Driver assistance device, driver assistance system, and driver assistance method

Abstract

To provide more effective driving assistance that takes into account not only anticipated risks but also the chain reaction of those risks. [Solution] The driving assistance device according to the embodiment has a controller. The controller estimates a first situation in which a dangerous situation is likely to occur based on the vehicle's driving data. The controller also increases the sensitivity of the detection function for a second situation of the vehicle related to the first situation and notifies the vehicle's driver of the change in sensitivity.

Description

Technical Field

[0001] The disclosed embodiments relate to a driving support device, a driving support system, and a driving support method.

Background Art

[0002] Conventionally, a technique for providing driving support information that supports driving operations for a vehicle driver has been known. For example, Patent Document 1 discloses a technique for warning of approaching a risky location based on information on a location where a dangerous behavior such as a skid has occurred and transmitted from a plurality of vehicles.

[0003] In recent years, the installation of advanced driver assistance systems (ADAS) including ABS (Anti-lock Braking System) and DMS (Driver Monitoring System) in vehicles has become widespread. With driving support functions such as ADAS, a driver can avoid dangers safely even if the driving skill is low.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the above-described conventional technology, there is still room for further improvement in performing more effective driving support considering even the chain of risks for the predicted risks.

[0006] Specifically, using the conventional technology described above, a driver can recognize, for example, approaching a location with a risk of slipping through a warning. However, it is rare for a driver to immediately understand, for example, which driver assistance function might be activated or what precautions they should take while driving, based on that warning.

[0007] Even if a driver is aware that ABS may activate in response to a risk of slipping, a slipping risk may trigger a chain reaction of other risks, such as lane departure. Using the conventional technology described above, it is difficult to provide more effective driving assistance that takes these chain reactions of risks into account.

[0008] One embodiment, made in view of the above, aims to provide a driver assistance device, a driver assistance system, and a driver assistance method that can provide more effective driver assistance in response to foreseeable risks, taking into account even the chain of risks. [Means for solving the problem]

[0009] A driver assistance device according to one embodiment includes a controller. The controller estimates a first situation in which a dangerous situation is likely to occur based on the vehicle's driving data. The controller also increases the sensitivity of the detection function for a second situation of the vehicle related to the first situation and notifies the vehicle's driver of the change in sensitivity. [Effects of the Invention]

[0010] According to one embodiment, the controller increases the sensitivity of detecting a second vehicle situation related to a first situation estimated based on the vehicle's driving data, and notifies the driver of this change in sensitivity. This makes the driver aware that they should pay attention to the second situation that may occur in conjunction with the first situation. It also makes the driver aware that, for example, a driving assistance function related to the second situation may be activated. Furthermore, if the second situation is actually detected, the driver can be made aware of it more quickly. In other words, according to one embodiment, it is possible to provide more effective driving assistance that takes into account the chain of risks in response to predicted risks. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 is a schematic diagram illustrating the driver assistance method according to the embodiment. [Figure 2] Figure 2 shows the relationship between event types and the most likely first situation. [Figure 3] Figure 3 shows an example of sensitivity control information. [Figure 4] Figure 4 shows an example of a notification sent to the driver. [Figure 5] Figure 5 shows an example of the configuration of a driver assistance system according to the embodiment. [Figure 6] Figure 6 shows an example of the configuration of a drive recorder according to the embodiment. [Figure 7] Figure 7 shows an example of the configuration of a center device according to an embodiment. [Figure 8] Figure 8 shows the processing sequence executed by the driver assistance system according to the embodiment. [Modes for carrying out the invention]

[0012] Hereinafter, embodiments of the driver assistance device, driver assistance system, and driver assistance method disclosed in this application will be described in detail with reference to the attached drawings. However, the present invention is not limited to the embodiments described below.

[0013] Also, hereinafter, the driving support system according to the embodiment will be described by taking the driving support system 1 (see FIG. 1) as an example. Further, hereinafter, it is assumed that the driving support device according to the embodiment is the center device 100 (see FIG. 1) included in the driving support system 1. The driving support method according to the embodiment is assumed to be a driving support method executed by the controller 103 (see FIG. 7) of this center device 100.

[0014] Also, hereinafter, when it is necessary to distinguish between a plurality of identical elements, this element may be numbered in the form of “-n” (n is a natural number) after the symbol indicating this element. When there is no particular need to distinguish, this numbering will not be performed.

