Systems etc.

Abstract

To provide a mechanism different from the conventional one, such as a mechanism for determining whether or not the photographed target vehicle is highly possibly driving dangerously.SOLUTION: A system comprises a control unit that determines a possibility of dangerous driving of a target vehicle, which is identified based on image information acquired by one or more cameras, based on the number of times the target vehicle entered a predetermined proximity region.SELECTED DRAWING: Figure 13

Description

[Technical Field]

[0001] The present invention relates to a system and the like. [Background technology]

[0002] Japanese Patent Application Laid-Open Publication No. 2013-134590 (Patent Document 1) discloses that a vehicle is equipped with a rear camera and a front camera. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-134590 Summary of the Invention [Problem to be solved by the invention]

[0004] However, Patent Document 1 does not consider a mechanism for determining whether or not the photographed target vehicle is in a state where there is a high possibility that it is driving recklessly. Therefore, the present invention provides a mechanism that differs from conventional mechanisms, such as a mechanism that determines whether or not a photographed target vehicle is likely to be driving recklessly.

[0005] The applicant intends to obtain rights to configurations that achieve the effects achieved by the components disclosed in this specification and drawings, etc., through divisional applications, amendments, etc. For example, this specification discloses problems in which phrases such as "can" and "is possible" are read as "the problem is." Each problem is described as an independent one, and the applicant intends to obtain rights to the configurations that solve each problem separately through divisional applications, amendments, etc. Even if the problem is implicitly understood from the description in the specification, the applicant intends to include part of the configuration described in this specification in the scope of the patent claim through amendments or divisional applications. The applicant also discloses configurations that solve problems that combine these independent problems, and the applicant intends to obtain rights to them. [Means for solving the problem]

[0006] In order to solve the above problems, for example, the configurations described in the claims are adopted. The present application includes multiple means for solving the above problems, and one example is a system characterized by having a control unit that determines the possibility of dangerous driving of a target vehicle identified based on image information acquired by one or more cameras, based on the number of times the target vehicle enters a specified proximity area. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide a mechanism that is different from conventional mechanisms, such as a mechanism that determines whether or not a photographed target vehicle is in a state where there is a high possibility that it is driving recklessly. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments.

[0008] The effects of the present invention are not limited to these, and effects achieved by the configuration disclosed in the present specification and drawings, etc. are also disclosed, and the applicant intends to obtain rights to the configuration achieving such effects through divisional applications, amendments, etc. For example, in this specification, phrases such as "can" and "is possible" are descriptions that clearly indicate the effects achieved, and there are also parts that demonstrate effects even without the phrases "can" and "is possible." Furthermore, there are effects that can be understood from the configuration even without such phrases. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is an explanatory diagram illustrating an example of an installation position of a drive recorder 101 in a vehicle according to the present embodiment. [Figure 2] 1 is a diagram illustrating an example of the configuration of a camera in a drive recorder 101. FIG. [Figure 3] 10 is another example of a configuration diagram of a camera in the drive recorder 101. FIG. [Figure 4] 1 is an example of a connection diagram of a system including a drive recorder 101. [Figure 5] FIG. 1 is a diagram illustrating an example of a schematic hardware configuration of a drive recorder 101(F, R). [Figure 6] 1 is a diagram illustrating an example of a schematic configuration of a management server 106. [Figure 7] 1 is a diagram illustrating an example of a hardware configuration of a user terminal 107. [Figure 8] 3 is an example of a block diagram of a control unit 303. [Figure 9] 10 is an example of a tailgating determination process flow. [Figure 10] 10 is an example of a vehicle determination process flow. [Figure 11] 10 is an explanatory diagram illustrating an example of a following vehicle to be detected. [Figure 12] 10 is an explanatory diagram of an example of a tilt index determination table. [Figure 13] 10 is an explanatory diagram of an example of a tilt index determination graph. [Figure 14] 10 is an example of a processing flow for each provocation level. [Figure 15] 1 is a diagram illustrating an example of the configuration of a camera in a drive recorder 101. FIG. [Figure 16] 1 is an example of an explanatory diagram of a first operation example of the drive recorder 101. FIG. [Figure 17] 1 is an example of an explanatory diagram of a first operation example of the drive recorder 101. FIG. [Figure 18] 1 is an explanatory diagram illustrating an example of a configuration for measuring a vehicle-to-vehicle distance determined from perspective. [Figure 19] 1 is an explanatory diagram illustrating an example of a configuration for measuring a vehicle-to-vehicle distance determined from perspective. [Figure 20] 1 is an explanatory diagram illustrating an example of a configuration for detecting a person outside the vehicle 10. FIG. [Figure 21] 1 is an explanatory diagram illustrating an example of a configuration for detecting a person outside the vehicle 10. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment shown below is one embodiment of the present invention, and the content of the present invention should not be interpreted as being limited based on the following description.

[0011] [First embodiment] In this embodiment, a dangerous driving determination system will be described, which is a system for determining the possibility of dangerous driving behavior that may cause traffic hazards on roads to other vehicles, etc. Determining the possibility of tailgating will be described as an example of dangerous driving, but the present invention is not limited to this. At the time of filing this application, the following 10 types of obstructive driving, which is tailgating, have been defined. 1.Violation of traffic classification 2. Violation of the sudden braking ban 3. Not maintaining following distance 4. Violation of lane change prohibition 5. Overtaking violations 6. Violation of obligations such as dimming lights 7. Violation of horn usage restrictions 8. Violation of the duty to drive safely 9. Minimum speed violation (high-speed motorway national highway) 10.Violation of parking on national highways etc.

[0012] FIG. 1 is an explanatory diagram illustrating an example of the installation position of a drive recorder 101 in a vehicle according to this embodiment. FIG. 1(a) is a side view of the vehicle, and FIG. 1(b) is a top view of the vehicle.

[0013] As shown in Figures 1(a) and 1(b), drive recorders (DVRs) 101 are provided at the front and rear of the cabin of a vehicle 10. The drive recorder for the front of the vehicle is referred to as a front drive recorder 101F, and the drive recorder for the rear of the vehicle is referred to as a rear drive recorder 101R. Note that the vehicle may be configured to include only the front drive recorder 101F or the rear drive recorder 101R.

[0014] 1(b), the front drive recorder 101F of the vehicle is installed, for example, on the passenger seat side on the left side of the ceiling, and the rear drive recorder 101R is installed in the center of the rear ceiling. However, they may be installed in other locations. The installation location of the drive recorder 101 in the vehicle in Figure 1 is displayed on the screen of the management terminal 105, management server 106, user terminal 107, etc., and indicates the location where the drive recorder 101 (F, R) is installed, and it is possible to change the settings of each drive recorder 101 (F, R) from that screen.

[0015] Next, a description will be given of the cameras in the drive recorder 101. In this embodiment, two types will be described as examples with reference to FIGS. 2(a) is an example of a configuration diagram of cameras in the drive recorder 101. The drive recorder 101 is viewed from above, with two cameras arranged on the left and right sides of the front or rear of the vehicle 10.

[0016] A drive recorder 101 (F, R) shown in FIG. 2(a) has a vehicle image capturing camera 102 and a vehicle number plate detection camera 103 installed at the same height and substantially parallel to the ground. In this embodiment, the drive recorder 101 (F, R) includes the vehicle photographing camera 102 and the vehicle number plate detection camera 103 in the same housing. Therefore, the positional relationship between the vehicle photographing camera 102 and the vehicle number plate detection camera 103 is fixed, making it easy for the user to position these cameras. The housing of the drive recorder 101 may be rectangular, cylindrical, or of another shape. The drive recorder 101 may be attached to the vehicle using a method known at the time of filing this application or another method.

[0017] The drive recorder 101 (F, R) may be configured so that the vehicle photographing camera 102 and the vehicle license plate number detection camera 103 are separable (e.g., detachable), or may be configured as separate bodies. In this case, the degree of freedom in the placement position and photographing direction of the vehicle photographing camera 102 and the vehicle license plate number detection camera 103 is improved. The drive recorder 101 may be one that obtains celestial spherical images (semi-sphere or full sphere) using a 360-degree camera or the like.

[0018] The vehicle photographing camera 102 has a wide angle of view of 130 degrees because it is necessary to photograph a wide area in front of or behind the vehicle 10. The vehicle photographing camera 102 should be configured in this way so that it can record images of a wide area in front of, behind, or to the sides of the vehicle 10.

[0019] On the other hand, the vehicle number detection camera 103 is a relatively telephoto camera with a narrow angle of 30 degrees or more and 40 degrees or less (for example, 30 degrees) in order to analyze and acquire the vehicle number of a vehicle in front of or behind the vehicle 10. The vehicle number detection camera 103 is a camera for acquiring the vehicle number as information for identifying the identity of the vehicle, and employs an angle of view suitable for detecting the target vehicle and its vehicle number.

[0020] In this embodiment, the vehicle number detection camera 103 is used for vehicle detection for forward vehicle collision warning systems (FCWS) or rear vehicle collision warning systems (RCWS). In this way, the camera for the forward vehicle collision warning systems or rear vehicle collision warning systems is also used as a camera for determining dangerous driving.

[0021] Of course, the camera for the forward vehicle collision warning system or the rear vehicle collision warning system may be a different camera from the camera used to determine dangerous driving. Regarding the angle, the angle of view may be other than the above-mentioned values, but the vehicle photographing camera 102 is a wide-angle camera and the vehicle license plate number detection camera 103 is a camera with a narrower angle of view. By using multiple cameras with different angles of view in this manner, the accuracy of identifying the target vehicle's license plate number and other details can be improved compared to when only a wide-angle vehicle camera is used, making it possible to more accurately determine the possibility of tailgating.

[0022] In the example of Figure 2(a), the lenses of the vehicle photographing camera 102 and the vehicle number detection camera 103 are oriented parallel to each other, but the lens of the vehicle number detection camera 103 may be configured to be oriented downward more than the lens of the vehicle photographing camera 102 so as to make it easier to photograph license plates installed near the bumper on the underside of the vehicle.

[0023] Furthermore, the lens direction (optical axis direction) of the vehicle number detection camera 103 may be configured to be changeable depending on the installation location of the drive recorder 101(F, R). For example, the vehicle photographing camera 102 has a wide angle and can photograph a wide area in front of or behind the vehicle 10, so there is no need to move the lens direction and it is fixed to the housing of the drive recorder 101(F, R). On the other hand, the vehicle number detection camera 103 has a narrow angle of view, so the lens direction can be changed to reliably aim at the license plate of a vehicle in front or behind.

[0024] For example, when the drive recorder 101 (F, R) is installed in the passenger seat on the left side facing the front of the vehicle 10 as shown in Figure 1 (b), the optical axis of the lens of the vehicle number detection camera 103 is changed so that it faces toward the center of the vehicle 10. Such a change in the direction of the lens of the vehicle number detection camera 103 so that it faces toward the center of the vehicle 10 can be done manually when installing the drive recorder 101 (F, R), or the direction of the lens can be changed by an actuator provided in the drive recorder 101 (F, R) in conjunction with the installation position of the drive recorder 101 in the vehicle shown in Figure 1.

[0025] Furthermore, a camera direction control unit may be provided to control the direction of the vehicle number detection camera 103, for example, as follows. 1. Always follow a position approximately 30 m ahead of or behind the center of vehicle 10. 2. Always follow the center of the lane in front of or behind the vehicle 10. 3. Always follow other vehicles in front of or behind vehicle 10 and their license plates. The lens orientation can be confirmed on a screen showing the installation position of the drive recorder 101 in the vehicle shown in Figure 1, which is displayed on the user terminal 107, management terminal 105, or management server 106, and the orientation can also be changed from the user terminal 107, management terminal 105, or management server 106.

[0026] The vehicle number detection camera 103 is placed at a position that does not interfere with the angle of view of the vehicle photographing camera 102. In other words, the distance between the respective cameras is sufficient so that the end 104E of the vehicle number detection camera 103 does not enter the photographing range of the vehicle photographing camera 102. By configuring the vehicle number plate photographing camera to be positioned so as not to interfere with the angle of view of the vehicle photographing camera in this way, it is possible to prevent the inconvenience of part of the image from the vehicle photographing camera 102, which has a wide angle of view, being lost.

[0027] FIG. 2(b) is an example of a configuration diagram of a drive recorder 101 in which two cameras are arranged one above the other. In the example of Fig. 2(a), two cameras are arranged on the left and right facing the front or rear of the vehicle 10, but in Fig. 2(b), these two cameras are arranged one above the other. In this case, it is advisable to provide the vehicle number detection camera 103 on the upper side and the vehicle photographing camera 102 on the lower side. In the example of Figure 2(b), the distance between vehicle shooting camera 102 and vehicle number detection camera 103 can be made narrower than in Figure 2(a). The lens of vehicle number detection camera 103 is captured within the angle of view of vehicle shooting camera 102, but the amount of information in the portion of the captured video that faces the sky is usually small, so even if the lens of vehicle number detection camera 103 is captured and blocks the image, there is little problem.

[0028] In this configuration where two cameras are arranged one above the other, the distance between the two lenses is shorter than in the case of FIG. 2(a), and the drive recorder 101 (F, R) can be made smaller. Even if two lenses are arranged one above the other, as explained in Figure 2(a), it is preferable to configure the vehicle number detection camera 103 to face the lower part of the vehicle in front or behind so that it is easier to photograph the license plate. The configurations shown in FIGS. 2(a) and 2(b) may be adopted only in the drive recorder 101R, or may be adopted in the drive recorder 101F, or may be adopted in both.

[0029] FIG. 3 is another example of a configuration diagram of the camera in the drive recorder 101. In the example of FIG. 3, instead of arranging the lens tip portions 104A and 104B of the two cameras on approximately the same plane, the imaging units of the cameras 104C and 104D are arranged at the back of the housing. By adopting such a configuration, the problem of interference caused by the lens of the vehicle number detection camera 103 is resolved, and the two cameras can be arranged closer together than in the case of FIG. 2(a).

[0030] Even with this configuration, the orientation of the lens of the vehicle number detection camera 103 can be changed, just like in FIG. For example, the lens tip 104A may be covered with an elastic body, allowing the lens to move up and down and left and right. Conversely, the position of the tip portion 104A of the lens may be fixed, and the position 104C of the imaging part of the vehicle number detection camera 103 may be moved up, down, left, and right to change the direction of the optical axis (lens direction). In the configuration of Fig. 3, the dimension of the lens of the drive recorder 101 in the optical axis direction is smaller than in the configuration of Fig. 2. As a result, it is expected that the degree of freedom in selecting the installation position and installation direction of the drive recorder 101 will be improved.

