WO2022196660A1 - Driving assistance device, driving assistance method, drive recorder, and driving assistance control program - Google Patents

Abstract

A driving assistance device (14) has: a first condition recognition unit (36) that acquires, as an essential information source, position information of a vehicle and behavior information of the vehicle and recognizes an essential condition for the vehicle on the basis of the essential information source; a second condition recognition unit (36, 40, 42) that acquires an arbitrarily defined information source on the basis of image information relating to the surroundings of the vehicle and/or inside a vehicle cabin and recognizes a driving condition of the vehicle on the basis of the essential information source and the arbitrarily defined information source; a determination unit (40) that analyzes a recognition result by the first condition recognition unit or a recognition result by the second condition recognition unit and determines the presence/absence of a risk event which can occur during traveling of the vehicle; and a notification unit (50) that, when the determination result by the determination unit has indicated that the risk event is present, notifies at least a driver who is driving the vehicle of advice for eliminating the risk event.

Description

Driving support device, driving support method, drive recorder, driving support control program

The present disclosure relates to a driving assistance device, a driving assistance method, a drive recorder, and a driving assistance control program that provide advice on driving operations to the driver.

Cross-references to related applications

This application is based on and claims the benefit of priority from patent application number 2021-046575, filed March 19, 2021, the entire contents of which are incorporated by reference. incorporated herein by.

In recent years, when a vehicle is operated by a driver, using acceleration and speed information, there are problems with predetermined safe driving operations such as sudden acceleration and deceleration caused by sudden acceleration and braking, and exceeding the legal speed limit. It has been put into practical use to send advice to the driver to correct the problematic behavior such as driving operation when there is a certain behavior such as driving operation.

With the above advice, it is not possible to identify the driving situations that the driver is not good at (for example, when turning left, it is easy to brake suddenly due to the delay in noticing a pedestrian, etc.) and the characteristic driving operations of individual drivers. , there are cases where it is not possible to provide appropriate and specific corrective advice for difficult driving scenes such as those described above.

Here, Japanese Unexamined Patent Application Publication No. 2013-191230 describes a vehicle safe driving promotion system that can improve the driver's awareness of safe driving by giving the driver mental encouragement.

More specifically, the in-vehicle device disclosed in Japanese Unexamined Patent Application Publication No. 2013-191230 stores the safe driving threshold value and the economical driving threshold value stored in the storage means, the driving state information obtained by the driving state obtaining means, and the safe driving evaluation history. judging the driving situation of the driver from the information and the economic driving evaluation history information, and if the driving situation of the driver is within the judgment threshold value stored in the storage means, notifying the driver of a message to praise the driver via the notifying means; When the driving condition of the driver is outside the threshold value, advice is given to the driver via the notification means.

This praise (message) can give the driver mental encouragement, and as a result, it is expected that the driver's voluntary practice of safe driving will improve safe driving awareness and reduce traffic accidents.

However, it does not provide advice on how to drive depending on the scene, but rather general advice that takes into account the driving conditions of individual drivers. In addition, in order to grasp the driving information of each driver in detail, there are cases where the details of the surroundings of the vehicle and the behavior of the driver are required. In other words, depending on the scene, there are cases where the amount of information for analysis may be small, and cases where a huge amount of information is required. In this case, if the maximum amount of information is always prepared so that it can be used in any scene, the amount of information will increase in response to requests. The processing capacity of an aftermarket drive recorder, etc.) may not be sufficient.

The present disclosure obtains and analyzes necessary and sufficient driving operation information and information obtained by monitoring the surroundings of the vehicle for each of various scenes while driving the vehicle, and provides advice according to the driving operation of each individual driver. It is an object to obtain a driving assistance control device, a driving assistance method, a drive recorder, and a driving assistance control program capable of providing

A driving support control device according to the present disclosure acquires position information of a vehicle and behavior information of the vehicle as essential information sources, and recognizes an essential situation of the vehicle based on the essential information sources. A second situation in which an arbitrary information source is acquired based on image information of at least one of the surroundings of the vehicle and the interior of the vehicle, and the driving situation of the vehicle is recognized based on the essential information source and the arbitrary information source. Analyzing the recognition result of the recognition unit and the first situation recognition unit, or the recognition result of the second situation recognition unit, and determining whether or not there is a risk event that can occur while the vehicle is running. and a notification unit that notifies at least the driver driving the vehicle of advice for resolving the risk event when the risk event has occurred in the determination result of the determination unit. there is

A driving support method according to an aspect of the present disclosure acquires vehicle position information and vehicle behavior information as essential information sources, and according to recognition items used for risk event determination by a determination unit, a first stage of situation recognition. A first recognition function that recognizes the driving situation based on the essential information source and outputs it to the determination unit as a a second recognition function for recognizing the driving situation based on the essential information source and the arbitrary information source as situation recognition and outputting it to the determination unit; When analyzing at least one of the outputs of the recognition function of and determining the presence or absence of a risk event that can occur while the vehicle is running, a plurality of risk determination items are provided, and input parameters for each risk determination item Among them, there is a pattern in which a decision is made with a judgment formula that satisfies the input parameters only with the recognition items of the first situation recognition part, and a pattern that satisfies the input parameters without using the recognition items of the second situation recognition part depending on the risk judgment item. If not, the recognition items of the second situation recognition unit are additionally used for determination, and if the risk event is found in the determination result, advice for resolving the risk event is given, and at least the vehicle is driven. It is characterized by notifying the driver to do so.

A drive recorder according to one aspect of the present disclosure is mounted on a vehicle, captures at least the surrounding environment including the front of the vehicle, and records the captured images while rewriting the oldest images within a predetermined capacity range. In addition, it has a main control unit that, when an emergency is detected, saves images for a predetermined period before and after the emergency, and the above-described driving support control device.

A driving assistance control program according to one aspect of the present disclosure is characterized by causing a computer to operate as each part of the driving assistance control device described above.

According to the present disclosure, necessary and sufficient driving operation information and information obtained by monitoring the surroundings of the vehicle are acquired and analyzed for each of various scenes during driving of the vehicle, so that the driving operation of the individual driver can be performed. can provide good advice.