[0015] Also, expressions such as “specific”, “predetermined”, and “constant” in the following description may be read as “predetermined in advance”.

[0016] First, the outline of the driving support method according to the embodiment will be described with reference to FIG. 1. FIG. 1 is a schematic explanatory diagram of the driving support method according to the embodiment. In the description using FIG. 1, FIGS. 2 to 4 will be appropriately referred to.

[0017] As shown in FIG. 1, the driving support system 1 includes drive recorders 10-1, 10-2,..., 10-m (m is a natural number of 3 or more) and a center device 100.

[0018] The drive recorder 10 is a video recording device mounted on a vehicle. The drive recorder 10 corresponds to an example of an “in-vehicle device”. The drive recorder 10 according to the embodiment has a camera 12a. The camera 12a is provided so as to be able to capture an image outside the vehicle and an image inside the vehicle.

[0019] While the vehicle is in operation, the drive recorder 10 records, in a ring buffer memory in an overwritable manner, the operation record data including the video captured by the camera 12a for a certain period. The certain period is, for example, 24 hours. The operation record data includes, in addition to the video, date and time information, position information, G (acceleration) values, and the like. The operation record data corresponds to an example of "vehicle running data".

[0020] In addition, while recording the operation record data, the drive recorder 10 executes image recognition processing on the video using, for example, an AI (Artificial Intelligence) model for image recognition. The AI model is, for example, a DNN (Deep Neural Network) model learned using a machine learning algorithm. This AI model is pre-learned so as to be able to detect the type, position, color, etc. of each object reflected in the video. The AI model is used, for example, for the detection function of each object in various driving support functions.

[0021] In addition, the drive recorder 10 is provided so as to be able to detect a specific event that satisfies a preset event condition. The drive recorder 10 detects, for example, ABS activation, DMS detection, speeding, sudden acceleration or sudden deceleration, etc. as specific events. DMS detection refers to the detection of a driver's glance, signs of drowsiness (such as a non-operation state, a distracted state, etc.), smartphone operation, etc. in the DMS.

[0022] When the drive recorder 10 detects a specific event, it sets the operation record data for a certain period before and after the detection time point to be write-protected. Hereinafter, the operation record data corresponding to the specific event set to be write-protected is appropriately referred to as "event data". Alternatively, the drive recorder 10 records this event data on another recording medium. This write-protection setting and recording on another recording medium may be performed according to an instruction from the center device 100.

[0023] Furthermore, when the drive recorder 10 detects a specific event, it transmits event data to the central device 100. The event data includes event type, date and time information, location information, video, G-value, image recognition information, etc. The image recognition information includes the detection results obtained from the image recognition processing described above.

[0024] The central device 100 collects event data transmitted from each drive recorder 10 and is configured to analyze the vehicle's status when a specific event is detected based on the collected event data. The central device 100 is also configured to perform information processing based on the analysis results.

[0025] In the driving assistance method according to this embodiment, the center device 100 estimates a first situation that is likely to occur in, for example, any area while the vehicle is in motion, based on the analysis results. The center device 100 also extracts the conditions for similar situations that are similar to the estimated first situation, based on the aforementioned analysis results. Herein, "similar" includes cases where they "match". The center device 100 also generates sensitivity control information that enhances the sensitivity of the detection function for detecting a second situation related to the first situation, linked to the extracted conditions. The "second situation" is, for example, a dangerous situation that may occur in a chain reaction with the first situation. The "first situation" may also be a dangerous situation. The center device 100 also transmits the generated sensitivity control information to each drive recorder 10.

[0026] Based on sensitivity control information received from the center device 100, the drive recorder 10 changes the sensitivity of the detection function for the second situation described above when the vehicle falls under a similar situation as described above. The drive recorder 10 also notifies the driver of driving assistance information related to the change in sensitivity.

[0027] Let me explain in more detail. As shown in Figure 1, when the controller 15 of each drive recorder 10 (see Figure 6) detects a specific event based on pre-set event conditions (step S1), it transmits event data corresponding to this event to the central device 100 (step S2). As already mentioned, the event data includes event type, date and time information, location information, video, G value, image recognition information, etc.

