiment (see Figure 6(A)) are given the same step numbers, and the explanation of their processing is omitted.

[0165] In step 110, after it is determined that there is sufficient input information for the risk event determination formula, or in step 116, after the determination of the second-stage risk event is performed, in step 128, the determination result and determination accuracy are sent to UI52.

[0166] In the next step, 130, UI52 determines whether adjustments to the judgment result and judgment accuracy (threshold adjustment, judgment level adjustment) are necessary. If adjustments are deemed necessary in step 130, the process proceeds to step 132, where the judgment level adjustment process and threshold adjustment process are executed, and the process returns to step 108 to repeat the above steps.

[0167] Furthermore, if a negative result is obtained in step 132, it is determined that no adjustment of the judgment result or judgment accuracy is necessary, and the process proceeds to step 118.

[0168] According to the third embodiment, for example, if general traffic manners change due to changes in laws or social conditions, advanced advice can be continuously provided without new development by editing the threshold and judgment level adjustments for determining risk events.

[0169] In addition, according to the third embodiment, by filtering and sorting the output according to the accuracy of the risk event determination results, when checking the event determination results in UI52, it is possible to check them efficiently by checking them in order from the lowest to the highest accuracy.

[0170] (Example of the third embodiment, "Example 4")

[0171] In addition to the embodiment 3 of the second embodiment, the output of the risk event determination unit 40 is enhanced with a determination accuracy, which is then presented to the operator via the UI 52.

[0172] If there is an error in the judgment, in addition to the measures in Example 3, the following actions will be taken.

[0173] Case 1: Regarding the provision of advice

[0174] For risk events with a prediction accuracy below a certain value, advice will not be provided, or its priority in the order of provision will be lowered.

[0175] Case 2: Regarding the display of UI52

[0176] Risk events with a detection accuracy of a certain value or higher will be displayed preferentially in UI52.

[0177] [Fourth Embodiment]

[0178] A fourth embodiment of the present invention will be described below with reference to Figures 13 and 14. Note that components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0179] In the first embodiment, the risk event determination unit 40 was equipped with an image request unit 42. In the first stage of the risk event determination unit 40's determination based on essential information, if it determined that image information was necessary, it requested image information (optional information) from the drive recorder main control unit 30, and made a determination (second stage) taking the image information into account.

[0180] In contrast, in the fourth embodiment, the risk event determination unit 40 determines risk events using sensor information and image information from the outset, without distinguishing between essential and optional information.

[0181] Figure 14 is a functional block diagram of the driver assistance device 14A, which mainly shows the driver assistance control functions of the drive recorder 14 according to the fourth embodiment of the present invention, classified by function.

[0182] The situation recognition unit 36 ​​sends information on the vehicle's location, analyzed by the location analysis unit 36A, and the vehicle's behavior, analyzed by the behavior analysis unit 36B, to the risk event processing control unit 38.

[0183] Furthermore, the situation recognition unit 36 ​​acquires information from the camera group 26 and sends the surrounding environment of the vehicle 10 to the risk event determination unit 40 from the surrounding environment recognition unit 36C (see Figure 2), and also sends the driver's behavior of the driver 24 (distracted driving, glancing, inattentive driving, smartphone operation, poor posture, failure to check for safety, etc.) to the risk event determination unit 40 from the driver situation recognition unit 36D (see Figure 2).

[0184] The risk event determination unit 40 determines the presence or absence of risks for conceivable items based on the vehicle 10's location, the vehicle 10's behavior, the surrounding environment of the vehicle 10, and the driver's 24 driving posture.

[0185] The operation of the fourth embodiment will be described below.

[0186] Figure 10 is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the fourth embodiment. Steps identical to those in the first embodiment (see Figure 6(A)) are given the same step numbers, and the explanation of their processing is omitted.

[0187] In step 106, the vehicle behavior is analyzed from GPS information, G-force information, and gyroscopic information, and then the process proceeds to step 114.

[0188] In step 114, image information is acquired from the drive recorder main control unit 30, and the process proceeds to step 116.