The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description with reference to the accompanying drawings. The drawing is
FIG. 1 is a schematic diagram of a driving support system that supports driving in automatic driving of a vehicle according to the first embodiment, FIG. 2 is a functional block diagram of a driving assistance device in the drive recorder according to the first embodiment, mainly showing driving assistance control classified by function; FIG. 3 is a functional block diagram showing the detailed configuration of the situation recognition unit according to the first embodiment; FIG. 4 is a table diagram in which items processed by the action-based scoring processing unit according to the first embodiment are classified; FIG. 5 is a table diagram in which items processed by the location-specific scoring processing unit according to the first embodiment are classified; 6A is a flowchart showing a driving support control analysis routine in the driving support system according to the first embodiment, FIG. 6B is a flowchart showing a driving support control notification routine in the driving support system according to the first embodiment; FIG. 7 is a time-CPU resource characteristic diagram of the drive recorder according to the first embodiment, FIG. 8 is a functional block diagram showing the detailed configuration of the situation recognition unit according to the modification of the first embodiment (addition of CAN information); FIG. 9 is a functional block diagram of a driving assistance device in the drive recorder according to the second embodiment, mainly showing driving assistance control classified by function; FIG. 10 is a flowchart showing a driving support control analysis routine in the driving support system according to the second embodiment; FIG. 11 is a functional block diagram of a driving assistance device in a drive recorder according to a third embodiment, in which mainly driving assistance control is categorized by function; FIG. 12 is a flowchart showing a driving support control analysis routine in the driving support system according to the third embodiment, FIG. 13 is a functional block diagram of a driving assistance device in a drive recorder according to a fourth embodiment, in which mainly driving assistance control is categorized by function; FIG. 14 is a flowchart showing a driving support control analysis routine in the driving support system according to the fourth embodiment, FIG. 15 is a functional block diagram of a driving assistance device in a drive recorder according to a fifth embodiment, mainly showing driving assistance control classified by function; FIG. 16 is a flowchart showing a driving support control analysis routine in the driving support system according to the fifth embodiment; FIG. 17 is a functional block diagram of a driving assistance device in a drive recorder according to a sixth embodiment, in which mainly driving assistance control is categorized by function; FIG. 18 is a flowchart showing a driving support control analysis routine in the driving support system according to the sixth embodiment; FIG. 19 is a schematic diagram of a driving support system that supports traveling in automatic driving of a vehicle according to the seventh embodiment.

[First embodiment]

FIG. 1 is a plan view of a vehicle 10 to which a driving support system according to the first embodiment is applied.

A vehicle control device 12 and a drive recorder 14 are mounted on the vehicle 10 . The drive recorder 14 has the original functions of the drive recorder 14 (monitoring by photographing the exterior and interior of the vehicle, and the function of storing images in an emergency), as well as the driving assistance device 14A according to the first embodiment (see FIG. 1). (represented by a dotted line frame). The driving assistance device 14A includes, for example, a CPU (Central Processing Unit) and a rewritable nonvolatile memory. The nonvolatile memory stores a program indicating driving support control, which will be described later, and the CPU reads and executes the program.

The vehicle control device 12 executes control including the drive system (engine control, etc.) and the electrical system when the vehicle 10 is running.

The drive recorder 14 includes a gyro sensor (Gyro sensor) 16 (indicated as "Gyro" in FIG. 1), an acceleration sensor (G sensor) 18 (indicated as "G" in FIG. 1), and a GPS receiver 20 ( In FIG. 1, "GPS") is connected.

The gyro sensor 16 detects azimuth information in the running direction of the vehicle 10 , the acceleration sensor 18 detects acceleration and deceleration of the vehicle 10 , and the GPS receiver 20 detects position information of the vehicle 10 .

A radar group 22 including a plurality of millimeter wave radars and LIDAR is also connected to the vehicle control device 12 .

The radar group 22 detects obstacles and the like ahead of the vehicle 10 .

The vehicle control device 12 uses the received information to execute control including the drive system and the electrical system, or to notify the driver 24 who is driving of the position information, the travel route to the destination, and the like. Note that FIG. 1 shows the driver 24 getting off the vehicle.

The drive recorder 14 includes a group of cameras that capture the surroundings of the vehicle 10 (a front monitoring camera 26A and a rear monitoring camera 26B are shown in FIG. 1 as an example). The drive recorder 14 of the first embodiment also includes a vehicle interior monitoring camera 26C that captures the interior of the vehicle 10 (hereinafter referred to as the front monitoring camera 26A, the rear monitoring camera 26B, and the vehicle interior monitoring camera 26C). When collectively referred to as "camera group 26"). Note that the camera group 26 may include a right monitoring camera 26</b>D that captures the right side of the vehicle 10 and a left monitoring camera 26</b>E that captures the left side of the vehicle 10 .

The drive recorder 14 is equipped with a driving support device 14A according to the first embodiment. In FIG. 1, the inside of the drive recorder 14 is indicated by a dotted line. The description of the original function of the recorder 14 and the description of the function of the driving support device 14A are used separately.

FIG. 2 is a functional block diagram of the driving assistance device 14A in the drive recorder 14, which mainly shows driving assistance control classified by function. Note that each block does not limit the hardware configuration of the driving support device 14A. If necessary, some or all of the blocks may be operated by a microcomputer as a driving support program.

As shown in FIG. 2 , the drive recorder 14 has a drive recorder main control section 30 . A camera group 26 (front monitoring camera 26A, rear monitoring camera 26B, and vehicle interior monitoring camera 26C) is connected to the drive recorder main control unit 30, and the camera group continuously captures images at least during driving. .

(Original function of the drive recorder 14)

In the drive recorder main control unit 30, as an original function of the drive recorder 14, the images captured by the camera group 26 are rewritten sequentially from the oldest image within a predetermined capacity (for example, about one hour). I'm trying In other words, the camera group 26 always shoots, and records while shifting the predetermined period.

Here, an emergency time (for example, during sudden deceleration such as sudden braking) is detected (or a signal is received from the vehicle control device 12), and images of a predetermined period (for example, 15 minutes before and after) before and after the emergency time are captured. save. A through image (image being recorded) can be confirmed by the driver 24 through the monitor unit 32 .

Images before and after the emergency period can be applied, for example, to analyze the factors causing the emergency. The monitor unit 32 can also be used to reproduce recorded images.

(driving support function)

Here, the drive recorder 14 of the first embodiment has a role as a driving support device 14A. The driving support device 14A analyzes the driving situation of the driver 24 based on information from the gyro sensor 16, the acceleration sensor 18, the GPS receiver 20, and the camera group 26, and detects dangerous behavior unsuitable for driving (hereinafter referred to as risk event) is determined, and advice for reducing the risk event is notified for the next driving. Information may be acquired from the radar group 22 connected to the vehicle control device 12 .

The driving support device 14A includes a sensor information acquisition unit 34 and acquires Gyro information (direction information), G information (acceleration/deceleration information), GPS information (position information), and radar group analysis information (obstacle information). .

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.

The situation recognition unit 36 is connected to the drive recorder main control unit 30. The situation recognizing unit 36 acquires shooting information from the camera group 26 that is used by the drive recorder main control unit 30 .

As a result, the situation recognition unit 36 can collect the travel history, behavior, and situations (image information) of the vehicle 10 outside and inside the vehicle when the driver 24 is driving, and analyze the situation during driving. , can be recognized.