[0028] Then, the controller 103 of the central device 100 estimates a first situation in which a dangerous situation is likely to occur, based on the event data collected from each drive recorder 10 (step S3).

[0029] Figure 2 shows the relationship between event types and the likely first situations. As shown in Figure 2, the likely first situations corresponding to each event can be trivially derived from the characteristics of each event.

[0030] For example, "ABS activation" indicates that the vehicle was in a situation where slippage was likely to occur. Similarly, "DMS detection" indicates that the vehicle was in a situation where it was likely to wobble, such as detecting signs of distraction, drowsiness, or smartphone use. Furthermore, "speeding" indicates that the vehicle was in a situation where it was likely to become too close to the vehicle in front. Finally, "sudden acceleration or sudden deceleration" indicates that the vehicle was in a situation where it was likely to become too close to the vehicle in front or to make contact. The controller 103 estimates the first situation using, for example, table information that pre-defines the relationship between the event type shown in Figure 2 and the likely first situation.

[0031] The controller 103 estimates the first situation for each arbitrary area, including, for example, locations where ABS activation frequently occurs or locations where DMS detection frequently occurs. This makes it possible to set specific sensitivity settings for each arbitrary area, such as locations where ABS activation frequently occurs or locations where DMS detection frequently occurs.

[0032] Returning to the explanation of Figure 1, the controller 103 then generates sensitivity control information to increase the sensitivity of the detection function for the second situation of the vehicle related to the first situation, based on the first situation estimated in step S3 (step S4). Note that "increasing the sensitivity of the detection function" can be rephrased as, for example, "raising the sensitivity of the detection function" or "sharpening the detection sensitivity of the detection function."

[0033] Figure 3 shows an example of sensitivity control information. The "detection function for a second situation related to a first situation" refers to a detection function on the driver assistance system that detects a second situation, which is a dangerous situation that may occur in a chain reaction with the first situation. As shown in Figure 3, for example, in the case of a first situation "slip," it is predicted that a second situation such as "lane departure" is likely to occur.

[0034] In this case, the controller 103 generates sensitivity control information to increase the sensitivity of the lane departure detection function, for example, used in LDW (Lane Departure Warning) in ADAS. In the example in Figure 3, the controller 103 generates sensitivity control information to increase the sensitivity of the "lane departure" detection function by, for example, lowering the threshold for outputting a warning (warning threshold). By lowering this warning threshold, the detection sensitivity of the detection function can be sharpened.

[0035] Furthermore, for example, in response to the first situation, "swaying," it is predicted that the second situation, such as "lane departure" or "falling asleep at the wheel," is more likely to occur.

[0036] The response to "lane departure" is the same as in the first situation, "slip." Regarding "drowsiness," the controller 103 generates sensitivity control information to increase the sensitivity of the "drowsiness" detection function, for example, used in the DMS. In the example in Figure 3, the controller 103 generates sensitivity control information to increase the sensitivity of the "drowsiness" detection function by lowering the warning threshold, similar to the case of "lane departure."

[0037] Furthermore, for example, in the case of the first situation, "close distance between vehicles," it is predicted that a second situation such as "vehicle approaching in front" is likely to occur.

[0038] In this case, the controller 103 generates sensitivity control information to increase the sensitivity of the "vehicle approaching ahead" detection function, which is used, for example, in FCW (Forward Collision Warning) in ADAS. In the example in Figure 3, the controller 103 generates sensitivity control information to increase the sensitivity of the "vehicle approaching ahead" detection function, for example, by increasing the processing frequency of the detection process. The detection sensitivity of the detection function can also be sharpened by increasing the processing frequency of this detection process.

[0039] Furthermore, for example, in response to the first situation, "contact," it is predicted that a second situation, such as further "collision damage," is likely to occur.

[0040] In this case, the controller 103 generates sensitivity control information to increase the sensitivity of the "collision damage" detection function, which is used, for example, in AEBS (Advanced Emergency Braking System) in ADAS. In the example in Figure 3, the controller 103 generates sensitivity control information to increase the sensitivity of the "collision damage" detection function by increasing the processing frequency of the detection process, similar to the case of "approaching vehicle ahead".

[0041] The controller 103 then extracts the conditions for similar situations that are similar to the estimated first situation based on the analysis results of the event data, and associates them with each entry in the sensitivity control information. As shown in Figure 3, the conditions for similar situations include, for example, area requirements and additional requirements.