[0189] In step 116, a risk event is determined based on the vehicle 10's location and behavior, as well as the surrounding environment of the vehicle 10 and the driver's (24) driving posture, and the process proceeds to step 118.

[0190] According to the fourth embodiment, the vehicle 10 can determine risk events corresponding to various scenarios acquired while driving and provide accurate advice to resolve those risk events.

[0191] Furthermore, according to the fourth embodiment, by identifying particularly problematic driving scenarios among the many risky driving situations and prioritizing notification, it becomes possible to quickly correct problematic driving scenarios.

[0192] [Fifth Embodiment]

[0193] A fifth embodiment of the present invention will be described below with reference to Figures 15 and 16. Note that components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0194] In the first embodiment, the risk event determination unit 40 includes an action-based scoring processing unit 44 and a location-based scoring processing unit 46. The action-based scoring processing unit 44 sends the determination results of whether or not each item is risky to the action-based scoring processing unit 44 and the location-based scoring processing unit 46. The action-based scoring processing unit 44 scores each sub-item based on a predetermined calculation formula and evaluates based on the total value, while the location-based scoring processing unit 46 scores each scene based on a predetermined calculation formula and evaluates based on the total value.

[0195] In contrast, in the fifth embodiment, the risk event determination unit 40 makes determinations based on so-called raw data, without distinguishing or setting priorities for the results determined by the risk event determination unit 40.

[0196] Figure 15 is a functional block diagram of the driver assistance device 14A, which mainly shows the driver assistance control functions of the drive recorder 14 according to the fifth embodiment of the present invention, classified by function.

[0197] The risk event determination unit 40 performs a two-stage determination of whether or not there is a risk.

[0198] In the first stage of the risk event determination unit 40, the presence or absence of risks for conceivable items is determined based on essential information (the location where the vehicle 10 is traveling and the behavior of the vehicle 10).

[0199] In this case, there is no problem if the presence or absence of risk can be determined using only the essential information, but there are times when it is difficult to determine the risk due to insufficient information.

[0200] Therefore, if there is insufficient information, the image request unit 42 requests the drive recorder main control unit 30 to send information from the camera group 26 to the situation recognition unit 36.

[0201] The situation recognition unit 36 ​​acquires information from the camera group 26 and, as optional information, sends the surrounding environment of the vehicle 10 from the surrounding environment recognition unit 36C (see Figure 2) to the risk event determination unit 40, and also sends the driver behavior of the driver 24 (distracted driving, glancing, inattentive driving, smartphone operation, poor posture, failure to check for safety, etc.) from the driver situation recognition unit 36D (see Figure 2) to the risk event determination unit 40.

[0202] In the second stage of the risk event determination unit 40, the presence or absence of risks for conceivable items is determined based on essential information (the location where the vehicle 10 is traveling and the behavior of the vehicle 10) and optional information (the surrounding environment of the vehicle 10 and the driving posture of the driver 24).

[0203] In other words, by not using image information, which contains a relatively large amount of information and takes a long time to process, from the outset, and instead determining the presence or absence of risk based on sensor information, which contains a relatively small amount of information and does not take a long time to process, it is possible to realize the function of a driving assistance device 14A without impairing the original function of a drive recorder 14.

[0204] The risk event determined by the risk event determination unit 40 is sent to the advice notification unit 50.

[0205] The advice notification unit 50 performs specific risk consulting based on the received risks and notifies the driver 24 of the mobile terminal device 24A, etc.

[0206] The operation of the fifth embodiment will be described below.

[0207] Figure 16 is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the fifth embodiment. Steps identical to those in the first embodiment (see Figure 6(A)) are given the same step numbers, and the explanation of their processing is omitted.

[0208] If a negative result is determined in step 110, or if it is determined that there is insufficient input information for the risk event determination formula, the process proceeds from step 110 to step 112, where image information of the exterior and interior of the vehicle is requested.

[0209] In the next step 114, image information is acquired from the drive recorder main control unit 30, and the process proceeds to step 116.