(Detailed configuration of situation recognition unit 36)

FIG. 3 is a functional block diagram showing the detailed configuration of the situation recognition unit 36. As shown in FIG.

The situation recognition unit 36 includes a travel point analysis unit 36A, a behavior analysis unit 36B, a surrounding environment recognition unit 36C, and a driver situation recognition unit 36D.

The travel point analysis unit 36A acquires GPS information from the sensor information acquisition unit 34 and analyzes the travel point of the vehicle 10, such as an intersection, parking lot, indoors, narrow road, or the like.

The behavior analysis unit 36B acquires G information (acceleration information) and Gyro information (azimuth information) from the sensor information acquisition unit 34, and analyzes the behavior of the vehicle 10, for example, turning right or left, starting, stopping, vehicle speed, steering angle, etc. do.

The surrounding environment recognition unit 36C acquires vehicle exterior image information from the drive recorder main control unit 30 and, if necessary, obstacle information from the sensor information acquisition unit 34. , the positions and movements of the preceding and oncoming vehicles, the white and yellow lines on the roadway, and the distance between vehicles.

The driver situation recognition unit 36D acquires vehicle interior image information from the drive recorder main control unit 30, and recognizes the driving posture of the driver 24 who drives the vehicle 10, such as line of sight, face direction, degree of eyes open/closed, skeleton, possession object. Analyze the state of things.

The situation recognition unit 36 sends information about the travel point of the vehicle 10 analyzed by the travel point analysis unit 36A and the behavior of the vehicle 10 analyzed by the behavior analysis unit 36B to the risk event processing control unit 38 (essential information sending).

In response to a request from the risk event processing control unit 38, the situation recognition unit 36 also detects 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. to the risk event processing control unit 38 (transmission of arbitrary information).

As shown in FIG. 2, the risk event processing control unit 38 includes a risk event determination unit 40. The risk event determination unit 40 receives essential information sent from the situation recognition unit 36 such as the travel location of the vehicle 10 and the behavior of the vehicle 10, and optional information such as the surrounding environment of the vehicle 10 and the driver 24 of each of the driving postures is aggregated.

The risk event determination unit 40 has the role of determining whether or not there is a risk while driving the vehicle 10 .

The risk during driving is, for example, the degree of risk of a situation that may hinder safe driving in the behavior pattern determined by checking with the Road Traffic Act, etc., and the location pattern determined by the driving point and driving state of the vehicle 10. It is the degree, and in the first embodiment, it is quantified (scoring).

Here, the risk event determination unit 40 determines whether or not there is a risk in two steps.

In the risk event determination unit 40, based on the essential information (driving point of the vehicle 10 and the behavior of the vehicle 10) and optional information (surrounding environment of the vehicle 10, driving posture of the driver 24), the risk of items that can be assumed. Determine the presence or absence of Items that can be assumed may be extracted from, for example, pre-registered risks that have occurred in the past. The number is not limited. Judgment items are judged by a scene search formula and a judgment formula, respectively.

Scene search formulas include search conditions based on points such as intersections without traffic lights, intersections with traffic lights, parking lots, etc., search conditions based on behavior such as turning right, turning left, going straight, stopping, vehicles in front, pedestrians on the left shoulder, and vehicles stopped at intersections. There are search conditions based on the surrounding environment, such as a bicycle, and search conditions based on the driver's state, such as the driver's line of sight, drowsiness, and smartphone calls. For the scenes that match the scene search formula, the decision formula is used to determine whether or not there is a risk.

As a judgment formula, when judging only sudden braking (specifically, whether the acceleration exceeds a predetermined value (for example, 0.35 G)), when the distance to the preceding vehicle is too small (specifically, , inter-vehicle distance<1.5×(vehicle speed) ² /9.8), and so on.

The vehicle speed can be calculated using the integrated value of the G sensor information (corresponding to the first recognition situation), and the distance to the preceding vehicle is the size of the preceding vehicle recognized from the image taken by the forward monitoring camera 26A. , can be calculated from the hardware parameters of the camera group 26 (corresponding to the second recognition situation).

In the first stage of determination by the risk event determination unit 40, the presence or absence of a conceivable item of risk is determined based on the essential information (the travel location of the vehicle 10 and the behavior of the vehicle 10).

As the scene search formula in the first stage, there are search conditions based on points such as intersections without traffic lights, intersections with traffic lights, etc., and search conditions based on behavior such as turning right, turning left, going straight, and stopping. .

As the first-stage judgment formula, when judging only sudden braking (specifically, whether the acceleration exceeds a predetermined value (for example, 0.35 G)), non-stop at the stop place (specifically, , when passing through an intersection with a stop sign without including the vehicle speed = 0 km/h), and the like.

The vehicle speed can be calculated using the integrated value of the G sensor information (corresponding to the first recognition situation), and the distance to the preceding vehicle is the size of the preceding vehicle recognized from the image taken by the forward monitoring camera 26A. , can be calculated from the hardware parameters of the camera group 26 (corresponding to the second recognition situation).

Here, there is no problem if the presence or absence of risk can be determined with only the required information, but it may be difficult to determine the risk due to lack of information. Therefore, if the information is insufficient, the drive recorder main control section 30 is requested to transmit the information from the camera group 26 to the situation recognition section 36 via the image request section 42 .

In the situation recognition unit 36, by acquiring information from the camera group 26, the surrounding environment of the vehicle 10 is sent from the surrounding environment recognition unit 36C (see FIG. 2) to the risk event determination unit 40 as arbitrary information, and the driver The driving posture of the driver 24 is sent to the risk event determination section 40 from the situation recognition section 36D (see FIG. 2).

In the second stage determination in the risk event determination unit 40, based on the essential information (travel location of the vehicle 10 and the behavior of the vehicle 10) and optional information (surrounding environment of the vehicle 10, driving posture of the driver 24), Determine the presence or absence of risks for items that can be assumed.

With the scene search formula, search for [place search] intersection without traffic lights, [behavior] go straight, [surrounding environment] with preceding vehicle, [driver] look ahead. Next, in order to check whether or not the following distance is insufficient in the relevant scene, it is determined whether or not the condition of following distance<1.5×(vehicle speed) ² /9.8 is established. . The inter-vehicle distance is calculated based on the size of the preceding vehicle obtained from the image of the optional information and the hardware parameters. Based on the integral value of the G value obtained from the essential information, the own vehicle speed is calculated. If these values are entered into the determination formula and satisfy the risk, it is determined that there is no risk if they are not satisfied.

That is, the presence or absence of risk is determined based on sensor information, which has a relatively small amount of information and does not take much time to analyze, rather than using image information, which has a relatively large amount of information and takes a long time to analyze, from the beginning. Therefore, the function of the driving support device 14A can be realized without impairing the original function of the drive recorder 14. FIG.