[0042] The area requirement is within a predetermined range based on the frequent occurrence locations or similar locations of each event. Similar locations refer to locations that are, for example, topographically similar to the frequent occurrence locations of each event. The controller 103 searches for and extracts topographically similar locations based, for example, on the map information DB (Database) 102b (see Figure 7).

[0043] These area requirements allow for setting the sensitivity of the detection function to consider situations similar to the event location when a vehicle enters an area based on similar locations, not just the actual location where the event occurred. Furthermore, by considering topographical similarities, locations with similar road shapes to the event location can be extracted as similar locations.

[0044] Additional requirements are requirements added to area requirements. These additional requirements describe the external environment of the vehicle at the time of the event, such as the outside temperature, weather, time of day, and the position of the sun relative to the direction of travel. By considering these additional requirements, it becomes possible to narrow down similar situations to include external environmental factors beyond the area requirements at the time of the actual event.

[0045] The controller 103 may use the measurement value from the ambient temperature sensor mounted on the vehicle for the ambient temperature. The controller 103 may also use an information provider server, such as a weather information server operated as a public cloud, for ambient temperature, weather, and sun position. Furthermore, the controller 103 may use the image recognition results for weather and sun position.

[0046] Each of the additional requirements may be combined with the area requirement using AND conditions, or with the area requirement using OR conditions. Note that the additional requirements shown in Figure 3 are merely examples and are not limited to any additional requirements that enable the narrowing down of the circumstances at the time of event occurrence.

[0047] Furthermore, in each of the sensitivity control examples shown in Figure 3, "alarm threshold reduction" and "processing frequency increase" may be appropriately swapped.

[0048] Returning to the explanation of Figure 1, the controller 103 then transmits the sensitivity control information generated in step S4 to each drive recorder 10 (step S5). The controller 15 of the drive recorder 10 then changes the sensitivity of the detection function for the second situation when a similar situation to the first situation is found, based on the sensitivity control information received from the central device 100 (step S6). By transmitting the sensitivity control information to each drive recorder 10 and having each drive recorder 10 change the sensitivity of the detection function for the second situation when a similar situation is found based on the sensitivity control information, the central device 100 does not need to constantly monitor the position of each vehicle on which each drive recorder 10 is installed. This significantly reduces the communication load in the driver assistance system 1.

[0049] In addition, the controller 15 notifies the driver of driving assistance information related to the change in sensitivity (step S7). Figure 4 shows an example of notification to the driver. As shown in Figure 4, the controller 15 notifies the driver via the HMI (Human Machine Interface) unit 13 (see Figure 6) provided in the drive recorder 10.

[0050] For example, if the vehicle is driving in an area where ABS activation is frequent, the controller 15 will issue a notification to the effect of, as shown in Figure 4, "You are driving in an area where ABS activation is frequent. Slipping is likely to occur, so we will enhance the assistance provided by the lane departure detection function."

[0051] As shown in the example in Figure 4, the driver can recognize that they are driving in an area where ABS, as a driver assistance function, is likely to activate, and that the situation is prone to slipping (corresponding to an example of "Situation 1"). In addition, the driver can recognize that the situation is prone to lane departure (corresponding to an example of "Situation 2") in relation to Situation 1, and can recognize sooner that they should pay attention to lane departure. Furthermore, if lane departure actually occurs, the increased sensitivity of the detection function allows the driver to recognize that lane departure has occurred more quickly.

[0052] As described above, in the driving assistance method according to this embodiment, the controller 103 of the center device 100 estimates a first situation in which a dangerous situation is likely to occur based on the vehicle's driving data. The controller 103 also increases the sensitivity of the detection function for a second situation of the vehicle related to the first situation and notifies the vehicle's driver of the change in sensitivity.

[0053] Therefore, according to the driving assistance method according to the embodiment, the sensitivity of detecting a second situation of the vehicle related to a first situation estimated based on the vehicle's driving data is increased, and by notifying the driver of this, the driver can recognize sooner that they should pay attention to the second situation. In addition, the driver can be made aware that, for example, a driving assistance function related to the second situation may be activated. Furthermore, if a detection related to the second situation actually occurs, such as lane departure, the increased sensitivity of the detection function allows the driver to recognize that a lane departure has occurred sooner. In other words, according to the driving assistance method according to the embodiment, more effective driving assistance can be provided that takes into account not only the predicted risks but also the chain of risks.