[0031] FIG. 4 is an example of a connection diagram of a dangerous driving determination system including a drive recorder 101, for example. The dangerous driving determination system 1 includes a drive recorder 101, a management terminal 105, a management server 106, and a user terminal 107, all of which are connected via a network 110. The network 110 may be wired or wireless, and each terminal can send and receive information via the network 110. The network 110 is not limited to the Internet, and may also be a combination of networks with different protocols.

[0032] The drive recorder 101 is a device that is mounted on, for example, a vehicle and records video while driving. The drive recorder 101 is an example of an in-vehicle device. However, although the vehicle to be equipped with the drive recorder 101 in this embodiment is a four-wheeled automobile, it is not limited to a four-wheeled automobile, and any vehicle capable of being fitted with the drive recorder 101 may be suitable. For example, large transport vehicles with four or more wheels, such as buses and trucks, two-wheeled vehicles such as motorcycles and bicycles, and other vehicles may be suitable. For example, with regard to the seventh type of violation, excluding the above-mentioned violations 6, 9, and 10, even acts committed by bicycles are considered obstructive driving. Furthermore, for example, public transport vehicles such as trains, monorails, and linear motor cars may also be suitable for installation. The drive recorder 101 can transmit the acquired various information, information relating to the result of the tailgating determination, etc. to the management server 106 via the network 110. The management terminal 105 is a terminal that operates and manages the management server 106 .

[0033] The management server 106 is a server that stores and manages various information such as recording information and event information corresponding to image information acquired by the drive recorder 101, and information related to the results of tailgating determination. The various information acquired by the drive recorder 101 may be configured to be sent directly from the drive recorder 101 to the management server 106, or may be configured to be sent to the management server 106 via a data center.

[0034] The user terminal 107 is a terminal used by, for example, a user who drives a car. The user terminal 107 is connected to the drive recorder 101 via a mobile data communication network or an in-vehicle network such as Wi-Fi (registered trademark) of the car, and can operate the drive recorder 101. Furthermore, the user terminal 107 is connected to the management server 106 via these networks 110 and can display various information stored in the management server 106 .

[0035] Each terminal of the dangerous driving determination system 1 and the management server 106 may be, for example, a portable terminal (mobile terminal) such as a smartphone, tablet, mobile phone, or personal digital assistant (PDA), or a wearable terminal such as glasses, a wristwatch, or clothing. They may also be stationary or portable computers, or servers located on the cloud or a network. In terms of functionality, they may be VR (Virtual Reality) terminals, AR (Augmented Reality) terminals, or MR (Mixed Reality) terminals. Alternatively, they may be a combination of multiple of these terminals. For example, a combination of one smartphone and one wearable terminal may logically function as a single terminal. Other information processing terminals may also be used.

[0036] Each terminal and management server 106 of the dangerous driving determination system 1 includes a processor that executes an operating system, applications, programs, etc., a main storage device such as RAM (Random Access Memory), an auxiliary storage device such as an IC card, hard disk drive, SSD (Solid State Drive), flash memory, etc., a communication control unit such as a network card, wireless communication module, or mobile communication module, input devices such as a touch panel, keyboard, mouse, voice input, and input based on motion detection captured by a camera unit, and an output device such as a monitor or display. Note that the output device may also be a device or terminal that transmits information to be output to an external monitor, display, printer, device, etc.

[0037] The main memory stores various programs and applications (called modules), and the processor executes these programs and applications to realize the various functional elements of the overall system. These modules may be implemented in hardware, such as by integration. Each module may be an independent program or application, or may be implemented as a subprogram or function within a single integrated program or application.

[0038] In this specification, each module is described as the entity (subject) that performs the processing, but in reality, the processing is carried out by a processor that processes various programs, applications, etc. (modules). Various databases (DB) are stored in the auxiliary storage device. A "database" is a functional element (storage unit) that stores a set of data so that it can accommodate any data manipulation (e.g., extraction, addition, deletion, overwriting, etc.) from a processor or an external computer. The method of implementing the database is not limited, and may be, for example, a database management system, spreadsheet software, or a text file such as XML or JSON.

[0039] FIG. 5 is a diagram showing an example of a schematic hardware configuration of the drive recorder 101(F, R). The DVR controller 304 is connected to and controls the vehicle photographing camera 102, the vehicle number plate detection camera 103, the acceleration sensor 305, the SD card 306, the GNSS sensor 307, and other sensors (not shown). Based on information received from these elements, the DVR controller 304 generates status information indicating the state of the DVR controller 304. The DVR controller 304 also transmits the generated status information to the microcomputer 301.

[0040] The microcomputer 301 controls the communication processing unit 302. Furthermore, the microcomputer 301 controls the communication processing unit 302 to transmit status information acquired from the DVR controller 304 to the management server 106. The microcomputer 301 is programmable, and stores programs for executing the various processes described above. The various processes described above are realized by the processing unit of the microcomputer 301 executing these programs.

[0041] The DVR controller 304, microcomputer 301, and communication processing unit 302 can each be implemented as an integrated circuit (chip) such as an SoC (System on a chip), or a configuration in which a plurality of these are implemented together on a single chip is also possible. In particular, in this embodiment, the DVR controller 304 and microcomputer 301 operate in cooperation with each other, so they may be implemented together on a single chip.

[0042] Also, a configuration may be adopted in which the microcomputer 301 executes some of the functions of the DVR controller 304, or a configuration may be adopted in which the DVR controller 304 executes some of the functions of the microcomputer 301. In this embodiment, the DVR controller 304 and the microcomputer 301 are collectively referred to as the control unit 303. The control unit 303 may be a single chip, or may be configured to include multiple chips in which the functions of the DVR controller 304 and the microcomputer 301 are separated.

[0043] By equipping the image sensors of the vehicle photographing camera 102 and the vehicle number plate detection camera 103 with an AI processing function that performs preprocessing, the following output can be generated in addition to or instead of the normal generation of photographed images. The AI ​​processing function has the function of performing image recognition based on the images photographed by these cameras. -Export objects from images as metadata. - ISP (Image Signal Processor) output format, such as YUV or RGB images. - Output an image cropped from a specific area.

[0044] By performing preprocessing on the image sensor side in this way, it is possible to reduce the amount of data and enable real-time tracking of objects using high-speed AI processing. In particular, there is an advantage in that the amount of data (i.e., communication volume) sent from the drive recorder 101 to the management server 106 can be reduced.

[0045] The acceleration sensor 305 detects acceleration and generates acceleration information. For example, when a sudden change in acceleration occurs due to an impact, sudden steering, sudden stopping, etc., the control unit 303 detects the occurrence of an event. By analyzing this change in acceleration information, it is possible to infer the circumstances of an accident, etc., that has occurred in a car, etc. The SD card 306 is a storage device that records various information such as image information and recording information corresponding to that image information. Note that the SD card is not limited to an SD card and any configuration that can store data will do, but a flash memory with high vibration resistance is preferable for in-vehicle use.

[0046] The communication processing unit 302 transmits information from the drive recorder 101 to the management server 106 via a wireless communication antenna 308 directly or via the data center 104 . The GNSS sensor 307 has a location information acquisition unit implemented as an integrated circuit or the like, and acquires location information based on a signal received from a GNSS antenna compatible with a GNSS (Global Navigation Satellite System) such as a GPS (Global Positioning System). The location information acquisition unit can also acquire time information, moving speed information, and moving direction information.

[0047] The drive recorder 101 has a power supply 311 connected to a vehicle power supply 310 . The power supply 311 supplies power received (or sometimes referred to as power reception) from the vehicle power supply 310 to the DVR controller 304 and also charges the secondary battery 312 .

[0048] The secondary battery 312 is a rechargeable battery such as a lithium ion battery, a nickel-cadmium battery, a nickel-metal hydride battery, or a lead-acid battery. However, a non-rechargeable primary battery may also be used. When the accessory power supply (ACC power supply) is turned off, or when the supply of power from the vehicle power supply 310 to the power supply 311 of the drive recorder 101 is interrupted due to a fault such as a broken wire or a disconnected wire caused by an accident, or when the power supply 311 is unable to supply power due to a malfunction or the like, the secondary battery transmits (or may also be called power transmission or power supply) power to the microcomputer 301, the communication processing unit 302, etc., thereby maintaining at least some of the functions of the drive recorder 101.

[0049] The control unit 303 acquires image information from the vehicle image capturing camera 102 and the vehicle number plate detection camera 103 of the drive recorder 101 (F, R), and determines whether the vehicle is tailgating based on the count value of the vehicle entering a predetermined proximity area and the proximity time, which is the time the vehicle is in the predetermined proximity area, based on this image information. It is also possible to use the function of a forward collision warning system (FCWS) or a rear collision warning system (RCWS) to determine whether the vehicle has entered the proximity area. The adjacent area is an area close to the drive recorder 101(F, R) or the vehicle 10 equipped with the drive recorder 101(F, R), and will be described in detail later.

[0050] The control unit 303 stores the recorded information in folders divided into multiple levels corresponding to the possibility of tailgating in accordance with the determined level of tailgating in the storage means, the SD card 306. The recorded information is image information captured by a camera and stored in the storage means, such as the SD card 306. For example, when the level of tailgating is high, the control unit 303 stores all recording information including the approach time in a high tailgating level folder on the SD card 306, and when the level of tailgating is low, the control unit 303 stores the approach time and recording information for a predetermined time (for example, 20 seconds) before and after the approach time in a low tailgating level folder on the SD card 306. The tailgating level is determined using a threshold value, which will be described later.

[0051] In addition, the control unit 303 of the front drive recorder 101F has the function of receiving rear vehicle images, vehicle numbers, etc. from the rear drive recorder 101R using the communication processing unit 302 in order to determine whether the front vehicle is the same as the rear vehicle.

[0052] FIG. 6 is an example of a schematic configuration diagram of the management server 106. The management server 106 is configured, for example, by a server placed on a cloud.

[0053] The main memory device 601 stores programs and applications such as a DVR management module 610 and a recording information management module 611, and the processor 603 executes these programs and applications to realize each functional element of the management server 106.

[0054] The DVR management module 610 acquires event information and the like of the drive recorder 101(F, R) from the drive recorder 101(F, R), stores it in the event information 620 of the auxiliary storage device 602, and manages it.

[0055] The DVR management module 610 also transmits some or all of the information obtained by decoding the event information 620 to the user terminal 107 or the management terminal 105 via push distribution or in response to a request from the user terminal 107 or the management terminal 105.

[0056] The video recording information management module 611 acquires video recording information stored in the drive recorder 101(F, R) from the drive recorder 101(F, R), stores it in the video recording information 630 in the auxiliary storage device 602, and manages it.

[0057] The video recording information management module 611 also transmits video recording information 630 (for example, an image of a vehicle behind) to the user terminal 107 or the management terminal 105 by push distribution or in response to a request from these terminals. The auxiliary storage device 602 stores event information 620, recording information 630, and the like.

[0058] FIG. 7 is a diagram showing an example of the hardware configuration of the user terminal 107. As shown in FIG. The user terminal 107 is configured as a terminal such as a smartphone, a tablet, a notebook PC, or a desktop PC.

[0059] The main memory device 701 stores programs and applications such as a management server collaboration module 710 and a DVR collaboration module 711, and the processor 703 executes these programs and applications to realize each functional element of the user terminal 107.

[0060] The management server cooperation module 710 cooperates with the management server 106, acquires the event information 620 and recording information 630 stored in the management server 106, and displays this information on an output device 705 such as a display. Furthermore, the management server cooperation module 710 cooperates with the management server 106 and can perform various settings for the management server 106 .

[0061] The DVR collaboration module 711 operates the drive recorder 101 and configures the drive recorder 101 (F, R) when the drive recorder 101 (F, R) and the user terminal 107 are connected via an in-vehicle network such as Wi-Fi (registered trademark).

[0062] The management terminal 105 can also be configured in the same way as the user terminal 107, and can operate the drive recorder 101 (F, R) and management server 106 and configure them using the DVR collaboration module and management server collaboration module stored in the main memory device.

[0063] Fig. 8 is an example of a block diagram of the control unit 303. As shown in Fig. 8, the control unit 303 includes an image processing unit 321, a counting unit 322, a timing unit 324, a determination unit 326, an information input / output unit 328, an output unit 330, etc. The SD card 306 also stores a low-excitement level folder 342, a medium-excitement level folder 344, a high-excitement level folder 346, etc.

[0064] The image processing unit 321 analyzes and processes the image information acquired by the vehicle number detection cameras 103 (R, F) to extract vehicle images of vehicles located in front of or behind the vehicle 10. The vehicle number detection camera 103 constantly captures moving images of the front or rear of the vehicle 10, and extracts the vehicle image from this image information. It is also possible to configure the system so that when another vehicle enters the proximity area in front of or behind the vehicle 10, an image of the vehicle is extracted.

[0065] The proximity area is an area close to the drive recorder 101 (F, R) or the vehicle 10 equipped with it. More specifically, the proximity area is specified as an area within a predetermined distance range from the drive recorder 101 (F, R) or the vehicle 10 equipped with it. The vehicle number detection camera 103 can detect the vehicle number of the target vehicle when the distance to the target vehicle is within a detectable distance, such as approximately 30 m or less, or 20 m to 25 m.

[0066] Alternatively, the proximity area may be an area within a distance at which the vehicle number can be detected. The proximity area is, for example, an area where the distance to the vehicle 10 is 30 m or less, preferably 25 m or less. The proximity area may be an area at a distance other than this. The distance in front of the vehicle 10 may be different from that in behind the vehicle 10. The distance defining the proximity area may be set by the user. The control unit 303 determines that another vehicle has entered within the proximity area by analyzing the captured image or by measuring using another distance measurement sensor.

[0067] If there is another vehicle in the nearby area, the image processing unit 321 cuts out an image of the license plate portion from the image information captured by the vehicle number detection camera 103, and performs character recognition on the image to extract the vehicle number (automobile registration number or vehicle number) of the nearby vehicle.

[0068] The counting unit 322 counts the number of times (proximity count) that another vehicle has entered a predetermined proximity area using a counter (not shown). More specifically, the counting unit 322 counts the number of times by detecting that the target vehicle has entered the proximity area based on the image information processed by the image processing unit 321. This configuration makes it possible to detect intrusions into the proximity area using only image processing by the camera, without the need for a special sensor. However, it is also possible to use other sensors to detect intrusions into the proximity area in parallel with or in conjunction with image processing.

[0069] Each time another vehicle is counted as having entered the proximity area, the timing unit 324 measures the proximity time, which is the time the vehicle stays in the proximity area, using a timer (not shown). The determination unit 326 calculates a tailgating index (tailgating point) P based on the number of times the other vehicle has entered the proximity area and the average time that the other vehicle has been in the proximity area (average proximity time), and determines (also referred to as judgment) the tailgating level based on the degree of this tailgating index P. The tailgating index P and tailgating level will be described later using a flowchart.