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 provides the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46 with each item. The determination result of the presence or absence of risk is sent out.

It should be noted that it is not necessary to send the determination result of the presence or absence of risk for all items to the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, and it is also possible to select based on the concept of behavior and location. is. For example, out of 160 items in total, 130 items may be sent to each of the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46 .

FIG. 4 is a table diagram in which the items processed by the action-based scoring processing unit 44 are classified. As shown in FIG. 4, the behavioral items are classified into large items, medium items, and small items.

Major items include, for example, classification according to the Road Traffic Act, classification according to safe driving obligations, classification according to the driver's condition, etc.

Medium items include, for example, classifications related to road signs, classifications related to driver behavior, classifications related to driver's physical condition, etc.

Subcategories include classification by road sign, classification by driver behavior, classification by driver's physical condition, etc.

IDs are assigned in advance to identify each of the major, medium, and minor items, and each ID is aggregated into the minor item ID. By looking at this minor item ID, it is possible to identify the major item type, the medium item type, and the minor item type.

The action-based scoring processing unit 44 scores each sub-item based on a predetermined calculation formula, and evaluates with the total value. For example, in the behavior, a calculation that gives 50 points out of 100 to the driver 24 who drives on average, deducts points if there is risk, and adds points if the risk-free state continues. You can build expressions.

FIG. 5 is a table diagram in which the items processed by the location-specific scoring processing unit 46 are classified. As shown in FIG. 5, items for each location are classified into vehicle location conditions and vehicle running conditions, and a scene is set by combining each.

Vehicle point conditions include, for example, the presence or absence of facilities such as traffic lights, the shape of roads, and specific locations.

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

As for the combination of the vehicle point situation and the vehicle traveling state, there are scenes of the number of types of vehicle point situation times the number of types of vehicle traveling state, and an ID for identifying each is assigned. Identifiable.

The location-specific scoring processing unit 46 scores each scene based on a predetermined calculation formula, and evaluates with the total value. For example, a calculation that gives 50 points out of 100 to the driver 24 who drives on average in the place, points are deducted if there is risk, and points are added if the risk-free state continues. You can build expressions.

As shown in FIG. 2, the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46 are each connected to a priority determination unit 48.

The priority determining unit 48 extracts risks to be notified to the driver 24 based on the scoring results of the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, and prioritizes the extracted risks. set the degree. Risks are premised to be notified to the driver 24 , but if notification is restricted, it is necessary to notify the risks in descending order of priority.

The advice notification unit 50 executes specific risk consulting based on the received risks, and notifies the mobile terminal device 24A or the like possessed by the driver 24. In addition, it is possible to notify the mobile terminal device 24A of the notification destination via the mobile terminal device 24A using a web application or a native application. In addition, not only the portable terminal device 24A but also the drive recorder 14 or the voice notification function of the vehicle 10 may be used to notify the driver 24, or via the cockpit or display of the vehicle 10 to the driver 24. may notify you.

The operation of the first embodiment will be described below according to the flowchart of FIG.

6A is a flowchart showing a driving assistance control analysis routine in the driving assistance system according to the first embodiment, and FIG. 6B is a flowchart showing a driving assistance control notification routine in the driving assistance system according to the first embodiment. be.

First, the driving support control analysis routine will be described according to FIG. 6A.

At step 100, it is determined whether or not it is time to analyze the information. Information may be analyzed periodically or irregularly.

When executing image information processing, it is preferable to set predetermined conditions, for example. The predetermined condition is set based on the availability of hardware (CPU resources) installed in the drive recorder 14, as shown in FIG.

In FIG. 7, the horizontal axis is time and the vertical axis is CPU resource (usage rate), and the usage rate at which the function locks is set to 95%. In this state, the CPU resource fluctuates over time and is driven while maintaining 5% or less.

Here, in the driving assistance device 14A according to the first embodiment, the time period for executing image processing is set to be equal to or less than a predetermined threshold value (90% in FIG. 7). That is, the image processing does not have to be executed in real time, and it is sufficient that the image processing is executed by the time of notifying the driver 24 and appropriate advice is generated. The timing of notification may be until getting off the vehicle for the current driving or until getting off the vehicle for the next driving. The distance may be detected by the drive recorder 14 , or may be acquired from the short-range communication function between the mobile terminal device 24</b>A possessed by the driver 24 and the drive recorder 14 .

It should be noted that the threshold is not limited to 90%, and may be determined as long as it does not interfere with the original function of the drive recorder 14.

If a negative determination is made in step 100 of FIG. 6A, the process proceeds to step 126 to determine whether or not to continue the analysis. If the determination in step 126 is affirmative, the process returns to step 100 .

If an affirmative determination is made in step 100, the process moves to step 102 to acquire various sensor information, then moves to step 104 to analyze the travel point from the GPS information, and moves to step 106.

At step 106, vehicle behavior is analyzed from GPS information, G information and Gyro information, and the process proceeds to step 108.

In step 108, the risk event is judged by the first stage, that is, the essential information, and the process proceeds to step 110 to judge whether or not the input information to the risk event judgment formula is sufficient.

If a negative determination is made in step 110, or the input information to the risk event determination formula is insufficient, the process proceeds from step 110 to step 112 to request image information outside and inside the vehicle.

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

In step 116, the second step, that is, the risk event including optional information in essential information is determined, and the process proceeds to step 118. Also, if the determination in step 110 is affirmative, it is determined that the second stage of risk determination in consideration of arbitrary information is unnecessary, and the process proceeds to step 118 .

In step 118, action-based scoring processing is executed for each determined risk event (see FIG. 4), and then the process proceeds to step 120, where location-based scoring processing is performed for each determined risk event (see FIG. 4). 5), and go to step 122. Although steps 118 and 120 are processed in this order, the order may be step 120→step 118, or step 118 and step 120 may be processed simultaneously (parallel processing).

In step 122, the priority of risk event notification is determined based on the scoring process results, and the process proceeds to step 124. At step 124 , result storage processing is executed, and the process proceeds to step 126 .

At step 126, it is determined whether or not to continue the analysis, and if the determination is affirmative, the process returns to step 100 as described above, and if the determination is negative, this routine ends.

Next, the driving support control notification routine will be described according to FIG. 6B.

At step 150, it is determined whether or not it is time to notify the risk event. If the determination at step 150 is negative, the routine ends. Also, if the determination in step 150 is affirmative, the process proceeds to step 152 .

In the first embodiment, the notification is made when the ignition key is turned off, and as shown in FIG. 1, the notification is made when the driver 24 gets off the vehicle 10 .