[0054] The following describes in more detail an example of the configuration of the driver assistance system 1, which includes a center device 100 to which the driver assistance method according to the above embodiment is applied.

[0055] Figure 5 shows an example of the configuration of the driver assistance system 1 according to the embodiment. As shown in Figure 5, the driver assistance system 1 includes drive recorders 10-1, 10-2, ... 10-m and a center device 100.

[0056] Each drive recorder 10 and the central device 100 are connected to each other via a network N1, such as the Internet, a mobile phone network, or a C-V2X (Cellular Vehicle to Everything) communication network, enabling them to communicate with one another.

[0057] Since the drive recorder 10 has already been explained, its explanation will be omitted here. The central device 100 is implemented, for example, as a private cloud. The central device 100 is managed, for example, by a data center operator (insurance company, etc.). The central device 100 collects event data transmitted from each drive recorder 10.

[0058] Furthermore, the central device 100 analyzes the collected event data and estimates, for example, the most likely first situation to occur in each arbitrary area based on the analysis results. The central device 100 also extracts the conditions for similar situations that are similar to the estimated first situation based on the aforementioned analysis results. The central device 100 also generates sensitivity control information to enhance the sensitivity of the detection function that detects the second situation related to the first situation, linking it to the extracted conditions. The central device 100 also transmits the generated sensitivity control information to each drive recorder 10.

[0059] Next, an example of the configuration of the drive recorder 10 will be described. Figure 6 is a diagram showing an example of the configuration of the drive recorder 10 according to the embodiment. As shown in Figure 6, the drive recorder 10 has a communication unit 11, a sensor unit 12, an HMI unit 13, a storage unit 14, and a controller 15.

[0060] The communication unit 11 is implemented by a network adapter or the like. The communication unit 11 is wirelessly connected to the network N1 and transmits and receives information to and from the center device 100 via the network N1.

[0061] The sensor unit 12 is a group of various sensors mounted on the drive recorder 10. The sensor unit 12 includes, for example, a camera 12a, a GPS (Global Positioning System) sensor 12b, and a G-sensor 12c.

[0062] Camera 12a includes an external camera and an internal camera, not shown in the diagram. The external camera is mounted to capture images of the outside of the vehicle. The external camera is mounted near the windshield, near the dashboard, near the rear window, etc.

[0063] The in-car camera is installed to capture images of the interior of the vehicle. The in-car camera is mounted near the windshield or dashboard, etc., so that at least the driver's face is included in the shooting range. Note that the in-car camera and the exterior camera do not necessarily have to be separate; for example, they may be integrated into a single 360-degree camera.

[0064] The GPS sensor 12b determines the GPS position of the vehicle. The G sensor 12c measures the acceleration applied to the drive recorder 10.

[0065] In addition to the sensor unit 12, the drive recorder 10 is also connected to an in-vehicle sensor unit 5, which is a group of various sensors mounted on the vehicle. The in-vehicle sensor unit 5 includes, for example, an accelerator sensor, a brake sensor, a vehicle speed sensor, and an outside temperature sensor. The in-vehicle sensor unit 5 is connected to the drive recorder 10 via an in-vehicle network such as CAN (Controller Area Network).

[0066] Furthermore, the drive recorder 10 is connected to ADAS7. ADAS7 includes the aforementioned ABS, DMS, LDW, FCW, AEBS, etc. ADAS7 is connected to the drive recorder 10 so that they can communicate with each other via an in-vehicle network such as CAN.

[0067] Furthermore, ADAS7 enables various advanced driver assistance functions by utilizing, for example, the detection function of the drive recorder 10 through image recognition processing.

[0068] The HMI unit 13 is a component that provides interface components for input and output to a user, such as a driver, who operates the drive recorder 10. The HMI unit 13 includes an input interface that accepts input operations from the user. The input interface is implemented, for example, by a touch panel. Alternatively, the input interface may be implemented by a microphone or the like. Furthermore, the input interface may be implemented by software components.