[0210] In step 116, the second stage, i.e., the risk event including optional information in addition to the required information, is determined, and the process proceeds to step 124. Also, if the determination in step 110 is positive, it is determined that the second stage risk determination considering the optional information is unnecessary, and the process proceeds to step 124.

[0211] In step 124, the result storage process is executed, and the process proceeds to step 126.

[0212] In step 126, a decision is made as to whether or not to continue the analysis. If the result is positive, the process returns to step 100 as described above; if the result is negative, this routine terminates.

[0213] do.

[0214] According to the fifth embodiment, the vehicle 10 can determine risk events corresponding to various scenarios acquired while driving and provide accurate advice to resolve those risk events.

[0215] Furthermore, according to the fifth embodiment, since a timestamp for image analysis is specified, it becomes possible to reduce the CPU resources required for image analysis.

[0216] [Sixth Embodiment]

[0217] A sixth embodiment of the present invention will be described below with reference to Figures 17 and 18. Note that components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0218] (Difference 1 from the first embodiment)

[0219] In the first embodiment, the risk event determination unit 40 was equipped with an image request unit 42. In the first stage of the risk event determination unit 40's determination based on essential information, if it determined that image information was necessary, it requested image information (optional information) from the drive recorder main control unit 30, and made a determination (second stage) taking the image information into account.

[0220] In contrast, in the sixth embodiment, the risk event determination unit 40 determines risk events using sensor information and image information from the outset, without distinguishing between essential and optional information.

[0221] (Difference 2 from the first embodiment)

[0222] In the first embodiment, the risk event determination unit 40 includes an action-based scoring processing unit 44 and a location-based scoring processing unit 46. The action-based scoring processing unit 44 sends the determination results of whether or not each item is risky to the action-based scoring processing unit 44 and the location-based scoring processing unit 46. The action-based scoring processing unit 44 scores each sub-item based on a predetermined calculation formula and evaluates based on the total value, while the location-based scoring processing unit 46 scores each scene based on a predetermined calculation formula and evaluates based on the total value.

[0223] In contrast, in the sixth embodiment, the risk event determination unit 40 makes determinations based on so-called raw data, without distinguishing or setting priorities for the results determined by the risk event determination unit 40.

[0224] Figure 17 is a functional block diagram of the driver assistance device 14A, which mainly shows the driver assistance control functions of the drive recorder 14 according to the fourth embodiment of the present invention, classified by function.

[0225] The situation recognition unit 36 ​​sends information on the vehicle's location, analyzed by the location analysis unit 36A, and the vehicle's behavior, analyzed by the behavior analysis unit 36B, to the risk event processing control unit 38.

[0226] Furthermore, the situation recognition unit 36 ​​acquires information from the camera group 26 and sends the surrounding environment of the vehicle 10 to the risk event determination unit 40 from the surrounding environment recognition unit 36C (see Figure 2), and also sends the driver's behavior of the driver 24 (distracted driving, glancing, inattentive driving, smartphone operation, poor posture, failure to check for safety, etc.) to the risk event determination unit 40 from the driver situation recognition unit 36D (see Figure 2).

[0227] The risk event determination unit 40 determines the presence or absence of risks for conceivable items based on the vehicle 10's location, the vehicle 10's behavior, the surrounding environment of the vehicle 10, and the driver's 24 driving posture.

[0228] The risk event determined by the risk event determination unit 40 is sent to the advice notification unit 50.

[0229] The advice notification unit 50 performs specific risk consulting based on the received risks and notifies the driver 24 of the mobile terminal device 24A, etc.

[0230] The operation of the sixth embodiment will be described below.

[0231] Figure 18 is a flowchart showing the driver assistance control analysis routine in the driver assistance system according to the sixth embodiment. Steps identical to those in the first embodiment (see Figure 6(A)) are given the same step numbers, and the explanation of their processing is omitted.

[0232] In step 106, the vehicle behavior is analyzed from GPS information, G-force information, and gyroscopic information, and then the process proceeds to step 114.

[0233] In step 114, image information is acquired from the drive recorder main control unit 30, and the process proceeds to step 116.