Note that the notification timing is not limited to when the vehicle 10 gets off, and may be, for example, when the ignition key is turned on next time. In addition, for example, using the short-range communication function, between the key or the mobile terminal device 24A possessed by the driver 24 and the drive recorder 14, the driver 24 temporarily goes out of the predetermined range and then returns to the predetermined range. Other notification times, such as when to notify, may be used. Also, even if there is no driver around the vehicle, the notification may be sent via a web application or a native application at any timing.

At step 152, the risk event stored at step 124 in FIG.

At step 156, archive processing of the notified risk event is executed, and this routine ends. It should be noted that it is not necessary to keep all the risk events as a history, and they may be selected.

(Modification of the first embodiment)

Incidentally, in the first embodiment, as shown in FIG. However, as shown in FIG. 8, a vehicle operation mode recognition unit 36E that recognizes the vehicle operation mode based on the CAN data of the vehicle 10 may be added. Thereby, the behavior of the host vehicle (vehicle 10) can be recognized in more detail.

(Example "Example 1" of the first embodiment)

　Perform the risk event processing according to the following procedures (a) to (c).

(a) Based on the GPS information and acceleration information, the own vehicle (vehicle 10) behavior and point information are derived. For example, turn left at an intersection with a signal.

(b) Acquire the image processing result.

· Analyze the image information from the camera group 26 (outside the vehicle) and estimate the surrounding situation. For example, five seconds before turning left at a green light, a bicycle was on the left side of the own vehicle (vehicle 10).

· Analyze the image information from the camera group 26 (inside the vehicle) and estimate the state of the driver 24 . For example, safety confirmation is not performed within 5 seconds before turning left.

(c) Using the data (a) and (b) only for an arbitrary amount of time before and after the left turn scene, determine the risk event.

　Case 1: When the brake is suddenly applied when turning left in (b)

This is a risky scene in which the driver stepped on the brakes suddenly without noticing it, which is equivalent to unsuitable safety operation.

　Case 2: When the brake is not operated at all when turning left in (b)

It's a risky scene where you pass by without noticing it, and it's equivalent to interfering with someone crossing the street.

　Case 3: Give specific advice based on the judgment result of (c).

In the case of Case 1, "Always check safety before entering the intersection and turn left. ', and in Case 2, 'Be sure to slow down to a stopable speed and turn left after confirming safety. ’ is notified.

(Example "Example 2" of the first embodiment)

After analyzing the location x own vehicle (vehicle 10) behavior, additional images are analyzed only at the timing when analysis of risk scenes requiring image analysis is necessary (using arbitrary information).

An example that does not require image analysis (an example that can be analyzed with only essential information) is the event of excessive speed while going straight on a main road.

In this case, the location is a main road, the behavior of the own vehicle (vehicle 10) is to go straight, the speed of the own vehicle (vehicle 10) is compared with the upper speed limit of the main road, and it is detected whether the vehicle is over speeding. becomes unnecessary.

According to Example 2 of the first embodiment, since the timestamp for image analysis is specified, it is possible to reduce CPU resources required for image analysis.

(Example "Example 3" of the first embodiment)

By classifying the detected risk events by location and behavior and performing scoring, the scene with the lowest score is selected, and the priority of risk events that should be given priority advice is calculated.

According to Example 3 of the first embodiment, the problematic driving scenes are specified among the many risky driving and notified with priority, so that the problematic driving scenes can be quickly corrected. becomes possible.

[Second embodiment]

A second embodiment of the present disclosure will be described below with reference to FIGS. 9 and 10. FIG. The same reference numerals are given to the same components as those of the first embodiment, and the description of the configuration is omitted.

A feature of the second embodiment is that the determination result of the risk event determination unit 40 deviates from the presumed determination, or does not correspond to any of the preset risk event items. A function is added to edit (add, delete, change, etc.) items such as determination thresholds and risk event determination when new risks are identified.

FIG. 9 is a functional block diagram of a driving assistance device 14A that mainly classifies driving assistance control by function in the drive recorder 14 according to the second embodiment of the present disclosure.

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

The risk event determination unit 40 sends information about the determination result to this UI52. The UI 52 analyzes the determination result and determines whether or not the threshold value adjustment and the determination level need to be adjusted.

When the operator determines that threshold adjustment is necessary, the operator operates the UI 52 to send threshold adjustment information to the threshold adjustment unit 54 . The threshold adjusting unit 54 is connected to the situation recognizing unit 36 and adjusts the threshold for comparison with the sensor information executed by the situation recognizing unit 36 .

Also, when the operator determines that the determination level needs to be adjusted, the operator operates the UI 52 to send determination level adjustment information to the determination level adjustment unit 56 . The determination level adjustment unit 56 is connected to the risk event determination unit 40 and adjusts the determination criteria and the like for risk event determination performed by the risk event determination unit 40 .

The operation of the second embodiment will be described below.

FIG. 10 is a flowchart showing a driving support control analysis routine in the driving support system according to the second embodiment. The same step numbers are given to the same steps as those in the first embodiment (see FIG. 6A), and the description of the processing is omitted.

After it is determined in step 110 that the input information to the risk event determination formula is sufficient, or after the second stage of risk event determination is executed in step 116, in step 128, the determination result is Send to UI52.

In the next step 130, the UI 52 side determines whether adjustment of the judgment result (threshold adjustment, judgment level adjustment) is necessary. If it is judged at step 130 that adjustment is necessary, the process moves to step 132 to execute the judgment level adjustment process and the threshold value adjustment process, returns to step 108, and repeats the above steps.

Also, if a negative determination is made in step 130, it is determined that adjustment of the determination result is unnecessary, and the process proceeds to step 118.

According to the second embodiment, for example, when general traffic manners change due to changes in laws and regulations or social conditions, by editing the risk event determination threshold and determination level adjustment, a new It is possible to continuously provide high-level advice without having to develop it in detail.

(Example "Example 4" of the second embodiment)

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

If there is an error in the determination content, the threshold value and determination level are adjusted according to the following cases.

　Case 1: When it is determined that there is no risk

Although the determination target of the risk event matches (combination of location, own vehicle (vehicle 10) behavior, etc.), if the determination threshold does not match the actual degree of risk, the determination threshold is adjusted (for example, , following distance and relative speed thresholds, etc.).

　Case 2: When the judgment target of the risk event is incorrect and it is determined that it should be changed to another pre-designed rule

For example, if there is an error in the detection result of the location, etc., which is subject to risk event determination, the following processes 1 and 2 are executed.

· Process 1 Correct the detection results such as the location so that the judgment result of the corresponding risk event is output.

• Processing 2 Correct the decision threshold value group so that the output of the situation recognition unit 36 matches the correction result of the processing 1.

　Case 3: When the risk event determination target is incorrect and none of the pre-designed rules apply

Add new risk event judgment rules.