[0070] When the road rage level (degree of road rage index P) is high, the information input / output unit 328 stores all captured images of other vehicles that have entered the proximity area, including the proximity time, in the road rage level high folder 346 of the SD card 306. The information stored in the road rage level high folder is not overwritten. On the other hand, when the level of the provocation is low, the proximity time and image information for a predetermined time (for example, 20 seconds) before and after the proximity time are stored in the provocation level low folder 342. The provocation level low folder 342 is also overwritten based on a certain cycle, a certain period, etc.

[0071] When the provocation level is medium, the information input / output unit 328 stores the proximity time and image information for a predetermined time (for example, 20 seconds) before and after the proximity time in the provocation level medium folder 344. This stored data may also be overwritten.

[0072] The control unit 303 retrieves the recording information stored in the high provocation level folder 346, the medium provocation level folder 344, and the low provocation level folder 342 via the information input / output unit 328, and displays or outputs the information to the outside. When the provocation level is high, the output unit 330 can also generate a warning sound or voice from the speaker 309. The output of the alarm is not limited to sound or voice output, and the output unit 330 may generate light from a light-emitting diode or other light-emitting element instead of or in addition to sound or voice, or may output the alarm in a manner that can be perceived by a user inside the vehicle 10. The alarm may also be output to a person outside the vehicle 10.

[0073] Next, the details of the tailgating determination will be explained using the flowcharts of Figures 9 and 10. FIG. 9 shows an example of a flow of a tailgating determination process. The control unit 303 performs the following processing by having the configuration of each of the above units. This processing can be started, for example, when entering a highway, but it can also be started when traveling at a speed of about 20 km or more and 50 km or less. In other words, it can detect tailgating even on ordinary roads.

[0074] The control unit 303 starts acquiring image information (including date, time, camera identification number, etc.) from the vehicle photographing cameras 102 (R, F) (S10). Next, the control unit 303 measures traveling information such as the speed and acceleration of the vehicle 10 using the acceleration sensor 305 (S12), and stores this speed and acceleration information (S14). The acceleration information is a component in the forward and backward directions of the traveling direction of the vehicle 10 acquired from the acceleration sensor 305, but a three-axis composite value other than the gravitational acceleration may also be used.

[0075] More specifically, the control unit 303 combines the acquired speed and acceleration with information acquired from various sensors of the drive recorder 101 (F, R) to generate recording information. The control unit 303 associates the recording information with the image information acquired from the camera and stores them in the SD card 306 (storage unit). For example, the control unit 303 stores the date, time, camera identification number, front or rear type, and driving information (speed, acceleration, position coordinates, etc.) in association with each other in the storage means.

[0076] The control unit 303 analyzes the acquired image information and executes a vehicle determination process to determine whether a vehicle is present in front of or behind the vehicle 10 (S16). This vehicle determination process will be described later. The control unit 303 determines whether or not there is a vehicle (neighboring vehicle) in front of or behind the vehicle 10 based on the acquired image information (S18).

[0077] The determination of whether or not the vehicle is an approaching vehicle is based on, but not limited to, detection by a forward collision warning system (FCWS) or a rearward collision warning system (RCWS). For example, when the size of a vehicle in an image captured by the vehicle number detection camera 103 or the vehicle image capturing camera 102 becomes equal to or larger than a predetermined size, it can be determined that the vehicle has approached within 30 m, for example. Alternatively, proximity determination can be made by measuring distance using a distance measurement sensor that uses radio waves, sound waves, or the like, using a method other than image processing.

[0078] The proximity range for determining tailgating can be made variable. For example, the proximity range setting can be changed depending on the speed of the host vehicle 10. For example, when the vehicle 10 is traveling at a high speed, the distance between the vehicles increases, so the proximity range can be set wide, and when the vehicle is traveling at a low speed, the distance between the vehicles decreases, so the proximity range can be set narrow.

[0079] In step S18, if the determination unit 326 determines that no vehicle ahead or behind has entered the proximity area, the process returns to the image acquisition and travel information acquisition process (No in S18). In step S18, if the judgment unit 326 determines that a vehicle ahead or behind has entered the proximity area, the counting unit measures the number of times proximity is detected (proximity count) (S20), and the timing unit measures the time during which the vehicle is in proximity (proximity time) (S22).

[0080] The control unit 303 stores the measured information as count information, which includes the date, time, number of approaches, approach time, and vehicle number information of the approaching vehicle from which the image information was extracted. In order to reduce storage capacity, video information captured by the vehicle number detection camera 103 is not stored, and only the vehicle number information of the extracted nearby vehicles is stored, but if there is sufficient storage capacity, video information captured by the vehicle number detection camera 103 may also be stored.

[0081] The determination unit 326 performs a tailgating determination process to obtain a tailgating index P based on the number of approaches, the approach time, the acceleration (and / or the speed), etc. (S24). This tailgating determination process will be described later. The control unit 303 executes a process for each of the tilt levels according to the determined tilt level, and changes the storage method for the acquired video information (S26). The control unit 303 determines whether or not there is an instruction to end recording, and if not, returns the process to step S12, and if recording is to end, ends the process (S28). For example, when the car comes to a halt and the engine is turned off, the control unit 303 determines that recording has ended and ends the process.

[0082] FIG. 10 shows an example of a vehicle determination process flow. The rear vehicle number detection camera 103R will be described as an example. The image processing unit 321 identifies a target vehicle that is the target for determining tailgating from the image information captured by the vehicle number detection camera 103R (S31). At this time, if multiple vehicles are shown in the image information, it is preferable that the image processing unit 321 identifies one other vehicle on the same lane that is closest to the vehicle 10 as the target vehicle. Even when multiple vehicles are captured in an image, the accuracy of tailgating determination can be improved by configuring the system to determine the possibility of tailgating only for the extracted target vehicle. In addition, the accuracy of tailgating determination can be improved by configuring the system to determine the possibility of tailgating only for target vehicles in the same lane as the vehicle where tailgating is occurring.

[0083] When the vehicle number plate detection camera 103 captures an image at a distance of about 30 m with a 30-degree angle of view, which is the distance required for determining proximity, about three vehicles will be captured in the image, as shown in Figure 11. The image processing unit 321 identifies the target vehicle for which tailgating determination is to be performed from among these three vehicles.

[0084] There are various methods for identifying a target vehicle, but for example, the image processing unit 321 identifies the largest vehicle among multiple vehicles captured on the screen as the target vehicle. In the example of Fig. 11, vehicles 12, 13, and 15 are captured in the same image frame, and vehicle 15, which is the largest among them, is identified as the target vehicle.

[0085] As another method, a vehicle behind the vehicle 10 that is currently traveling in the same lane as the vehicle 10 may be identified as the target vehicle. In this case, the captured image is analyzed to extract the lanes (white lines, dotted lines, center divider lines, etc.) on the left and right of the vehicle 10, and the vehicle behind the vehicle 10 that is in this lane is identified as the target vehicle.

[0086] 11, if vehicle 15 were not present, vehicles 11, 12, and 13 would appear in the same image frame. Image processing unit 321 performs image analysis to trace backward the lanes 20 and 21 on the left and right of host vehicle 10, and identifies vehicle 11 present in the same lane as the target vehicle. For example, if the lane (road) on which the vehicle is traveling is curved, the vehicle directly behind the vehicle 10 may be in the adjacent lane, so it is effective to trace the lanes on the left and right of the vehicle 10 and identify target vehicles in the same lane as the vehicle 10.

[0087] As another method, angular velocity information or attitude information of the vehicle 10 is acquired using a gyro sensor (not shown) mounted on the drive recorder 101, and the image processing unit 321 corrects the position at which the target vehicle is identified in the image information using the acquired angular velocity information or attitude information. For example, when the vehicle is turning left, correction is made based on the angular velocity, and the vehicle located on the right side of the image frame is identified as the target vehicle. In this way, when the lane is curved, the system is configured to determine the possibility of tailgating only for vehicles located behind or in front of the vehicle along the lane, rather than directly behind or in front of the vehicle, thereby improving the accuracy of tailgating determination.

[0088] It is also possible to combine a plurality of the above examples to identify a target vehicle from a plurality of vehicle images captured within an image frame. Furthermore, in the above example, the vehicle number detection camera 103R located behind the vehicle 10 is described as processing for identifying the target vehicle, but the vehicle photographing camera 102R may be configured to identify the target vehicle.

[0089] Furthermore, for other vehicles located ahead of the vehicle 10, the vehicle photographing camera 102F or the vehicle number detection camera 103F of the drive recorder 101F can perform the same process as described above to identify the target vehicle. Furthermore, in the above example, the vehicle number detection camera 103 has been described as being fixed to the drive recorder 101R, but in the case of a drive recorder 101R in which the orientation of the lens of the vehicle number detection camera 103 can be changed, the control unit 303 may change the orientation of the lens of the vehicle number detection camera 103 so that it faces the target vehicle, and the lens may follow the target vehicle.

[0090] Next, the image processing unit 321 cuts out the part of the target vehicle from the image information of the camera (S33). In addition, the image processing unit 321 extracts the license plate area from the image captured by the vehicle license plate detection camera 103, and the control unit 303 performs character recognition on the image to extract the license plate number (automobile registration number or vehicle number) of the nearby vehicle (S35). The control unit 303 stores the extracted vehicle number in association with the image information in the SD card 306 (S37).

[0091] Next, the tailgating determination process (S24) in FIG. 9 will be described in detail. The tailgating determination process calculates a tailgating index P, which indicates the degree of possibility of tailgating, based on acceleration information from the acceleration sensor 305, changes in position information acquired by the GNSS sensor 307, or speed information acquired from the vehicle, and the number of times nearby vehicles are detected and the average detection time. The degree of possibility of tailgating due to approaching from the front of the vehicle ahead of the vehicle 10, calculated by the front drive recorder 101F, is expressed as an index P f The probability of tailgating due to approaching from behind the vehicle behind the vehicle 10, calculated by the rear drive recorder 101R, is expressed as an index P r Shown in.

[0092] The determination unit 326 determines the tailgating index P r , the tailgating index Pf The overall tailgating index P when the rear vehicle and the front vehicle are the same is calculated, for example, using the following formula. P r =avn r p t r q (Formula 1) P f =avn f p t f q (Formula 2) P=P r +P f (Formula 3) a is the vehicle acceleration coefficient, v is the vehicle speed coefficient, n r is the number of times that a rear vehicle has entered the proximity area, n f is the number of times the vehicle ahead has entered the proximity area, t r is the average detection time for a rear vehicle to be present in the proximity area, t f is the average detection time for a forward vehicle to be present in the proximity area. p is the exponent (e.g., 1.5) q is the exponent (e.g., 1.3)

[0093] The determination unit 326 sets a coefficient based on acceleration information from the acceleration sensor 305 (hereinafter referred to as acceleration coefficient a), and also sets a coefficient based on velocity information (hereinafter referred to as velocity coefficient v). The acceleration coefficient a is set, for example, as follows: Rear tailgating index P r against: -0.05G<acceleration of the vehicle: a=1 If vehicle acceleration is less than or equal to -0.05G, a=0 Let's say. Front tailgating index P f against: If vehicle acceleration is less than 0.05G, a=1 If the vehicle acceleration is 0.05G or less, a=0 Let's say.

[0094] Rear tailgating index P r In contrast, when the host vehicle acceleration is -0.05G or less, this means that the host vehicle 10 is suddenly decelerating, and in such a case, the distance to the vehicle behind may become shorter and closer. In order not to determine such a case of sudden deceleration of the host vehicle 10 as tailgating, the coefficient is set to zero when the host vehicle acceleration is -0.05G or less. In this case, since the coefficient is multiplied by zero, the tailgating coefficient, which is the calculation result of Equation 1, becomes zero, and it is not detected as tailgating. Even during normal driving, noise of about ±0.03G occurs. The value of -0.05G corresponds to the acceleration of lightly braking, and is a value that overcomes the influence of noise and allows the influence of braking to be detected. When braking suddenly, the acceleration is about -0.2G. For example, the threshold value may be set to a value of about -0.1 G, and only sudden deceleration when the brakes are applied more firmly may not be judged as tailgating.

[0095] Front tailgating index P f In contrast, when the host vehicle acceleration is 0.05G or more, this means that the host vehicle 10 is accelerating rapidly, and in such a case, the distance to the vehicle ahead may become shorter and closer. In order not to determine that such a case of rapid acceleration of the host vehicle 10 is tailgating (determine that there is no possibility of tailgating), the coefficient is set to zero when the host vehicle acceleration is 0.05G or more. In this case, since the coefficient is multiplied by zero, the tailgating coefficient, which is the calculation result of Equation 2, becomes zero, and tailgating is not detected.

[0096] For example, the threshold value may be set to a value of about 0.1 G, and only sudden acceleration when the accelerator is pressed more firmly may not be judged as tailgating. As described above, by configuring the system to determine that there is no possibility of tailgating when the vehicle's acceleration meets certain conditions, it is possible to prevent the system from mistakenly determining that tailgating is occurring when, for example, the acceleration changes when the vehicle brakes suddenly or starts suddenly, and a vehicle approaches in front or behind.

[0097] When the vehicle 10 is on an uphill or downhill slope, the acceleration generated when the accelerator or brake is applied differs from that when the vehicle is traveling on a flat road. When traveling on a slope like this, the determination unit 326 corrects the acceleration information acquired from the acceleration sensor based on the information acquired from the gyro sensor before determining whether the vehicle is tailgating, thereby canceling out the influence of the slope. By configuring it in this way, if the acceleration is different from normal driving, for example when driving on a slope, the value can be corrected before determining whether the vehicle is tailgating, thereby improving the accuracy of the determination.

[0098] The speed coefficient v is set, for example, as follows: If the vehicle speed is less than 20km / h, v=1 If the vehicle speed is less than or equal to 20km / h, v=0 Let's say. For example, when traveling at low speeds such as in a traffic jam, the distance between the vehicle and the vehicle ahead or behind narrows. In order not to determine such cases as tailgating, the coefficient is set to zero when the vehicle speed is 20 km / h or less. In other words, when traveling at 20 km / h or less, the coefficient is multiplied by zero, so the tailgating coefficient calculated using Equation 1 or Equation 2 becomes zero, and the vehicle is not detected as tailgating.

[0099] The threshold value of 20 km / h may be changed. For example, the threshold value may be set to 60 km / h or more, and tailgating may be determined only when driving on a highway. In this way, if the vehicle's speed is below a predetermined speed, the system will not judge it to be tailgating (it will judge that there is no possibility of tailgating), which will prevent the system from mistakenly judging that a vehicle approaching from in front or behind is tailgating when driving at low speed, such as in a traffic jam.