[0069] Furthermore, the HMI unit 13 includes an output interface for presenting visual and auditory information to the user. The output interface is implemented, for example, by a display or speaker. The HMI unit 13 may also provide the input interface and output interface to the user as an integrated unit, for example, by using a touch panel display.

[0070] The memory unit 14 is implemented using memory devices such as ROM (Read Only Memory), RAM (Random Access Memory), and flash memory. In the example shown in Figure 6, the memory unit 14 stores an image recognition model 14a, event condition information 14b, operation record data DB 14c, and sensitivity control information 14d.

[0071] The image recognition model 14a corresponds to the AI ​​model for image recognition described above. After being loaded as an AI model into the controller 15, the image recognition model 14a is configured to detect various objects in each frame when each frame of video captured by the camera 12a is input to the controller 15.

[0072] The image recognition model 14a is configured to detect, for example, vehicles, lanes, traffic lights, and the color of the traffic lights in each frame when each frame of external video footage is input. The image recognition model 14a may also be configured to detect weather conditions, the position of the sun, and so on.

[0073] Furthermore, the image recognition model 14a is configured to detect, for example, the faces of people, including the driver, in each frame when each frame of in-car video is input. The image recognition model 14a is also configured to detect, for example, signs of driver distraction, drowsiness, or smartphone operation based on facial feature point clouds. Additionally, the image recognition model 14a is configured to detect objects other than faces in each frame of the in-car video.

[0074] Event condition information 14b is information in which predetermined event conditions are set for detecting the specific events described above. The event conditions are transmitted as appropriate from, for example, the center device 100 and stored in event condition information 14b. Operation record data DB 14c is a database of operation record data recorded by the drive recorder 10.

[0075] The sensitivity control information 14d corresponds to the sensitivity control information explained using Figure 3. The sensitivity control information 14d is received by the controller 15 from the center device 100 via the communication unit 11 and stored.

[0076] The controller 15 corresponds to a so-called processor. The controller 15 is implemented by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphical Processing Unit), etc. The controller 15 executes a program according to an embodiment not shown, stored in the memory unit 14, using RAM as the working area. The controller 15 can also be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0077] The controller 15 executes the information processing performed by the drive recorder 10 in the processing sequence shown in Figure 8. An explanation using Figure 8 will be given later.

[0078] Next, an example of the configuration of the center device 100 will be described. Figure 7 is a diagram showing an example of the configuration of the center device 100 according to the embodiment. As shown in Figure 7, the center device 100 has a communication unit 101, a storage unit 102, and a controller 103. The center device 100 is also connected to an HMI unit 150.

[0079] The HMI unit 150 is a component that provides interface components for input and output to operators, etc., who operate the center device 100. The HMI unit 150 includes an input interface that receives input operations from operators, etc. The input interface is implemented, for example, by a touch panel. Alternatively, the input interface may be implemented by a keyboard, mouse, pen tablet, microphone, etc. Furthermore, the input interface may be implemented by software components.

[0080] Furthermore, the HMI unit 150 includes an output interface for presenting visual and audio information to the operator. The output interface is implemented, for example, by a display or speaker. The HMI unit 150 may also provide the input interface and output interface to the operator as an integrated unit, for example, by using a touch panel display.

[0081] The communication unit 101 is implemented by a network adapter or the like. The communication unit 101 is connected to the network N1 by wire or wireless connection and transmits and receives information to and from each drive recorder 10 via the network N1.

[0082] The memory unit 102 is implemented by a storage device such as ROM, RAM, flash memory, or HDD (Hard Disk Drive). In the example shown in Figure 7, the memory unit 102 stores collected data DB102a, map information DB102b, and sensitivity control information DB102c.

[0083] The collected data DB102a is a database that stores event data collected from each drive recorder 10. The map information DB102b is a database of map information used for searching for similar locations as described above.

[0084] The sensitivity control information DB102c is a database that stores sensitivity control information generated by the controller 103.

[0085] Although not shown in the diagram, the memory unit 102 may store an AI model corresponding to the image recognition model 14a described above. When analyzing event data, the controller 103 may perform image recognition processing using such an AI model, thereby including the image recognition results recognized by the center device 100 in the event data analysis results.

[0086] The controller 103 corresponds to a so-called processor. The controller 103 is implemented by a CPU, MPU, GPU, etc. The controller 103 executes a program according to an embodiment not shown, stored in the memory unit 102, using RAM as the working area. The controller 103 can also be implemented by an integrated circuit such as an ASIC or FPGA.