The above response may be performed manually by the driver 24, processed according to a predetermined program, or machine-learned based on a vast amount of past history information (so-called big data) using AI. can be judged by

[Third embodiment]

A third embodiment of the present disclosure will be described below with reference to FIGS. 11 and 12. FIG. It should be noted that the same components as those in the first embodiment and the second embodiment are denoted by the same reference numerals, and the description of the configuration is omitted.

The feature of the third embodiment is that the determination result and determination accuracy in the risk event determination unit 40 deviate from the determination assumed in advance, or the risk event items set in advance, etc. When a new risk that does not correspond to the above is identified, a function is added to edit (add, delete, change, etc.) items such as the judgment threshold value and risk event judgment items.

FIG. 11 is a functional block diagram of a driving assistance device 14A that mainly classifies driving assistance control by function in the drive recorder 14 according to the second embodiment of the present disclosure.

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

The risk event determination unit 40 sends information regarding determination results and determination accuracy to this UI 52 . The UI 52 analyzes the determination result and determination accuracy, and determines whether or not threshold adjustment is necessary, and whether or not the determination level needs to be adjusted.

When the operator determines that threshold adjustment is necessary, the operator operates the UI 52 to send threshold adjustment information to the threshold adjustment unit 54 . The threshold adjusting unit 54 is connected to the situation recognizing unit 36 and adjusts the threshold for comparison with the sensor information executed by the situation recognizing unit 36 .

Also, when the operator determines that the determination level needs to be adjusted, the operator operates the UI 52 to send determination level adjustment information to the determination level adjustment unit 56 . The determination level adjustment unit 56 is connected to the risk event determination unit 40 and adjusts the determination criteria and the like for risk event determination performed by the risk event determination unit 40 .

The operation of the third embodiment will be described below.

FIG. 12 is a flowchart showing a driving support control analysis routine in the driving support system according to the third embodiment. The same step numbers are given to the same steps as those in the first embodiment (see FIG. 6A), and the description of the processing is omitted.

After it is determined in step 110 that the input information to the risk event determination formula is sufficient, or after the second step of risk event determination is executed in step 116, in step 128, the determination result and Send the determination accuracy to the UI 52 .

In the next step 130, the UI 52 side determines whether or not adjustment of the judgment result and judgment accuracy (threshold adjustment, judgment level adjustment) is necessary. If it is judged at step 130 that adjustment is necessary, the process moves to step 132 to execute the judgment level adjustment process and the threshold value adjustment process, returns to step 108, and repeats the above steps.

Also, if a negative determination is made in step 130, it is determined that adjustment of the determination result and determination accuracy is unnecessary, and the process proceeds to step 118.

According to the third embodiment, for example, when general traffic manners change due to changes in laws and regulations or social conditions, by editing the risk event determination threshold value and determination level adjustment, a new It is possible to continuously provide high-level advice without having to develop it in detail.

In addition, according to the third embodiment, by filtering and sorting the output according to the judgment accuracy of the risk event judgment result, when confirming the event judgment result on the UI 52, from those with low judgment accuracy Confirmation can be performed efficiently by confirming in order.

(Example "Example 5" of the third embodiment)

In addition to the embodiment 4 of the form of the second embodiment, the determination accuracy is added to the output of the risk event determination unit 40 and presented to the operator via the UI 52.

If there is an error in the content of the judgment, the following measures will be taken in addition to Example 3.

　Case 1: About providing advice

For risk events with judgment accuracy below an arbitrary value, advice will not be provided or the priority of the order of provision will be lowered.

　Case 2: Display of UI52

For risk events with a judgment accuracy greater than an arbitrary value, they are preferentially displayed on the UI52.

[Fourth embodiment]

The fourth embodiment of the present disclosure will be described below with reference to FIGS. 13 and 14. FIG. The same reference numerals are given to the same components as those of the first embodiment, and the description of the configuration is omitted.

Here, in the first embodiment, the risk event determination unit 40 is provided with the image request unit 42, and in the determination (first stage) based on the essential information of the risk event determination unit 40, it is determined that the image information is necessary. In this case, image information (arbitrary information) is requested from the drive recorder main control unit 30, and the image information is taken into consideration in the determination (second stage).

On the other hand, in the fourth embodiment, in the determination by the risk event determination unit 40, a risk event is determined using sensor information and image information from the beginning without distinguishing between essential information and optional information. be.

FIG. 13 is a functional block diagram of a driving assistance device 14A that mainly classifies driving assistance control by function in the drive recorder 14 according to the fourth embodiment of the present disclosure.

The situation recognition unit 36 sends information about the travel point of the vehicle 10 analyzed by the travel point analysis unit 36A and the behavior of the vehicle 10 analyzed by the behavior analysis unit 36B to the risk event processing control unit 38.

In addition, the situation recognition unit 36 acquires information from the camera group 26, sends the surrounding environment of the vehicle 10 from the surrounding environment recognition unit 36C (see FIG. 2) to the risk event determination unit 40, and recognizes the driver situation. The driver behavior of the driver 24 (inattentive glance, flickering glance, careless state, smartphone operation, posture collapse, safety unconfirmation, etc.) is sent to the risk event determination unit 40 from the unit 36D (see FIG. 2).

The risk event determination unit 40 determines the presence or absence of conceivable items of risk based on the travel point of the vehicle 10, the behavior of the vehicle 10, the surrounding environment of the vehicle 10, and the driving posture of the driver 24.

The operation of the fourth embodiment will be described below.

FIG. 14 is a flowchart showing a driving support control analysis routine in the driving support system according to the fourth embodiment. The same step numbers are given to the same steps as those in the first embodiment (see FIG. 6A), and the description of the processing is omitted.

In step 106, vehicle behavior is analyzed from GPS information, G information and Gyro information, and the process proceeds to step 114.

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

In step 116, a risk event is determined based on the travel point of the vehicle 10, the behavior of the vehicle 10, the surrounding environment of the vehicle 10, and the driving posture of the driver 24, and the process proceeds to step 118.

According to the fourth embodiment, it is possible to determine risk events according to various scenes acquired while the vehicle 10 is running, and provide accurate advice to eliminate the risk events.

In addition, according to the fourth embodiment, it is possible to quickly correct problematic driving scenes by identifying and giving priority to problematic driving scenes among many risky driving situations. becomes.

[Fifth embodiment]

The fifth embodiment of the present disclosure will be described below with reference to FIGS. 15 and 16. FIG. The same reference numerals are given to the same components as those of the first embodiment, and the description of the configuration is omitted.

Here, in the first embodiment, the risk event determination unit 40 includes the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, and the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, the result of determining the presence or absence of risk for each item is sent, and the behavior-specific scoring processing unit 44 scores each sub-item based on a predetermined calculation formula, and evaluates with the total value. , the location-specific scoring processing unit 46 scores each scene based on a predetermined calculation formula, and evaluates the score based on the total value.