[0100] The vehicle speed can be obtained by a number of methods, including calculating it from changes in position information from the GNSS sensor 307, obtaining it from the speed information of the vehicle 10, calculating it by analyzing the flow of scenery around the vehicle 10 using image analysis, and calculating it by analyzing the movement of other vehicles that appear relative to the vehicle 10 using image analysis. In addition, whether the vehicle 10 is moving can be determined using the multiple calculation and acquisition methods described above, and also by analyzing the values ​​of the acceleration sensor and gyro sensor.

[0101] p and q are exponents of the number of detections that entered the proximity area (proximity count) and the average detection time that existed in the proximity area (average proximity time). By making the change in the provocation index calculated from the number of approaches and the average time of approach an exponential change rather than a linear change, the possibility of it being judged as provocation increases the more the number of approaches, and the longer the average time of approach, the possibility of it being judged as provocation increases.

[0102] The exponent for the number of proximity attacks is set to, for example, 1.5, and the exponent for the average proximity time is set to, for example, 1.3, so that the influence of the number of proximity attacks is evaluated higher than the influence of the average proximity time in determining whether or not a person is provoking a car. However, the exponents may also be adjusted so that the influence of the average proximity time is evaluated higher. The thresholds for the number of proximity events and the average proximity time can also be changed according to the speed of the host vehicle 10. For example, when the traveling speed of the host vehicle 10 is fast, the relative speed with other vehicles is less likely to change, and the host vehicle is less likely to enter or leave the proximity range, so the threshold for the average proximity time is set to be longer. Conversely, when the traveling speed is slow, the threshold for the average proximity time can be set to be shorter.

[0103] The threshold value for the number of proximity counts can also be changed. For example, if the traveling speed of the vehicle 10 is fast, the relative speed with other vehicles is less likely to change, and the vehicle is less likely to enter or leave the proximity range, so the threshold value for the number of proximity counts can be set low. Conversely, if the traveling speed is slow, the threshold value for the number of proximity counts can be set high. The coefficients and threshold values ​​can be changed from the drive recorder 101, the management terminal 105, the management server 106, the user terminal 107, and the like.

[0104] When the vehicle 10 is being tailgated, it may happen that the same vehicle tailgates the vehicle 10 from behind, then turns around and tailgates the vehicle 10 from the front. When the determination unit 326 determines that the vehicle behind and the vehicle ahead are the same vehicle, the tailgating index P r and the tailgating index P f The above are summed up to calculate the overall provocation index P. If the same vehicle is not tailgating from both the front and rear, the tailgating index P r Or, the tailgating index P by the vehicle ahead f Let P be the final influence index. By configuring the system to count repeated tailgating behavior by the same vehicle in front or behind in this way, it is possible to make more accurate tailgating judgments.

[0105] In this embodiment, whether or not the approaching acts are being committed by the same vehicle is confirmed by analyzing the image captured by the vehicle number detection camera 103 and checking whether or not the vehicle number information extracted matches. However, the present invention is not limited to this, and other confirmation methods may be used as long as it can be confirmed that the vehicles are the same or that there is a high possibility that they are the same vehicles. For example, the analysis of the images may confirm that the vehicles are likely to be identical if any one or any combination of the vehicle shape, vehicle size, vehicle height, vehicle width, vehicle color, vehicle model, etc. matches.

[0106] The front drive recorder 101F and the rear drive recorder 101R are connected directly via a wired or wireless in-vehicle network, or via a communication network via the management server 106, and the control unit 303 of one of the drive recorders 101 acts as the master, obtaining the tailgating index information from the other drive recorder 101 and adding them up to calculate the overall tailgating index P.

[0107] For each vehicle that is the target of tailgating judgment, for example, a four-digit number such as the vehicle number, the number of approaches counted by the counting unit 322, the approach time that the target vehicle is in proximity for each approach detection count, and the vehicle's acceleration information and vehicle speed information at the time of proximity detection are stored in the SD card 306 or in a temporary memory area of ​​the control unit for a period of, for example, 30 minutes, and the judgment unit 326 reads out this information, calculates the average approach time, and calculates the tailgating index P.

[0108] In addition, since running the recognition algorithm after detecting the approach of a vehicle will delay processing, it is better to recognize the vehicle number digits when detecting the approach of a vehicle. The processing order is vehicle number recognition followed by vehicle detection, and the vehicle number may be stored at the time of vehicle detection.

[0109] In this embodiment, a dangerous driving judgment system has been described in which the control unit judges the possibility of dangerous driving of a target vehicle based on the number of times the target vehicle identified based on the image information has entered a specified proximity area. By configuring in this way, it is possible to provide a mechanism for determining whether or not the photographed target vehicle is in a state where there is a high possibility that it is driving recklessly.

[0110] Furthermore, in this embodiment, a dangerous driving judgment system has been described in which the control unit judges the possibility of dangerous driving of a target vehicle based on the number of times the target vehicle identified based on the image information has entered a specified proximity area and the proximity time, which is the time the target vehicle is in the specified proximity area. By configuring it in this way, it is possible to provide a mechanism that can more accurately determine whether the photographed vehicle is likely to be driving recklessly based on two pieces of information: the number and duration of the close-communication acts.

[0111] In this way, the inventors have found that the number of times a target vehicle outside vehicle 10 has entered a predetermined proximity area and the proximity time, which is the time the target vehicle is in the proximity area, are indicators of the possibility that the target vehicle is engaging in reckless driving. Based on this finding, the present embodiment employs a configuration for determining the possibility of reckless driving as described above. In the present embodiment, the tilt determination is performed using both the number of approach times and the approach time, but the tilt determination may be performed using only one of them. Furthermore, although the average proximity time is used for the proximity time, it is also possible to use, for example, the total proximity time.

[0112] FIG. 12 is an explanatory diagram of an example of the deflection index determination table. FIG. 12 shows the number of times (n) the approach of a vehicle behind is detected and the tailgating index P calculated from the average of the approach detection times (average approach time t (seconds)). The judgment threshold is as follows: if the provocation index P is less than 30, there is no provocation level; if it is between 30 and 50, there is a low provocation level; if it is between 50 and 100, there is a medium provocation level; and if it is 100 or more, there is a high provocation level. The values ​​shown in the lightest gray are the parts where the provocation index P exceeds the low provocation level. The values ​​shown in the second lightest gray are the parts where the provocation index P exceeds the medium provocation level. The values ​​shown in the darkest gray are the parts where the provocation index P exceeds the high provocation level.

[0113] FIG. 13 is an example of an explanatory diagram of a deflection index judgment graph. 13, the vertical axis represents the provocation index P, and the horizontal axis represents the number of detections n. The graph shows that the time spent within the proximity range is 1 second, 4 seconds, 6 seconds, 11 seconds, 17 seconds, and 20 seconds, respectively. The determination unit 326 determines each provocation level based on a threshold value (high provocation level: 100 or more, medium provocation level: 50 or more, low provocation level: 30 or more).

[0114] For example, if a vehicle has entered the proximity area a total of three times, and the average proximity time exceeds 11 seconds, the determination unit 326 determines that the tailgating index P exceeds the threshold value 100 and the level of tailgating is high. As shown in the graph in Figure 13, even if the average time of approach is long, if the number of approaches is one, the system is set so that the "high level of tailgating" is not determined. In other words, the system is set so that the "high level of tailgating" is determined only if the number of approaches is two or more. By configuring in this way, it is possible to prevent a single act of approach that is not likely to be tailgating from being mistakenly determined to be a high level of tailgating.

[0115] In addition, the average approach time is capped at 20 seconds. This is because, while tailgating usually involves repeated approach and departure from the proximity range, proximity that exceeds 20 seconds is likely due to traffic congestion or other reasons, and is therefore unlikely to be tailgating. The control unit 303 executes processing by each of the fantasizing levels based on the fantasizing level determined by the determination unit 326, classifies the acquired video information, and stores it in an SD folder, which is a storage means.

[0116] FIG. 14 shows an example of a processing flow for each provocation level. In this flow, the control unit 303 changes the post-determination process depending on the level of tailgating. Specifically, depending on the determined tailgating level, different event folders are created for high, medium, and low tailgating levels, and different event recording is performed. By configuring it in this way, appropriate processing can be assigned depending on the level of aggressive driving.

[0117] The control unit 303 checks whether or not the tailgating has been determined based on the tailgating level of the determination unit 326 (S50). If the control unit 303 determines that tailgating is not occurring because the tailgating level is "no," it terminates the process (S50 is No). If tailgating is occurring, the control unit 303 executes a folder sorting process according to the level of tailgating (S50 is Yes).

[0118] If the "tailgating level is high" (Yes in S52), the control unit 303 stores the image information captured by the vehicle-photographing camera 102 in the "tailgating level high" folder. If the image information has already been temporarily stored in another area of ​​the SD card 306 or in the memory unit of the control unit 303, the image information is stored by moving or copying it to the "tailgating level high" folder. In addition, a warning sound indicating the possibility of being tailgated is output from the speaker 309 (S54).

[0119] If the level is "mid-level tailgating" (Yes in S56), the control unit 303 stores the image information captured by the vehicle photographing camera 102 in the mid-level tailgating folder. If the image information has already been temporarily stored in another area of ​​the SD card 306 or in the storage unit of the control unit 303, the image information is stored by moving or copying it to the mid-level tailgating folder (S58).

[0120] If the "side swerving level is low" (Yes in S60), the control unit 303 stores the image information captured by the vehicle photographing camera 102 in the side swerving level low folder. If the image information has already been temporarily stored in another area of ​​the SD card 306 or in the memory unit of the control unit 303, the image information is stored by moving or copying it to the side swerving level low folder (S62).

[0121] The high, medium, and low excitement level folders each have different storage policies for the data they store, with the high excitement level folder having a policy of storing more important data for a longer period of time. For example, in the case of high level of tailgating, all image information from the time when the target vehicle starts detecting proximity and then repeatedly approaches and leaves multiple times until the approach finally ends is stored in the high level of tailgating folder, and the image information stored in the high level of tailgating folder is not overwritten but is kept for a long period of time.

[0122] When the provocation level is in progress, for example, 20 seconds before and after the last proximity detection time is stored in the provocation level folder, and the image information stored in the provocation level folder is not overwritten but is stored for a long period of time. When the provocation level is low, for example, 20 seconds before and after the last proximity detection time is stored in the provocation level low folder, and the image information stored in the provocation level low folder is saved for, for example, three months, after which it is overwritten.

[0123] By configuring it in this way, the storage period for recorded images of vehicles with a high possibility of tailgating can be extended, making them useful for analysis and display for a longer period of time, and recorded images of vehicles with a low possibility of tailgating can be overwritten and deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity. The processing of the control unit 303 is such that, if the judgment determines that the level of tailgating is high, new recording information is stored in the high tailgating level folder separately from the recording information already stored, and if the judgment determines that the level of tailgating is low, the recording information already stored in the low tailgating level folder is deleted and the recording information is overwritten and stored.

[0124] In addition to the above example, it is also possible to increase the storage period in the order of low, medium, and high in the provocative folder. For example, the storage period for low, medium, and high in the provocative folder can be 3 months, 6 months, and permanently. By configuring it in this way, the storage period for recorded images of vehicles that are likely to be involved in tailgating can be extended, making them useful for analysis and display for a longer period of time, and recorded images of vehicles that are unlikely to be involved in tailgating can be deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity.

[0125] By configuring it in this way, recorded images of vehicles that are likely to be involved in tailgating can be saved in succession, making them useful for analysis and display for a longer period of time, and recorded images of vehicles that are unlikely to be involved in tailgating can be deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity.

[0126] It is also possible to lengthen the recording period of the saved video information in the order of low, medium, and high provocation folders. For example, the provocation folders can store video information for the provocation detection period of the last proximity detection, video information for the last three provocation detection periods from the last proximity detection, and all video information for multiple provocation detection periods, in that order.

[0127] In addition, in the above example, a warning sound is output only when the level of agitation is high, but the control unit 303 can also control the output unit 330 and change the warning sound or voice output from the speaker 309 according to the determined level of agitation. For example, when the level of tailgating is high, a warning sound or voice with a higher level of urgency can be sounded to alert the driver compared to when the level of tailgating is low.

[0128] The control unit 303 stores information on the location and date and time when the provocation occurred in association with the provocation judgment level in the SD card 206, and also transmits this information to the management terminal 105, management server 106, user terminal 107, etc. Furthermore, the drive recorder 101 of this embodiment is equipped with a GNSS sensor 307, and when the tailgating level is determined to be high, medium, or low, the location determined to be tailgating can be displayed on a map displayed on the management terminal 105, management server 106, and user terminal 107.

[0129] In addition, to indicate the level of the tilt at each position, for example, positions with a high tilt level can be displayed in red, positions with a medium tilt level in yellow, and positions with a low tilt level in blue. Furthermore, when the selection of the display of the position is accepted, it is possible to play back the recorded information stored in association with the position as a possible case of tailgating. In this embodiment, the recording information is stored in different storage areas depending on the level of aggressive driving. By configuring in this way, the storage area for the recording information can be allocated depending on the level of aggressive driving, making management and display easier.

[0130] In addition, if the camera's image sensor has an AI processing function that performs preprocessing, the image processing unit 321 may also transmit data indicating the results of image recognition based on the video captured by the camera to the management server 106.

[0131] The front drive recorder 101F can be provided with a button to determine whether the driver is actually being tailgated and to confirm whether the tailgating judgment is correct. If it is determined that the driver is tailgating, a warning sound or the like can be sounded as described above, and when a warning sound is sounded, the control unit 303 accepts input from the driver via a button as to whether the determination of tailgating was correct.

[0132] In this way, by receiving confirmation from the driver each time a tailgating judgment is made as to whether the tailgating judgment was correct, training data on correctly judged tailgating judgments is accumulated, and AI learning is performed to improve the accuracy of tailgating judgments. Using the number of approaches, the average approach time, and the provocation judgment result that is judged to be correct as training data, a provocation judgment model is generated by machine learning, with the number of approaches and the average approach time as input and the provocation judgment result as output.By inputting the number of approaches and the average approach time into this judgment model and having it learn, it is possible to output the provocation judgment result.

[0133] In addition, by using statistical methods or AI to adjust the thresholds for the number of close approaches and the average time of close approaches based on the thresholds for the number of close approaches and the average time of close approaches used in correctly determined tailgating, it becomes possible to make more accurate judgments about tailgating.

[0134] In addition, tailgating determination can be performed by cooperation between the front and rear drive recorders 101. For example, if the drive recorder 101R detects the approach of a rear vehicle even though the drive recorder 101F detects no vehicle ahead, it can determine that tailgating is occurring, increase the possibility of tailgating, or increase the value of the weighting coefficient multiplied in Equation 1 or Equation 2. Similarly, if drive recorder 101R detects no vehicle behind but drive recorder 101F detects the approach of a vehicle ahead, it can determine that the vehicle is tailgating, increase the possibility of tailgating, or increase the value of the weighting coefficient multiplied by equation 1 or equation 2.