[0087] The controller 103, like the controller 15 described above, performs information processing by the center device 100 in the processing sequence shown in Figure 8.

[0088] Next, we will explain the information processing performed by this processing sequence. Figure 8 is a diagram showing the processing sequence executed by the driver assistance system 1 according to the embodiment.

[0089] As shown in Figure 8, in the drive recorder 10, the controller 15 records the operation (step S101). The controller 15 also determines whether or not it has detected a specific event set in the event condition information 14b (step S102).

[0090] If an event is detected (Step S102, Yes), the controller 15 sends event data for a certain period of time before and after the event detection to the central device 100 (Step S103). If no event is detected (Step S102, No), the controller 15 repeats the process from Step S101.

[0091] The controller 103 of the center device 100 receives the event data in step S103 and stores it in the collected data DB 102a (step S104). Then, at any time, the controller 103 analyzes the event data stored in the collected data DB 102a (step S105).

[0092] Then, based on the results of the event data analysis, the controller 103 estimates the first situation that is likely to occur in each arbitrary area (step S106). Subsequently, based on the results of the event data analysis, the controller 103 extracts the conditions for similar situations that are similar to the first situation (step S107).

[0093] Then, the controller 103 generates sensitivity control information to enhance the sensitivity of the detection function for the second situation related to the first situation, linked to the relevant conditions extracted in step S107 (step S108). The generated sensitivity control information is stored in the sensitivity control information DB 102c.

[0094] The controller 103 then transmits the generated sensitivity control information to each drive recorder 10 (step S109).

[0095] Next, the controller 15 of the drive recorder 10 determines whether the situation of the vehicle in motion corresponds to a similar situation set in the sensitivity control information 14d, based on the sensitivity control information 14d received and stored from the center device 100 (step S110).

[0096] If the situation does not match the similar circumstances (step S110, No), the controller 15 repeats step S110. If the situation matches the similar circumstances (step S110, Yes), the controller 15 changes the sensitivity based on the sensitivity control information 14d (step S111).

[0097] Specifically, the controller 15 enhances the sensitivity of the detection function by, for example, outputting a control signal to the ADAS 7, which uses the detection results based on image recognition processing of the video captured by the camera 12a, that lowers the threshold for outputting various alarms. Alternatively, the controller 15 enhances the sensitivity of the detection function by, for example, increasing the processing frequency of the detection processing based on image recognition processing of the video captured by the camera 12a.

[0098] Furthermore, the controller 15 notifies the user of driving assistance information related to the change in sensitivity (step S112). An example of this notification is shown in Figure 4. The controller 15 then repeats the process from step S110.

[0099] Although not shown in the diagram, the controller 15 maintains the modified sensitivity until the vehicle leaves the similar situation. Once the vehicle leaves the similar situation, the controller 15 returns the sensitivity to its original value.

[0100] Furthermore, the controller 15 can execute the processes of steps S101 to S103 and the processes of steps S110 to S112 in parallel.

[0101] As described above, the center device 100 according to the embodiment (corresponding to an example of a "driving support device") has a controller 103. The controller 103 estimates a first situation in which a dangerous situation is likely to occur based on the vehicle's driving data. The controller 103 also increases the sensitivity of the detection function for a second situation of the vehicle related to the first situation and notifies the vehicle's driver of the change in sensitivity.

[0102] Therefore, according to the center device 100 of this embodiment, the controller 103 increases the sensitivity of detecting the second situation of the vehicle related to the first situation estimated based on the vehicle's driving data, and notifies the driver of this change in sensitivity. This makes the driver aware that they should pay attention to the second situation which may occur in a chain reaction with the first situation. It also makes the driver aware that, for example, a driving assistance function related to the second situation may be activated. Furthermore, if the second situation is actually detected, the driver can be made aware of it more quickly. In other words, according to the center device 100 of this embodiment, more effective driving assistance can be provided that takes into account the chain reaction of risks in response to predicted risks.

[0103] In the embodiment described above, an example was explained in which the central device 100 generates sensitivity control information and transmits it to each drive recorder 10, and the drive recorder 10 changes the sensitivity of the second situation detection function based on the sensitivity control information. However, if the central device 100 can constantly monitor the position of each vehicle, for example, the central device 100 may instruct the drive recorder 10 to change the sensitivity or notify the driver as appropriate, without transmitting sensitivity control information to each drive recorder 10.