On the other hand, in the fifth embodiment, in the determination by the risk event determination unit 40, the results determined by the risk event determination unit 40 are not distinguished or prioritized, and are based on so-called raw data. , to determine risk events.

FIG. 15 is a functional block diagram of a driving assistance device 14A in which driving assistance control is mainly classified by function in the drive recorder 14 according to the fifth embodiment of the present disclosure.

The risk event determination unit 40 determines whether or not there is a risk in two stages.

In the first stage of determination by the risk event determination unit 40, the presence or absence of a conceivable item of risk is determined based on the essential information (the travel location of the vehicle 10 and the behavior of the vehicle 10).

Here, there is no problem if the presence or absence of risk can be determined with only the required information, but it may be difficult to determine the risk due to lack of information.

Therefore, if the information is insufficient, the drive recorder main control section 30 is requested to send the information from the camera group 26 to the situation recognition section 36 via the image request section 42 .

In the situation recognition unit 36, by acquiring information from the camera group 26, the surrounding environment of the vehicle 10 is sent from the surrounding environment recognition unit 36C (see FIG. 2) to the risk event determination unit 40 as arbitrary information, and the driver The situation recognition unit 36D (see FIG. 2) sends the driver behavior of the driver 24 (inattentive glance, flickering glance, careless state, smartphone operation, posture collapse, unconfirmed safety, etc.) to the risk event determination unit 40.

In the second stage determination in the risk event determination unit 40, based on the essential information (travel location of the vehicle 10 and the behavior of the vehicle 10) and optional information (surrounding environment of the vehicle 10, driving posture of the driver 24), Determine the presence or absence of risks for items that can be assumed.

That is, the presence or absence of risk is determined based on sensor information, which has a relatively small amount of information and does not take much time to analyze, rather than using image information, which has a relatively large amount of information and takes a long time to analyze, from the beginning. Therefore, the function of the driving support device 14A can be realized without impairing the original function of the drive recorder 14. FIG.

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

The advice notification unit 50 executes specific risk consulting based on the received risks, and notifies the mobile terminal device 24A or the like possessed by the driver 24.

The operation of the fifth embodiment will be described below.

FIG. 16 is a flow chart showing a driving support control analysis routine in the driving support system according to the fifth embodiment. The same step numbers are given to the same steps as those in the first embodiment (see FIG. 6A), and the description of the processing is omitted.

If a negative determination is made in step 110, or the input information to the risk event determination formula is insufficient, the process proceeds from step 110 to step 112 to request image information outside and inside the vehicle.

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

In step 116, the second step, that is, the risk event including optional information in essential information is determined, and the process proceeds to step 124. Also, if the determination in step 110 is affirmative, it is determined that the second stage of risk determination in consideration of arbitrary information is unnecessary, and the process proceeds to step 124 .

In step 124, the result storage process is executed, and the process moves to step 126.

At step 126, it is determined whether or not to continue the analysis, and if the determination is affirmative, the process returns to step 100 as described above, and if the determination is negative, this routine ends.

According to the fifth embodiment, it is possible to determine risk events according to various scenes acquired while the vehicle 10 is running, and provide accurate advice to eliminate the risk events.

Also, according to the fifth embodiment, since the time stamp for image analysis is specified, it is possible to reduce CPU resources required for image analysis.

[Sixth embodiment]

The sixth embodiment of the present disclosure will be described below with reference to FIGS. 17 and 18. FIG. The same reference numerals are given to the same components as those of the first embodiment, and the description of the configuration is omitted.

(Difference 1 from the first embodiment)

Here, in the first embodiment, the risk event determination unit 40 is provided with the image request unit 42, and in the determination (first stage) based on the essential information of the risk event determination unit 40, it is determined that the image information is necessary. In this case, image information (arbitrary information) is requested from the drive recorder main control unit 30, and the image information is taken into consideration in the determination (second stage).

In contrast, in the sixth embodiment, in the determination by the risk event determination unit 40, a risk event is determined using sensor information and image information from the beginning without distinguishing between essential information and optional information. be.

(Difference 2 from the first embodiment)

In the first embodiment, the risk event determination unit 40 includes a behavior-based scoring processing unit 44 and a location-based scoring processing unit 46. For the behavior-based scoring processing unit 44 and the location-based scoring processing unit 46, Then, the action-specific scoring processing unit 44 scores each sub-item based on a predetermined calculation formula, evaluates the total value, and The scoring processing unit 46 is configured to score each scene based on a predetermined calculation formula and evaluate the total value.

On the other hand, in the sixth embodiment, in the determination by the risk event determination unit 40, the result determined by the risk event determination unit 40 is not distinguished or prioritized, and is based on so-called raw data. , to determine risk events.

FIG. 17 is a functional block diagram of a driving assistance device 14A in which driving assistance control is mainly classified by function in the drive recorder 14 according to the sixth embodiment of the present disclosure.

The situation recognition unit 36 sends information about the travel point of the vehicle 10 analyzed by the travel point analysis unit 36A and the behavior of the vehicle 10 analyzed by the behavior analysis unit 36B to the risk event processing control unit 38.

In addition, the situation recognition unit 36 acquires information from the camera group 26, sends the surrounding environment of the vehicle 10 from the surrounding environment recognition unit 36C (see FIG. 2) to the risk event determination unit 40, and recognizes the driver situation. The driver behavior of the driver 24 (inattentive glance, flickering glance, careless state, smartphone operation, posture collapse, safety unconfirmation, etc.) is sent to the risk event determination unit 40 from the unit 36D (see FIG. 2).

The risk event determination unit 40 determines the presence or absence of conceivable items of risk based on the travel point of the vehicle 10, the behavior of the vehicle 10, the surrounding environment of the vehicle 10, and the driving posture of the driver 24.

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

The advice notification unit 50 executes specific risk consulting based on the received risks, and notifies the mobile terminal device 24A or the like possessed by the driver 24.

The operation of the sixth embodiment will be described below.

FIG. 18 is a flow chart showing a driving support control analysis routine in the driving support system according to the sixth embodiment. The same step numbers are given to the same steps as those in the first embodiment (see FIG. 6A), and the description of the processing is omitted.

In step 106, vehicle behavior is analyzed from GPS information, G information and Gyro information, and the process proceeds to step 114.

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

In step 116, a risk event is determined based on the travel point of the vehicle 10, the behavior of the vehicle 10, the surrounding environment of the vehicle 10, and the driving posture of the driver 24, and the process proceeds to step 124.

In step 124, the result storage process is executed, and the process moves to step 126.

At step 126, it is determined whether or not to continue the analysis, and if the determination is affirmative, the process returns to step 100 as described above, and if the determination is negative, this routine ends.