[0135] 2 and 3, the vehicle image capturing camera 102 for recording images and the vehicle number plate detection camera 103 for detecting tailgating are provided in the same housing of the drive recorder 101, but these cameras can also be configured to be separate and removable. Alternatively, they can be mounted in separate housings from the beginning. In this case, the cameras are connected to each other via a wired or wireless network.

[0136] Alternatively, only one of the housings may be equipped with a large-capacity storage device for recording images such as an SD card 306, while the other housing may be equipped with only a camera, and video information captured by the housing equipped with only a storage device may be transmitted via a network to the housing equipped with the storage device and stored there. In such a configuration in which the two cameras can be separated, the vehicle recording camera 102 for recording and the vehicle number detection camera 103 for detecting tailgating can be installed in the most optimal locations, improving the accuracy of tailgating detection and making it easier to adjust the recording range.

[0137] In addition, when the vehicle photographing camera 102 for recording and the vehicle number plate detection camera 103 for detecting tailgating are integrated and configured to be separable, when they are integrated, there is an advantage that the installation location of the drive recorder 101 is one place and the place where the view to the front or rear is blocked can be one place. In this case, it is particularly preferable to configure the wiring between them to be hidden.

[0138] [Second embodiment] In the above-described embodiment, the drive recorder 101 includes the vehicle photographing camera 102 and the vehicle number plate detection camera 103. In this embodiment, the drive recorder 101 switches the camera used for distance measurement, vehicle detection, and vehicle number plate recognition processes depending on the distance to the target vehicle. The distance to the target vehicle may be the distance from the vehicle 10 to the target vehicle, which is the same as in the first embodiment. In this embodiment, the drive recorder 101 is assumed to include two cameras, a first camera 102C and a second camera 103C, in the same housing, as shown in FIG. 15. The angle of view of the first camera 102C is 130 degrees, the same as that of the vehicle photographing camera 102. The angle of view of the second camera 103C is 30 degrees, the same as that of the vehicle number plate detection camera 103. The external configuration and positional relationship of first camera 102C and second camera 103C may be the same as the positional relationship between vehicle photographing camera 102 and vehicle number plate detection camera 103 described in Fig. 2(A), and first camera 102C and second camera 103C may be provided at the same height and approximately parallel to the ground. However, first camera 102C and second camera 103C may be configured to be separable (for example, detachable) or configured as separate bodies, as in the first embodiment described above.

[0139] <2-1> First operation example The first operation example will be described with reference to FIG. 16. The control unit 303 of the drive recorder 101 switches a camera used for at least one of measurement of the distance to a target vehicle (for example, a vehicle directly ahead) or a following vehicle (for example, a vehicle directly behind) as the target vehicle, according to the distance to the target vehicle. In the present embodiment, the distance L to the target vehicle may be the distance measured based on the image information acquired by one or both of the first camera 102C and the second camera 103C.

[0140] Assume that the value of the distance L that is a condition for switching the camera is set to a switching distance L1 = 5 m. The switching distance L1 is an example of the first distance. When a target vehicle is approaching the vehicle 10 and the distance L between the vehicle 10 and another vehicle is greater than L1 and less than L2 (in the present embodiment, when L1 = 5 m < L < L2 = 100 m), the control unit 303 measures the distance L based on the image information acquired by the second camera 103C. When the distance L approaches to be L1 or less (in the present embodiment, when approaching to L ≦ L1 = 5 m or less), the control unit 303 switches the camera used for distance measurement from the second camera 103C to the first camera 102C. When the distance L once approaches within L1 = 5 m but then separates from it to be more than L1 = 5 m, the control unit 303 determines that the distance L is more than L1 = 5 m in a state where the distance is measured by the first camera 102C, and switches the camera used for distance measurement from the first camera 102C to the second camera 103C. When the target vehicle repeatedly approaches and separates from the vehicle 10 around L1 = 5 m, the control unit 303 frequently switches between the first camera 102C and the second camera 103C, but there is no problem. This is because when the distance L is around L1 = 5 m, both the first camera 102C and the second camera 103C have a margin for distance measurement and vehicle detection (for example, RCW). Regarding the recognition of the license plate number, it may be configured such that there is no problem in the recognition limit of license plate number recognition by each camera.

[0141] According to this first operation example, when the distance L between vehicle 10 and the target vehicle is long, the second camera 103C performs the processes of distance measurement, vehicle detection, and vehicle number recognition, and when the target vehicle is approaching vehicle 10 and the distance L between vehicle 10 and the other vehicle is short, the camera with a wide angle of view performs the processes of distance measurement, vehicle detection, and vehicle number recognition, thereby improving the accuracy of each process and enabling more accurate judgment of the possibility of dangerous driving.

[0142] <2-2> Second operation example Next, a second operation example will be described with reference to FIG. In the first operation example described above, depending on the configuration of drive recorder 101, even if there is a margin in the distance measurement and vehicle detection processes using first camera 102C and second camera 103C, there is a possibility that both first camera 102C and second camera 103C may reach their recognition limits for vehicle number recognition when distance L is about L1 = 5 m. In this case, there is a possibility that control unit 303 may not be able to recognize the vehicle number when switching cameras.

[0143] Therefore, it is preferable that control unit 303 alternately switches between first camera 102C and second camera 103C at predetermined time intervals (for example, every 50 ms). In this second operation example, control unit 303 selects whether to use only second camera 103C or alternately switch between the two cameras, second camera 103C and first camera 102C, depending on the distance measured by the camera.

[0144] For example, assume that the switching distance L3 is set to 10 m. The switching distance L3 is an example of the second distance. The distance L1=5 m described above is the recognition limit distance at which both the first camera 102C and the second camera 103C can recognize the vehicle number. However, the distance L3=10 m is a distance at which the first camera 102C cannot or has difficulty recognizing the vehicle number, but is a distance at which the second camera 103C can sufficiently recognize the vehicle number. Furthermore, the switching distance L3 is a distance at which both cameras can sufficiently measure distance and detect a vehicle. Here, in the distance range of L1 or more and L3 or less (in this embodiment, the distance L is 5 m to 10 m), the value measured by the second camera 103C is expected to be more reliable, while in the distance range of 0 m or more and less than L1 (in this embodiment, 0 m to 5 m), the value measured by the first camera 102C is expected to be more reliable. Therefore, the control unit 303 may use the value from one of the cameras that is expected to provide a more reliable value.

[0145] When the distance L is within the range of approximately L1 (approximately 5 m in this embodiment), distance measurement, vehicle detection, and vehicle number recognition are possible with both cameras, and values ​​can be acquired from both cameras, so the control unit 303 may select one of the values. Since the vehicle numbers recognized by both cameras may differ, for example, the control unit 303 may compare the vehicle numbers recognized when L1=5 m or more and decide which value to adopt, and may adopt the value from the camera that recognizes the same vehicle number, for example.

[0146] Another problem is the time required for distance measurement, vehicle detection, and vehicle license plate recognition. If the cameras are switched alternately every 50 ms, each camera must process the data within 100 ms. Even in this case, the distance L between vehicle 10 and the other vehicle is within 10 m, so it is unlikely that the relative speed is 20 km / h or greater. If the relative speed is 20 km / h, then the change is approximately 0.56 m in 100 ms, and so a judgment time (processing time) of 100 ms is considered acceptable.

[0147] In this way, when the distance L is equal to or greater than the switching distance L3 (=10 m), the control unit 303 may perform vehicle detection and vehicle license plate number recognition using the second camera 103C in 50 ms. When the second camera 103C determines that the distance is equal to or less than L3 (=10 m), the control unit 303 alternates between the first camera 102C and the second camera 103C every 50 ms. This switching allows the first camera 102C and the second camera 103C to perform vehicle detection and vehicle license plate number recognition processes essentially every 100 ms. While this embodiment describes a case in which vehicle detection and vehicle license plate number recognition are performed by alternately switching between the first camera 102C and the second camera 103C, performing at least vehicle license plate number recognition in this manner can reduce the possibility of the vehicle license plate number not being recognized.

[0148] [Third embodiment] In this embodiment, the following configuration is adopted as a configuration for measuring the distance L, which is the inter-vehicle distance determined from perspective (perspective view). The configuration of this embodiment will be described with reference to Figs. 18 and 19. The configuration of this embodiment can be applied, for example, to the configuration of the second operation example of the second embodiment described above.

[0149] The control unit 303 measures the distance to the target vehicle using image information acquired by the camera, using a measure calculated from a perspective view of the image information. The reference measure varies depending on the height of the camera from the ground, the camera direction, and the lens focal length. Therefore, the control unit 303 determines the reference measure line by aligning the camera with the horizon, assuming that the camera direction is horizontal to the ground.

[0150] The operation of this embodiment will be described with reference to FIGS. 18 and 19. The measurement setting line is, for example, a line parallel to the horizon as shown in FIGS. 18 and 19. The measurement setting line is an example of a reference position set for image information for distance measurement. Although the measurement setting lines are different between the first camera 102C and the second camera 103C, the control unit 303 sets the measurement setting line for each of the image information acquired by the first camera 102C and the second camera 103C. Assuming that the first camera 102C and the second camera 103C are at the same height from the ground and are oriented horizontally relative to the ground, it is necessary to align the horizons of the two cameras. Therefore, the control unit 303 first determines the camera height from the ground. For example, the camera height may be input by the user, but other methods are also possible. The camera height input by the user may be selected by the user from multiple options, such as 100 cm, 110 cm, 120 cm, and 250 cm. Control unit 303 identifies the difference between the images captured by first camera 102C and second camera 103C from the selected height, corrects the images to align with the horizon, and then measures the distance using the images captured by each camera.

[0151] The above method is based on the assumption that, for example, two cameras are installed at the same height from the ground and are oriented horizontally to the ground. In reality, however, the cameras can be aligned horizontally to the ground (i.e., perpendicular to the direction of gravity), but this can be cumbersome for the user, so the control unit 303 should automatically correct the alignment. Even if the camera is oriented slightly upward or downward, the control unit 303 should detect the camera angle and reflect this in the setting of the measure setting line.

[0152] Furthermore, the following modifications may be made. <3-1> When the target vehicle is a rear vehicle, the control unit 303 may determine whether the target vehicle is directly behind or not by drawing a virtual line without specifying the rear lane and determining whether the target vehicle is on the inside or outside of that line. Similarly, when the target vehicle is a front vehicle, the control unit 303 may determine whether the target vehicle is directly ahead or not by drawing a virtual line without specifying the front lane and determining whether the target vehicle is on the inside or outside of that line.

[0153] <3-2> The control unit 303 may have a function for setting a reference position such as the position of the horizon or the position of the vanishing point of the road in the captured image. Furthermore, the control unit 303 may have a function for setting a reference position in an image from one camera through a user operation, and for setting a reference position in an image from the other camera without a user operation (i.e., automatically) based on the installation positional relationship (arrangement) between the two cameras.

[0154] <3-3> The control unit 303 may have a function for setting a reference position, such as the position of the horizon or the position of the road's vanishing point, in a captured image. Furthermore, the control unit 303 may have a function for simultaneously displaying images from two cameras and displaying their respective reference positions in each image, and may automatically simultaneously display a reference position in the image of one camera that corresponds to a reference position set by a user operation for the image of the other camera. For example, when the telephoto reference position is set, the control unit 303 may display that position with a mark or line in the telephoto image. The control unit 303 may then calculate the corresponding wide-angle reference position and automatically display that position with a mark or line in the wide-angle image. This allows the user to easily align the reference positions of the two cameras by checking the deviation between the two and adjusting the installation of the device so that it is level or by manually adjusting the telephoto setting.

[0155] <3-4> The configurations of the modifications of this embodiment may be applied to an apparatus including a plurality of cameras with different angles of view and overlapping imaging ranges, such as the first camera 102C and the second camera 103C.

[0156] [Fourth embodiment] In this embodiment, the following configuration may be adopted as a configuration for recognizing the vehicle number.

[0157] <4-1> The control unit 303 may continuously (e.g., constantly) perform the vehicle number recognition process, rather than triggering the start of vehicle number recognition when the distance to the target vehicle or vehicle detection is detected. Continuously performing the vehicle number recognition process may refer to the control unit 303 repeatedly performing the vehicle number recognition process, for example, at predetermined intervals, while the vehicle 10 is traveling. Continuously performing the vehicle number recognition process may refer to outputting the vehicle number recognition result (a signal indicating that recognition is not possible or a recognized vehicle number (e.g., a four-digit number)) at predetermined intervals (e.g., every 50 ms), regardless of whether the vehicle distance is measured or a vehicle is detected. In this way, not only the vehicle number of the target vehicle but also data indicating whether recognition was successful or not can be recorded, along with data indicating the situation when the recognition process was performed, which can be used for analyzing the situation.

[0158] <4-2> The control unit 303 may record the vehicle number recognition results on the SD card 306 separately from video information (an example of image information) acquired by the camera. Furthermore, similar to the method of recording video information, the control unit 303 may create a continuous recording folder and an event folder on the SD card 306, and sequentially record video information in the continuous recording folder while overwriting it. When a predetermined event occurs, such as vehicle detection (e.g., RCW, FCW), an acceleration sensor, or manual operation, the video information may be moved from the continuous recording folder to the event folder, or the overwriting of the video information and vehicle number recognition results recorded in the continuous recording folder may be suppressed. Suppressing overwriting may be performed by prohibiting overwriting, but when overwriting is permitted for other reasons, it may also be possible to make it more difficult to permit overwriting, thereby making it more difficult for the video information and vehicle number information to be erased.

[0159] <4-3> The control unit 303 may continuously perform the vehicle number recognition process regardless of whether the vehicle number can be recognized or not, and continuously record the vehicle number information on the SD card 306. The vehicle number information may include, for example, the vehicle number if the vehicle number is recognized, and may further include information such as the time, latitude and longitude, vehicle speed, and acceleration as data indicating the situation when the vehicle number recognition process was performed. Continuous recording may refer to repeated recording at predetermined intervals while the vehicle 10 is traveling. Furthermore, the control unit 303 may continuously record still images (e.g., JPEG still images, an example of image information) based on image information captured by the camera at a predetermined cycle (e.g., 1 fps). The still images may be images captured by the first camera 102C, for example. However, the control unit 303 may also record images (e.g., JPEG still images) captured by the second camera 103C on the SD card 306 while continuously recording images by the first camera 102C.