[0104] Furthermore, in the embodiments described above, the center device 100 is managed by, for example, an insurance company that operates a data center, but it may also be managed by a transportation-related business operator that manages and operates commercial vehicles, etc. When the center device 100 is managed by such various businesses, the drive recorder 10 is often intended for corporate use. Some drive recorders 10 intended for corporate use and the center device 100 that manages them have a function to provide safe driving instruction and education to drivers.

[0105] If such a function is present, the driving assistance method according to this embodiment can be partially applied, for example, to the generation of e-learning materials for safe driving instruction and education. In this case, the controller 103 can generate questions such as, "What dangerous situations may occur in a chain reaction?" or "What driving assistance functions may be activated?" in response to a first situation in which the vehicle is prone to slipping at points where ABS activation frequently occurs.

[0106] Further effects and modifications can be readily derived by those skilled in the art. Therefore, broader aspects of the present invention are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and their equivalents. [Explanation of symbols]

[0107] 1. Driver assistance system 5. Vehicle-mounted sensor unit 7 ADAS 10. Dashcam 11 Communications Department 12 Sensor section 13 HMI section 14 Storage section 15 Controllers 100 Center device 101 Communications Department 102 Storage section 103 Controller 150 HMI section

Claims

1. Based on vehicle driving data, the first scenario, in which dangerous situations are likely to occur, is estimated. To increase the sensitivity of the detection function for the second situation of the vehicle related to the first situation, The driver of the vehicle is notified of the change in sensitivity. A driver assistance device equipped with a controller.

2. The aforementioned controller, The sensitivity is increased by lowering the threshold for outputting an alarm based on the detection function, or by increasing the processing frequency of the detection process in the detection function. The driving support device according to claim 1.

3. The aforementioned controller, Based on the aforementioned driving data, the conditions for similar situations that are similar to the first situation are extracted. Sensitivity control information to enhance the aforementioned sensitivity is generated and linked to the relevant conditions. The aforementioned sensitivity control information is transmitted to the vehicle. The vehicle is instructed to change the sensitivity based on the aforementioned sensitivity control information. The driving support device according to claim 1.

4. The controller estimates the first situation which is likely to occur in each arbitrary area. The driving support device according to claim 3.

5. The aforementioned arbitrary area is an area that includes locations where events corresponding to the aforementioned driving data frequently occur. The driving support device according to claim 4.

6. The aforementioned controller, A predetermined range based on the aforementioned high-incidence locations or similar locations similar to the aforementioned high-incidence locations is extracted as the area requirement for the applicable conditions. The driving support device according to claim 5.

7. The aforementioned similar locations are locations that are topographically similar to the aforementioned high-incidence locations. The driving support device according to claim 6.

8. The aforementioned controller, The requirements indicating the external environment of the vehicle at the time the aforementioned event occurs are extracted as additional requirements to the area requirements. The driving support device according to claim 6.

9. It comprises an in-vehicle device and a center device, The aforementioned in-vehicle device is When a predetermined event is detected, event data regarding the vehicle's status is transmitted to the aforementioned center device. The aforementioned center device is The event data is collected from the in-vehicle device. Based on the event data, a first situation, which is a dangerous situation likely to occur while the vehicle is in motion, is estimated. Based on the event data, the conditions for similar situations that are similar to the first situation are extracted. When the vehicle meets the above-mentioned conditions, the on-board device shall increase the sensitivity of the detection function for the second situation related to the first situation. The in-vehicle device is instructed to notify the driver of the vehicle of information related to the change in sensitivity. Driver assistance system.

10. A driver assistance method performed by a controller that collects event data regarding the vehicle's status from the vehicle when a predetermined event is detected, Based on the event data, estimate the first situation, which is a dangerous situation likely to occur while the vehicle is in motion. Based on the event data, extract the relevant conditions for similar situations that are similar to the first situation, When the vehicle meets the aforementioned conditions, the sensitivity of the vehicle's detection function for the second situation related to the first situation is increased. The vehicle is to notify the driver of the vehicle of information related to the change in sensitivity, Driving assistance methods including

Images