According to the sixth embodiment, it is possible to determine risk events according to various scenes acquired while the vehicle 10 is running, and provide accurate advice to eliminate the risk events.

Also, in the determination by the risk event determination unit 40, a risk event can be determined from the beginning using sensor information and image information without distinguishing between essential information and optional information.

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

That is, according to the sixth embodiment, the risk event corresponding to the driving scene of the vehicle 10 can be accurately determined with necessary and sufficient information without performing complicated control, thereby simplifying the device configuration. It can be said that it is a useful configuration as a low-priced version accompanying.

[Seventh embodiment]

The seventh embodiment of the present disclosure will be described below with reference to FIG. The same reference numerals are given to the same components as those of the first embodiment, and the description of the configuration is omitted.

As shown in FIG. 19, in the seventh embodiment, a gyro sensor 16 (indicated as "Gyro" in FIG. 19), an acceleration sensor (G sensor) 18 (indicated as "G" in FIG. 19), and A GPS receiver 20 (denoted as “GPS” in FIG. 19) is connected to the vehicle control device 12 .

In the seventh embodiment, information necessary for the travel point analysis unit 36A and the behavior analysis unit 36B, that is, information from the gyro sensor 16, the acceleration sensor 18, and the GPS receiver 20, is obtained from the vehicle control device 12. In this case, obstacle information in front of the vehicle 10 may also be acquired from the vehicle control device 12 as information from the radar group 22 . Especially at night or in rainy weather, the amount of information from the camera group 26 is small, and obstacles that are difficult to recognize can be reliably recognized.

According to the seventh embodiment, when any of the existing sensors (the gyro sensor 16, the acceleration sensor 18, and the GPS receiver 20) is present in the vehicle 10, the drive recorder 14 is provided with this function. Since the necessary sensor information can be acquired from the vehicle control device 12, the configuration can be simplified.

In each embodiment (including modifications) of the present disclosure, the drive recorder 14 is configured to execute all controls (information acquisition, situation recognition, risk determination, etc.), but the gyro sensor 16 and the acceleration sensor 18, GPS receiver 20, camera group 26, and drive recorder main control unit 30 are configured as in-vehicle hardware (drive recorder 14), and output signals from the hardware are transmitted to the cloud, In the above, a process that replaces the risk event determination unit 40, the priority determination unit 48, the advice notification unit 50, and the like may be executed. 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.

Also, in the present embodiment, a mode in which the program is pre-stored (installed) in the non-volatile memory has been described, but the present invention is not limited to this. A program is stored in a non-transitional substantive recording medium, and a method corresponding to the program is executed by executing the program. Programs are stored in non-transitory storage media such as CD-ROM (Compact Disk Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), USB (Universal Serial Bus) memory, semiconductor memory, etc. may be provided in any form. Further, each of the above programs may be downloaded from an external device via a network.

Although the present disclosure has been described with reference to examples, it is understood that the present disclosure is not limited to those examples or structures. The present disclosure also includes various modifications and modifications within the equivalent range. In addition, various combinations and configurations, as well as other combinations and configurations, including single elements, more, or less, are within the scope and spirit of this disclosure.

Claims (9)

1. (36) a first situation recognition unit that acquires vehicle position information and vehicle behavior information as essential information sources and recognizes the essential situation of the vehicle based on the essential information sources;
   a second situation recognition unit that acquires an arbitrary information source based on at least one image information of the surroundings of the vehicle and the inside of the vehicle, and recognizes the driving situation of the vehicle based on the essential information source and the arbitrary information source; , (36, 40, 42)
   a determination unit that analyzes the recognition result of the first situation recognition unit or the recognition result of the second situation recognition unit and determines whether or not there is a risk event that can occur while the vehicle is running; 40)
   (50) a notification unit for notifying at least a driver of the vehicle of advice for resolving the risk event when the determination result of the determination unit indicates that the risk event has occurred;
   A driving support device having
2. The judgment unit has a plurality of risk judgment items, and out of the input parameters of each risk judgment item, only the recognition items of the first situation recognition unit make judgments using a judgment formula that satisfies the input parameters. The driving support according to claim 1, wherein if the input parameters are not satisfied unless the recognition items of the second situation recognition unit are used depending on the risk determination item, the recognition items of the second situation recognition unit are additionally used. Device.
3. The risk events determined by the determination unit are classified so as to overlap at least into behavioral risk events related to violations of the Road Traffic Act and location-based risk events based on scenes determined by driving locations and driving conditions, and 2. Execution of scoring according to the degree of importance for each of the behavioral risk event and the location type risk event, and determining the priority of notification by the notification unit based on the scoring result, or The driving support device according to claim 2.
4. Claims 1 to 1, further comprising a monitoring unit that acquires the determination result of the determination unit, monitors whether the determination result of the determination unit is good or bad, and updates the determination criteria of the determination unit based on the monitoring result. The driving assistance device according to claim 3 .
5. 5. The driving support device according to claim 4, wherein the monitoring unit acquires determination accuracy information from the determination unit and monitors the quality of the determination results in descending order of determination accuracy.
6. The driving support device according to any one of claims 1 to 5, wherein the driving information of the vehicle is added as an information source acquired by the first situation recognition unit.
7. Acquire vehicle position information and vehicle behavior information as essential information sources, and according to the recognition items used for risk event determination by the determination unit,
   a first recognition function for recognizing a driving situation based on the essential information source as a first-stage situation recognition and outputting it to the determination unit;
   If the output of the first stage is insufficient as the recognition items used to determine the risk event, the driving situation is recognized based on the essential information source and the arbitrary information source as the situation recognition of the second stage and sent to the determination unit. a second recognition function that outputs,
   analyzing at least one of the output of the first cognitive function and the output of the second cognitive function,
   A plurality of risk determination items are provided when determining the presence or absence of a risk event that may occur while the vehicle is running,
   Of the input parameters for each risk judgment item, a pattern in which judgment is made with a judgment formula that satisfies the input parameters only with the recognition items of the first situation recognition unit, and depending on the risk judgment item, the recognition items of the second situation recognition unit If the input parameters are not satisfied unless the
   A driving support method for notifying at least a driver driving the vehicle of advice for resolving the risk event when the risk event is found in a determination result.
8. It is mounted on a vehicle, photographs the surrounding environment including at least the front of the vehicle, records the photographed images while rewriting them in order from the oldest image within the range of a predetermined capacity, and when an emergency is detected. , a main control unit that saves images for a predetermined period before and after the emergency;
   A driving support device according to any one of claims 1 to 6;
   Drive recorder with
9. the computer,
   Operate as each part of the driving support control device according to any one of claims 1 to 6,
   Driving assistance control program.

Images