[0160] <4-4> The control unit 303 may suppress overwriting of the vehicle number information and still images continuously recorded on the SD card 306 in response to distance measurement, vehicle detection, judgment, acceleration events (G events), and manual events, by copying them to a predetermined folder (for example, an event folder) or by applying a file lock, etc. Suppressing overwriting may be achieved by prohibiting overwriting, but in cases where overwriting is permitted due to other reasons, it may also be possible to make it difficult to permit overwriting and to make it difficult for moving image information and vehicle number information to be erased.

[0161] <4-5> The control unit 303 may repeatedly detect the approach of a rear vehicle (e.g., RCW / BSD) using a rear camera such as that of the drive recorder 101R, recognize the vehicle number, and if a vehicle with the same vehicle number is repeatedly seen approaching the front camera such as that of the drive recorder 101F, determine that the driving is malicious and dangerous, and perform processing according to the determination result. Alternatively, the control unit 303 may repeatedly detect the approach of a front vehicle (e.g., FCWS) using a front camera such as that of the drive recorder 101F, recognize the vehicle number, and if a vehicle with the same vehicle number is repeatedly seen approaching the rear camera such as that of the drive recorder 101R, determine that the driving is malicious and perform processing according to the determination result. Determining that the driving is malicious may be equivalent to determining that the driving is dangerous. The processing according to the determination result may be the processing performed when determining that the driving is dangerous, as described above, but may be a different processing.

[0162] [Fifth embodiment] In this embodiment, the following configuration may be adopted to detect a person outside the vehicle 10. <5-1> The drive recorder 101 may have a function to detect people outside the vehicle 10 and perform processing according to the detection results. The drive recorder 101 may be a camera that acquires image information of a planar image. However, a camera that acquires image information of a celestial image is preferable because it can capture a wider area and detect people. A camera that acquires image information of a celestial image is a camera that acquires image information by capturing an area of ​​a hemisphere or an area wider than a hemisphere. The image area of ​​a celestial image is circular or elliptical. The distortion (image distortion) caused by the imaging lens is smaller near the center of the celestial image, and the degree of distortion increases as one approaches the periphery (circumferential direction) in the radial direction. The object appears relatively larger near the center of the celestial image, and appears relatively smaller as one approaches the periphery in the radial direction. The celestial image may be, for example, a hemispherical image or a full celestial image. 20, the drive recorder 101 may be, for example, a drive recorder 101F for detecting a person outside the vehicle 10. The drive recorder 101F (an example of a third camera) may capture an image of the outside of the driver's seat or passenger seat of the vehicle 10 (for example, outside the window or through the windshield) and, when a dangerous act is committed (for example, when the vehicle is tailgated), detect the person who committed the dangerous act (for example, the tailgator). In FIG. 20, the tailgator is shown as "person P1."

[0163] In the drive recorder 101F, the position of the driver's seat or passenger seat window may be set as the area (hereinafter referred to as the "detection target area") for detecting a tailgating person. The shape, position, and size of the detection target area may be set by the user. This is because the areas showing the interior and exterior of the vehicle vary depending on the vehicle. For example, the control unit 303 may display an image captured by the drive recorder 101F on its own display unit (on the LCD if the drive recorder 101F has an LCD) and allow the user to set the area of ​​the image corresponding to the exterior of the vehicle as the detection target area through a user operation. The control unit 303 may also transmit an image captured by the drive recorder 101F to the user terminal 107. In this case, the user terminal 107 may display the image, allow the user to set the detection target area of ​​the image through a user operation, and notify the drive recorder 101F of the setting. As an example, when the image shown in FIG. 21(a) (in this example, a hemispherical image) is captured by the drive recorder 101F, detection target areas Ar1 and Ar2 are set as shown in FIG. 21(b), for example. The detection target area Ar1 corresponds to the position of the window, and the detection target area Ar2 corresponds to the position of the windshield. The shape of the detection target area may be any shape, and if the user can freely determine it, the position outside the vehicle 10 can be accurately identified. However, a quadrilateral such as a square or rectangle is easy for the user to set, and a polygon, ellipse, or the like may also be used.

[0164] Furthermore, when the control unit 303 detects a person from the detection target area, the control unit 303 may have a function of starting event recording as a predetermined process and notifying (e.g., issuing a warning) the person that event recording is in progress by a human-perceptible method such as light, sound, or voice. To achieve this, for example, the drive recorder 101F may be provided with a light-emitting unit in a location visible from outside the vehicle 10, or the drive recorder 101F may have a function of outputting a sound that can be heard outside the vehicle 10. Alternatively, the drive recorder 101F may be communicably connected to the vehicle 10 and may issue a notification in a manner linked to the vehicle 10, such as by turning on the hazard lights of the vehicle 10 or sounding a buzzer. In this way, when a person outside the vehicle is detected, image information acquired by the drive recorder 101F is recorded, and the situation when the person in the vehicle was detected can be confirmed using the image information, and the person outside the vehicle is notified that recording is in progress, thereby achieving an excellent effect in terms of crime prevention, such as preventing vehicle theft.

[0165] The control unit 303 may perform the above-mentioned predetermined process when it detects a person from the detection target area after determining that the following vehicle 40 is driving recklessly (for example, after detecting tailgating). For example, the control unit 303 may perform the above-mentioned predetermined process when it detects a person who is the same as an occupant (for example, the driver) of the following vehicle 40 from the detection target area after determining that the following vehicle 40 is driving recklessly (for example, after detecting tailgating). The same can be done for the drive recorder 101R, and the control unit 303 may determine that the preceding vehicle is driving recklessly.

[0166] Object detection technology can be applied to detect people outside the vehicle 10. Examples of object detection technology include detection using HoG features and SVM, and detection using Haar-like features based on the brightness and darkness of an image. Deep learning techniques such as R-CNN, YOLO, and SSD are particularly useful. When using deep learning, it is recommended to collect a large number of images of the object to be detected and tag the images with bounding boxes and object names as correct answers. These tagged images can be used to adjust the weights of the trained model layers to recognize specific objects.

[0167] <5-2> When the control unit 303 of the drive recorder 101 recognizes the face of a person in the vehicle 10 and records the captured image on the SD card 306, the control unit 303 may perform processing to make the person's face less recognizable. The processing to make the face less recognizable may be, for example, a process to mask the face, such as applying a mosaic or covering the face with another image, making it difficult for the human eye to recognize the face. For example, when recording an image, the control unit 303 may perform a process to mask the face of the person in the vehicle 10 automatically, without a user instruction. The control unit 303 may not perform a process to make the face less recognizable for faces outside the vehicle 10, or, if it does perform such a process, may record the image by recording the face as a separate image. Such recording is an example of recording the face of a person outside the vehicle in an identifiable manner. The reason for not performing a process to make the face less recognizable for faces outside the vehicle 10 is for crime prevention purposes. By configuring in this manner, the privacy of the legitimate user of the vehicle, such as the owner of the vehicle, can be protected, while the faces of people outside the vehicle who may be malicious can be recorded in an identifiable manner.

[0168] When the control unit 303 transmits image data of a captured image to the user terminal 107, for example, when transmitting a stream image, it is preferable to perform processing to make the faces of people in the passenger compartment of the vehicle 10 less visible using the method described above.

[0169] <5-3> As a predetermined process, the control unit 303 may perform a first process to make the faces of people inside the vehicle 10 less visible in the image area indicated by the image information acquired by the drive recorder 101F, and may also perform a second process to cancel the first process and make the image information acquired by the drive recorder 101F playable, and then record the image information after that. Even when viewing images captured by the drive recorder 101 using predetermined software (viewer) such as a PC viewer, the process to make the faces of people inside the vehicle 10 less visible may remain applied, but this process may be made more visible. The first process may be the same as the process to make the faces less visible described above. The second process may be a process to cancel the first process, such as removing a mosaic or removing an overlaid image (removing a mask), and may be a process to make the faces easier to understand for the human eye. To enable the release by the second process, the control unit 303 may perform, as the first process, a predetermined image process that enables the release, or may perform, as the first process, a process of recording image information that has not been processed to make it difficult to see the faces of people in the cabin of the vehicle 10, on the SD card 306 by a method that cannot be viewed by normal methods (for example, by making it a hidden file or encrypting it). In this way, it is possible to protect the privacy of people who are believed to be legitimate users of the vehicle, such as the owner of the vehicle, while making it possible to play back image information so that the faces of those people can be seen if necessary.

[0170] <5-4> The control unit 303 may perform the following processing based on the result of recognizing a human face from a captured image. The face recognition function for recognizing a human face from a captured image may be provided by the control unit 303, but may also be provided by an external device (e.g., a server device, a mobile terminal such as a user's smartphone) that can communicate with the drive recorder 101F. Referring to FIG. 21 , for example, if the driver D leans forward, the driver D's face may move upward in the image and into the detection target area Ar1. In this case, the control unit 303 may not perform processing to make the human face less visible if it recognizes a human face within the detection target area Ar1, and may perform processing to make the human face less visible if it does not recognize a face. The recognition of a human face within the detection target area Ar1 may be defined as a match with the face of the driver D registered in advance (i.e., successful face recognition), or may refer to the recognition of a face of some kind. Instead of setting a detection target area as in the present embodiment, face recognition may always be performed on the entire captured area. However, setting a detection target area and performing face recognition reduces the processing load. In this way, even if the face of a person who is thought to be a legitimate user of the vehicle, such as the owner of the vehicle, enters the detection target area, which is the area corresponding to the outside of the vehicle, due to a change in the person's posture, etc., the privacy of the person can be protected.

[0171] <5-5> When the control unit 303 records an image captured by a camera using the parking monitoring function, it is preferable that the control unit 303 does not perform processing that makes it difficult to view a person's face (i.e., stops processing that makes it difficult to view a person's face). The parking monitoring function is a function that records images captured while the vehicle 10 is parked. The parking monitoring function is a function for monitoring the interior of the parked vehicle 10 or the outside surroundings of the vehicle 10. When the engine of the vehicle 10 is in an off state, the control unit 303 receives power from an external battery and records images on the SD card 306. Regarding whether the vehicle 10 is parked, the control unit 303 may determine based on one or more of the following: the accessory power supply is turned off; the engine is turned off; power supply from the external battery has started; the vehicle speed is 0 km / h or a predetermined speed or less; and the location information acquired by the location information acquisition unit is predetermined location information (e.g., location information of the home, workplace, or parking lot). In this way, even if a person such as a thief is sitting in the driver's seat and the person's face is in an area that does not hit the window or windshield, the person's face can be seen.

[0172] <5-6> The inventors discovered that generating an image that has undergone a predetermined coordinate transformation (hereinafter referred to as "dewarping") to expand a celestial sphere image into a rectangular image or other image that is easily recognizable by AI can only achieve a low frame rate of, for example, 3 fps. Adding a person recognition process at a later stage is likely to further restrict the processing speed. Furthermore, when detecting people outside the vehicle 10 using object detection technology, applying the object detection technology to a dewarped image may improve detection accuracy rather than applying the object detection technology to the celestial sphere image. Therefore, the control unit 303 generates an image that has undergone a predetermined coordinate transformation using the detection target area (e.g., only the window area of ​​the vehicle 10) as the dewarped target area. The control unit 303 then applies object detection technology to the coordinate-transformed image to detect people outside the vehicle 10. This improves the accuracy of detecting people outside the vehicle 10 and also improves processing speed. Furthermore, at least two of the dewarp area of ​​the celestial spherical image that is the target of dewarping, the exposure calculation area, and the image recording area where the image is recorded on the SD card 306 may be set to be approximately the same range. For example, the control unit 303 may determine at least two of the dewarp area, the exposure calculation area, and the image recording area based on the set detection target area.

[0173] <5-7> The configuration of this embodiment can also be applied to imaging devices other than cameras mounted on vehicles, such as indoor cameras. The imaging device may be, for example, a security camera. The imaging device may capture an image of an indoor space such as a home or office, and if it recognizes a human face within a detection target area set at the position of a window or door, it may not perform processing that makes the human face difficult to see.

[0174] [Sixth embodiment] Regarding the sharpening process for sharpening the license plate (or only the portion showing the vehicle number) included in the image captured by the drive recorder 101, the following process may be adopted.

[0175] <6-1> The control unit 303 may sharpen the license plate in the image, for example, by deep learning. For example, a trained model that has previously trained on an image of a license plate may be prepared, and the control unit 303 may provide image information to this trained model for correction. If the drive recorder 101 captures a celestial image, a trained model that has trained on an image of a license plate included in the celestial image may be used, and the sharpening effect can be further enhanced by using a trained model that has trained on images of the same or similar type of image (for example, the degree of geometric deformation or the type of lens used for capturing).

[0176] The function for performing the sharpening of <6-2> and <6-1> may be installed in the drive recorder 101, but it is preferable that this function be installed on the viewer side and not provided in the drive recorder 101. In this way, the images recorded by the drive recorder 101 are not changed (processed), and therefore can be recorded in a state where the original images are maintained.

[0177] <6-3> The control unit 303 may generate new image information by sharpening the image indicated by the image information captured by the drive recorder 101 without changing it, and record both sets of image information. This is done so that the original image can be kept as it is, or, since tampering with the original image constitutes tampering, an image in which the license plate is sharpened can be obtained while leaving the original image as it is.

[0178] <6-4> The control unit 303 may sharpen the license plate portion without user operation (i.e., automatically) when playing back a video, but it is preferable to sharpen the license plate portion of an image that is paused while the license plate is displayed. This is based on the idea that the image from the drive recorder 101 is sharpened when it is actually played back, and the image is left as is until then.

[0179] <6-5> The control unit 303 may specify the range of the license plate area within the image without the user's specification (i.e., automatically), but it is also preferable for the user to specify it manually by encircling it. This makes it possible to eliminate the need for processing related to specifying the license plate area and to accurately specify the license plate area. Furthermore, the user can view an image that is as close to the original as possible.

[0180] <6-6> The control unit 303 may at least either display or record the sharpened image by adding information indicating that the image has been sharpened, such as "License plate sharpening processed." In this way, the user can know that the image is not the original image but an image after the license plate sharpening process.

[0181] [Seventh embodiment] The traffic signal may be recognized from the image captured by the drive recorder 101F, and the following processing may be performed.

[0182] <7-1> The control unit 303 may determine that the driving is dangerous when it detects from the captured image that the traffic light is red and a vehicle traveling in the same direction or in the opposite direction (opposite lane) attempts to enter the intersection. The processing according to the determination result may be the same as the processing performed when dangerous driving is determined as described above, but may also be a different processing.

[0183] <7-2> When the control unit 303 detects from the captured image that the traffic light is green, it may determine that the driving is dangerous when it is triggered by a vehicle entering (for example, crashing into) the vehicle on the side of the captured image where the traffic light is red (for example, in the intersecting direction). The processing according to the determination result may be the processing for determining dangerous driving as described above, but may also be a different processing.