[0234] In step 116, a risk event is determined based on the vehicle 10's location and behavior, as well as the surrounding environment of the vehicle 10 and the driver's (24) driving posture, and the process proceeds to step 124.

[0235] In step 124, the result storage process is executed, and the process proceeds to step 126.

[0236] In step 126, a decision is made as to whether or not to continue the analysis. If the result is positive, the process returns to step 100 as described above; if the result is negative, this routine terminates.

[0237] do.

[0238] According to the sixth embodiment, the vehicle 10 can determine risk events corresponding to various scenarios acquired while driving and provide accurate advice to resolve those risk events.

[0239] Furthermore, in the determination process of the risk event determination unit 40, risk events can be determined using sensor information and image information from the outset, without distinguishing between essential and optional information.

[0240] Furthermore, in the determination by the risk event determination unit 40, the risk event is determined based on so-called raw data, without distinguishing or setting priorities for the results determined by the risk event determination unit 40.

[0241] In other words, according to the sixth embodiment, risk events corresponding to the driving scene of the vehicle 10 can be accurately determined with sufficient information without complex control, and it can be said that this is a useful configuration as a low-cost version due to the simplification of the device configuration.

[0242] [Seventh Embodiment]

[0243] A seventh embodiment of the present invention will be described below with reference to Figure 19. Note that components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0244] As shown in Figure 19, in the seventh embodiment, a gyro sensor 16 (labeled "Gyro" in Figure 19), an acceleration sensor (G sensor) 18 (labeled "G" in Figure 19), and a GPS receiver 20 (labeled "GPS" in Figure 19) are connected to the vehicle control device 12.

[0245] In the seventh embodiment, the vehicle control device 12 acquires the necessary information for the driving location analysis unit 36A and the behavior analysis unit 36B, namely, information from the gyro sensor 16, the acceleration sensor 18, and the GPS receiver 20. In this case, the vehicle control device 12 may also acquire information about obstacles in front of the vehicle 10 as information from the radar group 22. In particular, it is possible to reliably recognize obstacles that are difficult to recognize when the amount of information from the camera group 26 is small, such as at night or in rainy weather.

[0246] According to the seventh embodiment, if the vehicle 10 has any of the existing sensors (gyro sensor 16, acceleration sensor 18, and GPS receiver 20), it is not necessary for the drive recorder 14 to have that function, and the necessary sensor information can be obtained from the vehicle control device 12, thus simplifying the configuration.

[0247] In each embodiment of the present invention (including modified examples), the drive recorder 14 is configured to perform all control functions (information acquisition, situation recognition, risk determination, etc.). However, the gyro sensor 16, acceleration sensor 18, GPS receiver 20, camera group 26, and drive recorder main control unit 30 may be configured as in-vehicle hardware (drive recorder 14), and the output signals from this hardware may be transmitted to the cloud, where processing equivalent to the risk event processing unit 40, priority determination unit 48, advice notification unit 50, etc., is performed. In other words, there are no restrictions on the arrangement between the hardware mounted on the vehicle 10 and the functions processed on the cloud. [Explanation of symbols]

[0248] 10 Vehicle, 12 Vehicle control device, 14 Drive recorder, 14A Driving assistance device, 16 Gyro sensor, 18 Acceleration sensor (G sensor), 20 GPS receiver, 22 Radar group, 24 Driver, 26A Forward-facing surveillance camera, 26B Rearward-facing surveillance camera, 26C In-cabin surveillance camera, 26 Camera group, 26D Right-facing surveillance camera, 26E Left-facing surveillance camera, 30 Drive recorder main control unit, 32 Monitor unit, 34 Sensor information acquisition unit, 36 Situation recognition unit, 36A Driving location analysis unit, 36B Behavior analysis unit, 36C Surrounding environment recognition unit, 36D Driver situation recognition unit, 38 Risk event processing control unit, 40 Risk event determination unit, 42 Image request unit, 44 Action-based scoring processing unit, 44 Location-based scoring processing unit, 48 Priority determination unit, 50 Advice notification unit