[0184] <7-3> The control unit 303 may detect the flashing of a pedestrian traffic signal from the captured image, detect that the signal may soon change, and notify the driver. Such a flashing signal is information about the signal change in front of the driver. For example, there are pedestrian traffic signals that count down the time until the light changes to green or red, and this is the image of displaying that information.

[0185] <7-4> The control unit 303 may store data of detected speed signs on a map and notify the driver even if the speed sign cannot be recognized due to reasons such as an inability to recognize images. The speed sign data may include, for example, the speed limit and location information (e.g., latitude and longitude information) of the speed sign's installation location. The notification may be made, for example, when the vehicle 10 travels through or near the speed sign's installation location (e.g., within a predetermined distance, while traveling on the same road). The notification may be made by a method perceptible to humans, such as light, sound, or voice. The notification may include, for example, the speed limit indicated on the speed sign and whether the vehicle's current speed exceeds the speed limit. In this way, the stored speed can be used to notify the driver, for example, while traveling in the opposite lane. The control unit 303 may also transmit (transmit) the detected speed sign data to a server device or other device, such as another drive recorder, via communication, so that the data can be used as shared information or mapped to transmit the speed limit to other vehicles. The control unit 303 may store speed sign data received from a server device or other devices such as other drive recorders on a map, and may issue a notification based on this data even if the speed sign cannot be recognized.

[0186] <7-5> The control unit 303 may further store traffic light information in the vicinity of the vehicle while driving in the recording contents of the drive recorder 101. In this way, even if the traffic light is not recorded in the video, the color of the traffic light can be determined.

[0187] [Eighth embodiment] The drive recorder 101 may have the following functions to check behind the vehicle 10 when the vehicle 10 is reversing. The drive recorder 101 (for example, the drive recorder 101F) may have a function to detect an object captured on the drive recorder 101R and notify the driver (for example, issue an alert) when it detects that the vehicle is in reverse gear (in other words, when it determines that the gear is in reverse). The object may be, for example, a person or an obstacle that may collide with the vehicle 10. The control unit 303 may detect that the vehicle is in reverse gear (determine whether the gear is in reverse) based on a signal (specifically, a signal that identifies the gear position) input from the vehicle 10 via a connection terminal (not shown). The notification may be made by a sound, light, display, or other method that can be perceived by humans.

[0188] Furthermore, the control unit 303 may vary the notification (the manner of alert) depending on the distance from the vehicle 10 to the object. For example, when the distance to the object is a first distance or less, the control unit 303 may warn the user not to back up the vehicle 10 (for example, output a voice message such as "Don't back up!!"). When the distance from the vehicle 10 to the object is a little farther, for example, greater than the first distance but less than a second distance, the control unit 303 may alert the user (for example, output a voice message). When the distance from the vehicle 10 to the object is farther, for example, greater than the second distance, the control unit 303 may display an image captured by the drive recorder 101R on a display unit (for example, the display unit of the drive recorder 101), and further display the object included in the captured image surrounded by a figure such as a square, without making any sound related to the notification.

[0189] Furthermore, when the distance to the object is close, for example, when the distance is equal to or less than a first distance, the control unit 303 may regard this as an event trigger (a dangerous event) and perform event recording. This event recording may record images of the drive recorder 101R for a predetermined period before and after the distance to the object becomes close, but it may also be possible to record only images from the time when the distance to the object becomes close.

[0190] If the drive recorder 101 (e.g., the drive recorder 101F) is a communication type capable of communicating with an external server device or the like via a network, the control unit 303 may notify the occurrence of the event via the network. This notification may be a notification to register the location where the event occurred in map data, such as a facade map, registered in the server device or the like. If the distance from the vehicle 10 to the object is a short distance, the control unit 303 may count the cumulative time for this distance at the same location, and when the cumulative time reaches a certain threshold, may notify the user that the location where the event occurred will be registered in map data, such as a facade map. This map data may be map data stored in the drive recorder 101 or may be map data that can be acquired from an external device such as a server device. Display based on the acquired map data allows the user to visually grasp where an object that poses a risk of collision is located, contributing to safe driving. Note that in this embodiment, the drive recorder 101R does not have to be a device equipped with two or more cameras.

[0191] [Ninth embodiment] Other variations are possible as follows. For example, the rear camera for detecting tailgating can also be used as a front sign recognition camera. This rear camera for detecting tailgating corresponds to the vehicle number detection camera 103 of the drive recorder 101R in the above-described embodiment. The rear camera for detecting tailgating and the front sign recognition camera have a commonality in that a narrower angle of view is preferable compared to the recording camera. Therefore, the performance required for the rear camera for detecting tailgating and the front sign recognition camera is common, and by standardizing both, inventory can be reduced and the number of parts purchased can be increased, thereby reducing manufacturing and storage costs. In this way, by attaching the drive recorder 101R to the front of the vehicle 10, like the drive recorder 101F, the drive recorder 101R can be used for other purposes.

[0192] The rear camera for detecting tailgating can also be used as a camera for front ADAS (Advanced Driver Assistance Systems). Furthermore, the front camera image may also be equipped with an ADAS function so that it operates in cooperation with the rear camera for detecting tailgating. The rear camera for detecting tailgating can also be used as a camera for monitoring the driver. Additionally, an infrared spotlight can be attached to the rear camera for tailgating detection. The rear camera for detecting tailgating can also be attached to the front camera and integrated.

[0193] When the rear camera for detecting tailgating is integrated with the rear camera for recording, the two cameras are integrated so that the angle between them cannot be adjusted, whereas when the rear camera is integrated with the front camera as a camera for recognizing front signs or a camera for monitoring the driver, the two cameras can be integrated so that the angle between them can be adjusted.

[0194] The drive recorder 101 can be installed either at the front or rear of the vehicle 10, but can be configured to have both an attachment part that can be installed at the front of the vehicle 10 and an attachment part that can be installed at the rear. Alternatively, the drive recorder 101 can be configured to switch between using an attachment part that can be installed at the front of the vehicle 10 and an attachment part that can be installed at the rear.

[0195] Furthermore, the drive recorder 101F installed in the front of the vehicle 10 may have a mounting part that can also be used as an ADAS camera in front of the vehicle 10. Furthermore, the drive recorder 101F installed in the front of the vehicle 10 may have an attachment part that can also be used as a camera for capturing images of the rear of the vehicle 10 from the front of the vehicle 10.

[0196] The drive recorder 101 can further include an infrared projector built in. This is particularly useful when used as a camera that captures images of the rear of the vehicle 10 from the front of the vehicle 10. It is also possible to provide a cover or seal that physically hides the infrared projector. In particular, it is preferable to provide a cover instead of a filter in a mechanism for inserting a visible light cut filter. Furthermore, a mechanism for inserting a visible light cut filter may be provided in both the vehicle photographing camera 102 and the vehicle number plate detection camera 103, or in only one of them.

[0197] Furthermore, the configuration may include a mounting fixture that can be installed so that the axial direction of the cylindrical housing is in the up-down direction. In this case, for example, the vehicle number plate detection camera 103 can be installed so as to face downward, which makes it easier to recognize the license plate located on the bottom of the front or rear vehicle. Conversely, the vehicle number plate detection camera 103 can be installed facing upward, which makes it easier to recognize signs and signals.

[0198] In a configuration in which the vehicle 10 is equipped with both a front drive recorder 101F and a rear drive recorder 101R, the video can be stored in either the front or rear drive recorder, or can be transmitted to either one and recorded in the other. When recording is performed using one of the drive recorders 101F and 101R, the other device only needs to have the function of transmitting video to the other device, so the other device does not need to be a device that is recognized as a drive recorder, but only needs to be a device with a shooting function.

[0199] Even when the video is stored in both the drive recorder 101 and the drive recorder 101, the video can be transmitted to the other drive recorder 101, thereby allowing for redundant recording. In this case, the drive recorders 101 can be recorded by synchronizing their times via an in-vehicle network. In addition, it is also possible to distribute the load of processes that consume processor power, such as the tailgating determination process, between the front and rear drive recorders 101 and execute them.

[0200] In addition, the drive recorder 101 in this embodiment has been described as having two cameras, a vehicle number detection camera 103 and a vehicle photographing camera 102, but for example, the front drive recorder 101F may have only the vehicle photographing camera 102, and the rear drive recorder 101R may have two cameras. By using only a single camera for the front drive recorder 101F, the camera installed at the front, which tends to obstruct the driver's field of view, can be made smaller, allowing for a clearer driving field of view, and AI processing such as license plate recognition can be performed at the rear using images from the narrow-angle camera.

[0201] With this configuration, it is possible to make the cable between the front and rear devices thinner than in a configuration where the front is the drive recorder 101F and the rear is a single camera, and it also becomes easier to record images from two cameras, one with a narrow angle and one with a wide angle. In addition, when transmitting power from the front standalone camera to the rear drive recorder 101R, the front standalone camera needs to have a power input terminal and a video input terminal for the rear drive recorder 101R. An output terminal and a power supply output terminal may be provided.

[0202] Another method of power routing is to branch off power from a cigarette lighter socket or the like to supply it to the front standalone camera and the rear drive recorder 101R. The video signal is transmitted from the front standalone camera to the rear drive recorder 101R via the cigarette lighter or the like. This configuration allows for neat wiring as only one cable is required to connect to the front standalone camera. In particular, there are cases where it is difficult for an amateur to run multiple cables, such as when there is an airbag in the A-pillar, but this also makes it easy for users to do the wiring themselves as a DIY project.

[0203] Furthermore, in a configuration in which a standalone camera is used in the front and drive recorder 101R is used in the rear, the manual trigger button attached to drive recorder 101R is no longer located near the driver. Therefore, it is advisable to provide a manual trigger button on the standalone camera in the front as well. It is also a good idea to provide a microphone on the front camera alone, as this will allow for clear recording of the front-facing audio.

[0204] It is also possible to arrange the drive recorder 101F in the front and the standalone camera in the rear, and it is also possible to provide a mounting fixture and cable that allow such an arrangement. The management terminal 105, management server 106, user terminal 107, etc. can set and display where the drive recorder 101 or standalone camera shown in Fig. 1 is installed, and the processing content can be changed depending on the setting. Note that while it is preferable to display the installation position on the vehicle design as shown in Fig. 1, the installation position may also be set using text, such as front right, front left, front center, rear right, rear left, rear center, etc.

[0205] Depending on the installation locations of the drive recorder 101 and the standalone cameras as described above, the manual trigger button of the standalone camera can be disabled or enabled, or the manual trigger button of the drive recorder itself can be enabled or disabled according to the settings, and the buttons of the devices installed at the rear can be disabled or the buttons of the devices installed at the front can be enabled.

[0206] For example, with regard to the microphones mentioned above, the microphone to be given priority during playback may be determined according to the setting of the installation location. Also, for example, depending on the setting of the installation location, the correspondence between the captured front and rear video signals and the recorded front and rear video data may be switched so that the front video is properly played back as the front side in the PC viewer.

[0207] In addition to the method of using the number of approaches and the duration of approach as described above, tailgating can also be determined using the following method by combining image analysis, various other sensors, FCWS, and RCWS. A driver tailgating a vehicle in front wants to get as close as possible to the vehicle in front, but does not want to hit it. Therefore, they accelerate to approach, and when they are about to hit it, they suddenly brake. If the vehicle in front is moving, suddenly braking will increase the distance between them, so they want to get as close as possible again, and accelerate again. This will then put them in danger of hitting it, so they suddenly brake again. This driving cycle is repeated.

[0208] Therefore, when it is detected that the vehicle behind has accelerated and approached to a distance where a rear-end collision is possible, the vehicle suddenly decelerates and moves away from the vehicle 10, and then accelerates again and approaches to a distance where a rear-end collision is possible, The system controls the vehicle in a direction that is likely to be tailgating the vehicle behind. In this case, when the vehicle 10 is accelerating, if the vehicle behind accelerates faster than the vehicle and approaches close enough to cause a rear-end collision, the vehicle is controlled in a direction that indicates a high possibility that the vehicle behind is tailgating. Alternatively, when the vehicle 10 is decelerating and a vehicle behind approaches close enough to cause a rear-end collision, the vehicle is controlled in a direction that makes it less likely that the vehicle behind is tailgating.

[0209] Furthermore, it is detected whether the brake of the vehicle 10 is being applied, and when the rear vehicle is accelerating and approaching while the brake is being applied, the vehicle is controlled in a direction that indicates a high possibility that the rear vehicle is tailgating. In this case, if the vehicle behind accelerates and approaches after the brake is released, the system controls the vehicle in a direction that indicates a high possibility that the vehicle behind is tailgating.

[0210] In this embodiment, the drive recorder 101 (F, R) having the vehicle photographing camera 102 and the vehicle number detection camera 103 has been described, but instead of having the vehicle photographing camera 102 and the vehicle number detection camera 103 separated, a configuration in which each function is performed by a single camera may also be used.

[0211] Furthermore, in this embodiment, a configuration has been described in which the drive recorder 101 performs tailgating determination, but the present invention can also be applied to a network camera that does not have a relatively large storage unit for storing video images, such as an SD card 306, and transmits captured video images to the management server 106 via a network and stores them on the management server 106 side.

[0212] In addition, the tailgating detection system that determines the possibility of tailgating can be implemented not only in the drive recorder 101, but also in, for example, the vehicle 10 itself, a microcontroller 301, computer, server equipment, etc. installed in the vehicle 10, or a management server 106.

[0213] When implemented in the management server 106, the processor 603 of the management server 106 analyzes the image information received via the network and determines the possibility of tailgating. The processor 603 of the management server 106 may be configured to measure both or either of the number of proximity times and the proximity time, instead of the drive recorder 101 . The image information received via the network may not only be that from a specific vehicle, but may also be image information uploaded to the management server 106 by multiple users.

[0214] When the possibility of tailgating is determined by the management server 106, processing according to the tailgating determination level may also be performed on the management server 106. For example, image information and the like transmitted from a camera via a network can be sorted into a high-excitement level folder, a medium-excitement level folder, a low-excitement level folder, and the like on the management server 106 .

[0215] In addition, a control unit provided in the vehicle 10 itself may be configured to determine the possibility of tailgating as described above and execute processing according to the level of tailgating that is the result of the determination. In addition, a microcomputer, computer, server equipment, etc. installed in the vehicle 10 may be configured to determine the possibility of tailgating as described above and perform processing according to the level of tailgating that is the result of that determination, and various modifications are possible regarding the entity that performs each process.

[0216] In the above-described embodiment, the possibility of dangerous driving is determined based on the behavior of a target vehicle in front of or behind the vehicle 10. However, the possibility of dangerous driving may also be determined based on the behavior of the target vehicle when it is positioned to the side (for example, pulling over). In this case, the proximity area is also set to the side of the vehicle 10. In this case, if either of the drive recorders 10F, 10R can capture an image of the side of the vehicle 10, the possibility of dangerous driving may be determined based on the captured image, or a separate camera may be provided to capture an image of the side.