Claims

1. A situation recognition unit that acquires vehicle location information and vehicle behavior information as information sources and recognizes the status of the vehicle based on the information sources, and (36) A determination unit analyzes the recognition results from the situation recognition unit to determine whether or not there are any risk events that may occur while the vehicle is in motion, and (38, 40) The determination unit determines that the risk event exists, and the notification unit notifies at least the driver operating the vehicle of advice on how to resolve the risk event, and (50) The determination unit determines the presence or absence of the risk event using a scene search formula for searching whether at least one of the following search conditions—a search condition based on the location where the vehicle is located and a search condition based on the behavior of the vehicle—is met, and a determination formula for determining the presence or absence of the risk event in the scene searched by the scene search formula. Driving assistance system.

2. A determination unit acquires vehicle location information and vehicle behavior information as information sources, recognizes the status of the vehicle based on the information sources, analyzes the results of the recognition of the vehicle's status, and determines whether or not there are any risk events that may occur while the vehicle is in motion. The vehicle includes a notification unit that, when the determination unit determines that the risk event exists, notifies at least the driver operating the vehicle of advice on how to resolve the risk event. The determination unit determines the presence or absence of the risk event using a scene search formula for searching whether at least one of the following search conditions—a search condition based on the location where the vehicle is located and a search condition based on the behavior of the vehicle—is met, and a determination formula for determining the presence or absence of the risk event in the scene searched by the scene search formula. Driving assistance system.

3. The aforementioned situation recognition unit, The aforementioned information sources are classified into essential information sources consisting of the vehicle's location information and vehicle behavior information, and optional information sources consisting of image information of the vehicle's surroundings and interior. In the aforementioned determination unit, according to the recognition items used to determine the risk event, As the first stage of situation recognition, a first recognition function recognizes the driving situation based on the essential information source and outputs it to the determination unit, If the output of the first stage is insufficient as recognition items to be used for determining risk events, a second recognition function is provided that recognizes the operating status based on the essential information source and the optional information source as a second stage of situation recognition and outputs it to the determination unit, The driving support device according to claim 1, comprising:

4. The driving assistance device according to any one of claims 1 to 3, wherein the risk events determined by the determination unit are classified in a manner that overlaps between behavioral risk events related to violations of the Road Traffic Act and locational risk events based on scenes determined by the driving location and the vehicle's driving behavior, a score is performed for each of the behavioral risk events and locational risk events according to the importance of countermeasures, and the priority to be notified by the notification unit is determined based on the scoring results.

5. The driving support device according to any one of claims 1 to 4, further comprising a monitoring unit that acquires the judgment result from the judgment unit, monitors whether the judgment result from the judgment unit is good or bad, and updates the judgment criteria in the judgment unit based on the monitoring result.

6. The driving support device according to claim 5, wherein the monitoring unit acquires judgment accuracy information from the judgment unit and monitors the quality of the judgment results in order of increasing judgment accuracy.

7. The driving assistance device according to any one of claims 1 to 6, wherein the vehicle's driving information is added as the information source to be acquired.

8. The system acquires vehicle location information and vehicle behavior information as information sources, and recognizes the status of the vehicle based on the information sources. The results of the recognition of the vehicle's status are analyzed to determine whether or not there are any risk events that may occur while the vehicle is in motion. If the aforementioned risk event is determined to exist, advice on how to resolve the risk event will be provided to at least the driver operating the vehicle. The presence or absence of the risk event is determined using a scene search formula for searching whether at least one of the following search conditions—a search condition based on the location where the vehicle is located and a search condition based on the behavior of the vehicle—is met, and a determination formula for determining the presence or absence of the risk event for the scene found by the scene search formula. Driving assistance methods.

9. A main control unit mounted on a vehicle captures the surrounding environment, including at least the area in front of the vehicle, records the captured images by overwriting them sequentially from oldest to newest within a predetermined capacity, and, when an emergency is detected, saves images for a predetermined period before and after the emergency. A driving support device according to any one of claims 1 to 7, A dashcam that has [a certain feature].

10. Computers, To be operated as each part of the driving assistance device described in any one of claims 1 to 7, Driver assistance control program.

Images