[0217] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0218] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations, functions, etc. may also be implemented in software, with a processor interpreting and executing a program that implements each function. Information such as the programs, tables, and files that implement each function can be stored in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.

[0219] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be assumed that almost all components are interconnected.

[0220] The scope of the present invention is not limited to the structures explicitly described in the specification, but also includes combinations of various aspects of the present invention disclosed herein. The structures of the present invention that are sought to be patented are specified in the appended claims, but it is the intention of the present inventors to claim structures disclosed in this specification in the future, even if they are not currently specified in the claims.

[0221] The present invention is not limited to the configurations described in the above-described embodiments. The components of each of the above-described embodiments and variations may be arbitrarily selected and combined. Furthermore, any component of each embodiment or variation may be arbitrarily combined with any component described in the Summary of the Invention or any component embodying any component described in the Summary of the Invention. The present invention also intends to obtain rights to these configurations through amendments or divisional applications of the present application. Even if a description is made of "in the case of..." or "when...," it is not intended to describe a configuration limited to that case or time. Configurations that are not limited to those cases or times are also disclosed, and the present invention intends to obtain rights to them. Furthermore, any descriptions that specify an order are not limited to this order. Configurations in which some parts are deleted or the order is changed are also disclosed, and the present invention intends to obtain rights to them.

[0222] Furthermore, we intend to obtain rights to the overall design or partial design by converting the application to a design registration. The drawings depict the entire device in solid lines, but they also include partial designs claimed for parts of the device. For example, a partial design can be a partial design for a part of the device, or a part of that part. A partial design can be a part of the device, or a part of that part. We intend to obtain rights not only for the overall design, but also for partial designs in which any part of the solid line portion of the drawing is drawn as a broken line. Furthermore, all of the modules, components, and parts inside the device's casing, shown in the drawings, are subject to independent commerce, and we intend to similarly obtain rights by converting the application to a design registration.

[0223] The above-described embodiment discloses at least the following configurations. (1) 1. A system comprising: The system has a control unit that determines the possibility of dangerous driving of a target vehicle based on the number of times the target vehicle, identified based on image information acquired by one or more cameras, has entered a predetermined proximity area. A system characterized by: The inventors have found that the number of times a target vehicle has entered a predetermined proximity area is an indicator of the possibility of dangerous driving. By configuring in this way, it is possible to provide a mechanism for determining whether a photographed target vehicle is likely to be driving recklessly. (2) The control unit may determine the possibility of dangerous driving of the target vehicle based on the number of times and a proximity time, which is the time during which the target vehicle is within the predetermined proximity area. Furthermore, the inventors have found that the possibility of dangerous driving can be grasped more accurately by referring to the number of times the target vehicle has entered a predetermined proximity area as well as the proximity time, which is the time that the target vehicle has been in the proximity area. By configuring in this way, it is possible to provide a system that more accurately determines whether the target vehicle that has been photographed is in a state where it is likely to be driving recklessly, based on the number and time of proximity acts. (3) The control unit may measure the number of times by detecting, based on the image information, that the target vehicle has entered the predetermined proximity area. This configuration makes it possible to detect intrusions into the proximity area using only image processing by the camera, without the need for a special sensor. However, it is also possible to use other sensors to detect intrusions into the proximity area in parallel with or in conjunction with image processing. (4) The possibility of dangerous driving may be expressed by a plurality of levels of dangerous driving, and the control unit may change the processing after the determination depending on the level of the dangerous driving. By configuring in this way, it is possible to allocate appropriate processing depending on the level of dangerous driving. (5) The control unit may store the recording information corresponding to the image information in different storage areas of the storage unit depending on the level of the dangerous driving. By configuring in this way, it is possible to allocate storage areas for recorded information according to the level of dangerous driving, making management and display easier. (6) The control unit may store the recorded information in a first storage area if the level of dangerous driving is high, and may store the recorded information in a second storage area having a shorter storage period than the first storage area if the level of dangerous driving is low. By configuring it in this way, the storage period for recorded images of vehicles with a high possibility of dangerous driving can be extended, making them useful for analysis and display for a longer period of time, and recorded images of vehicles with a low possibility of dangerous driving can be deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity. (7) If the level of dangerous driving is high, the control unit may store the recorded information in a first storage area that does not overwrite the recorded information to be stored, and if the level of dangerous driving is low, the control unit may store the recorded information in a second storage area that overwrites the recorded information to be stored. By configuring it in this way, the storage period for recorded images of vehicles with a high possibility of dangerous driving can be extended, making them useful for analysis and display for a longer period of time, and recorded images of vehicles with a low possibility of dangerous driving can be overwritten and deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity. (8) The control unit When the determination indicates that the level of the dangerous driving is high, the recording information is newly stored separately from the recording information that has already been stored. If the determination indicates that the level of the dangerous driving is low, the already stored recorded information may be deleted and the new recorded information may be stored. By configuring it in this way, recorded images of vehicles with a high possibility of dangerous driving can be saved in succession, making them useful for analysis and display for a longer period of time, and recorded images of vehicles with a low possibility of dangerous driving can be deleted after a certain period of time has passed since the analysis was completed, thereby reducing storage capacity. (9) The control unit may be configured not to determine that the driving is dangerous when the acceleration of the vehicle satisfies a predetermined condition. By configuring it in this way, it is possible to prevent the acceleration from changing when, for example, the driver suddenly brakes or takes off suddenly, and to prevent the driver from mistakenly judging the approach of a vehicle in front or behind as dangerous driving. (10) The predetermined condition may be that the absolute value of the acceleration is equal to or greater than a threshold value. By configuring it in this way, for example, when the driver brakes suddenly or starts suddenly, it is possible to prevent the absolute value of acceleration from exceeding a threshold value and the approach of a vehicle in front or behind from being mistakenly determined to be dangerous driving. (11) The acceleration may be corrected based on information obtained from a gyro sensor. By configuring it in this way, if the acceleration is different from that during normal driving, for example when driving on a slope, the value can be corrected before determining whether the vehicle is driving recklessly, thereby improving the accuracy of the determination. (12) The control unit may be configured not to determine that the driving is dangerous when the speed of the vehicle is equal to or lower than a predetermined speed. With this configuration, it is possible to prevent the approach of a vehicle ahead or behind when traveling at low speed due to traffic congestion, for example, from being mistakenly determined to be dangerous driving. (13) The control unit may be configured not to determine that the level of dangerous driving is high if the number of times the target vehicle has entered the predetermined proximity area within a predetermined time is less than two. This configuration makes it possible to prevent a single approaching act that is not likely to be dangerous driving from being erroneously determined to be a high level of dangerous driving. (14) The control unit may include an output unit that outputs a warning when it is determined that there is a high possibility of dangerous driving. With this configuration, a warning can be issued to alert the driver when a vehicle with a high possibility of dangerous driving is approaching. (15) The control unit may extract the target vehicle from the plurality of vehicles captured in the image information, and determine the possibility of reckless driving for the extracted target vehicle. By configuring in this manner, even if multiple vehicles are captured in the image, the possibility of dangerous driving can be judged for only the extracted target vehicle, thereby improving the accuracy of the judgment. (16) The target vehicle may be a vehicle that is present on the same lane as the subject vehicle. By configuring in this way, the possibility of reckless driving can be judged only for vehicles in the same lane as the vehicle in which reckless driving is occurring, thereby improving the accuracy of the judgment. (17) If the lane on which the vehicle is traveling is curved, it is preferable to determine that the vehicle located at a position within the image information corrected based on information obtained from a gyro sensor is the vehicle located on the same lane. By configuring in this way, when the lane is curved, the possibility of dangerous driving can be judged only for vehicles located behind or in front of the vehicle along the lane, rather than directly behind or in front of the vehicle, thereby improving the accuracy of the judgment. (18) The plurality of cameras may include a first camera which is a vehicle photography camera with a wide angle of view for photographing a wide area including the target vehicle, and a second camera which is a vehicle number photography camera with a narrow angle of view for photographing the vehicle number of the target vehicle. By using multiple cameras with different angles of view in this manner, the accuracy of identifying the target vehicle's license plate number and other details is improved compared to when only the first camera, which is a wide-angle vehicle-photography camera, is used, making it possible to more accurately determine the possibility of dangerous driving. (19) The plurality of cameras may include a first camera and a second camera for photographing the target vehicle, the first camera having a larger angle of view than the second camera, and the control unit may perform at least one of measuring the distance to the target vehicle, detecting the target vehicle, and recognizing the vehicle number of the target vehicle using the second camera when the distance to the target vehicle is greater than a first distance, and using the first camera when the distance to the target vehicle is equal to or less than the first distance. By configuring in this manner, the camera used for at least one of measuring the distance to the target vehicle, detecting the target vehicle, and recognizing the vehicle number of the target vehicle is switched depending on the distance to the target vehicle, thereby improving the accuracy of each process and enabling more accurate judgment of the possibility of dangerous driving. (20) The plurality of cameras may include a first camera and a second camera for photographing the target vehicle, the first camera having a larger angle of view than the second camera, and the control unit may recognize the vehicle number of the target vehicle using the first camera and the second camera. By configuring in this way, it is possible to reduce the possibility that the vehicle number will not be recognized when the camera is switched. (twenty one) When the distance to the target vehicle is greater than a second distance, the control unit recognizes the vehicle number of the target vehicle using the second camera, and when the distance to the target vehicle is less than the second distance, the control unit recognizes the vehicle number of the target vehicle using the first camera and the second camera. By configuring in this way, it is possible to reduce the possibility that the vehicle number will not be recognized when the camera is switched. (twenty two) The control unit may identify the installation height of the first camera and the second camera, and measure the distance to the target vehicle based on the identified height, a reference position set for the image information acquired by the first camera, and a reference position set for the image information acquired by the second camera. By configuring in this manner, the influence of the shift in the horizon due to the difference in the image captured by the first and second cameras is corrected, thereby improving the accuracy of measuring the distance to the target vehicle using the first and second cameras. (twenty three) The control unit may continuously perform the process of recognizing the vehicle number while the vehicle is traveling, and may record the result of the recognition and data indicating the situation when the recognition process was performed, regardless of whether the vehicle number is recognized or not. By configuring it in this way, it is possible to record not only the vehicle number of the target vehicle, but also data to determine whether or not recognition was successful, as well as data showing the situation when the recognition process was carried out, which can be useful for analyzing the situation. (twenty four) The control unit may detect a person outside the vehicle using a third camera that captures an image of the interior of the vehicle, and may perform processing according to the detection result. By configuring the vehicle in this manner, it is possible to perform processing according to the detection result of a person outside the vehicle using a camera that takes pictures of the interior of the vehicle. (twenty five) The control unit has a function of setting an area of ​​the image area indicated by the image information acquired by the third camera that corresponds to outside the vehicle as a detection target area, and detects people who appear within the set detection target area as people outside the vehicle. By configuring in this manner, the areas showing the inside and outside of the vehicle in the image area indicated by the image information acquired by the third camera may differ depending on the vehicle in which the camera is installed, but people outside the vehicle can be detected more accurately. (26) When the control unit detects a person outside the vehicle, as the specified processing, it may record the image information acquired by the third camera and notify the person outside the vehicle that recording is in progress. By configuring it in this way, when a person outside the vehicle is detected, the image information acquired by the third camera is recorded, and the situation when the person in the vehicle was detected can be confirmed using the image information, and people outside the vehicle are notified that recording is being performed, thereby providing excellent security against crimes such as vehicle theft. (27) As the specified processing, the control unit may record the faces of people inside the vehicle in the image area indicated by the image information acquired by the third camera by performing processing to make the faces difficult to see, and record the faces of people outside the vehicle in a manner that makes the faces identifiable. By configuring it in this way, it is possible to protect the privacy of people who are believed to be legitimate users of the vehicle, such as the owner of the vehicle, while recording the faces of people outside the vehicle who may be malicious in a way that allows their faces to be identified. (28) As the predetermined processing, the control unit may record the image information after performing a first processing that makes it difficult to see the faces of people inside the vehicle in the image area indicated by the image information acquired by the third camera, and a second processing that cancels the first processing and makes the image information acquired by the third camera reproducible. In this way, the privacy of a person who is considered to be a legitimate user of the vehicle, such as the owner of the vehicle, is protected, and image information can be reproduced so that the face of the person can be identified if necessary. (29) The control unit records image information acquired by the third camera in a manner that enables identification of the face of a person captured within a detection target area, which is an area outside the vehicle, and even if a face is recognized within the detection target area, if the face is recognized to be a specific face, the control unit performs processing to make the face less visible. In this way, even if the face of a person who is thought to be a legitimate user of the vehicle, such as the owner of the vehicle, enters the detection target area, which is an area corresponding to the outside of the vehicle, due to a change in posture, etc., the privacy of the person can be protected. By setting the detection target area and performing face recognition, the processing load can also be reduced. (30) As the specified processing, the control unit records the faces of people inside the vehicle in the image area indicated by the image information acquired by the third camera by performing processing to make the faces difficult to see, but when recording while the vehicle is parked, it is preferable that the control unit does not perform the processing to make the faces difficult to see. This protects the privacy of people who are believed to be legitimate users of the vehicle, such as the owner of the vehicle, while also making it easier to see the faces of people inside the vehicle when the vehicle is parked and there is a risk of theft, thereby providing excellent security effects. (31) The image information acquired by the third camera is image information of a celestial sphere image, and the control unit performs a predetermined coordinate transformation on an image of the detection target area in the celestial sphere image, and detects a person outside the vehicle based on the transformed image. By doing so, it is possible to improve the accuracy of detecting people outside the vehicle 10 and also improve the processing speed. (32) The second camera may be disposed at a position that does not interfere with the angle of view of the first camera. This configuration can prevent the inconvenience of part of the image from being lost from the first camera, which is a vehicle-photographing camera with a wide angle of view. (33) The lens of the second camera may be oriented more downward than the lens of the first camera. By orienting the lens of the first camera, which is the vehicle number detection camera, downward in this way, it becomes easier to photograph and analyze the license plate attached to the bottom of the vehicle. (34) The plurality of cameras are a rear camera that captures an image behind the vehicle and a front camera that captures an image in front of the vehicle, When the target vehicle identified based on the first image information acquired by the front camera is the same as the target vehicle identified based on the second image information acquired by the rear camera, the control unit may calculate a determination result of the possibility of dangerous driving by combining the determination result of the possibility of dangerous driving of the target vehicle determined based on the first image information acquired by the front camera and the determination result of the possibility of dangerous driving of the target vehicle determined based on the second image information acquired by the rear camera. By configuring in this way, reckless driving repeatedly performed by the same vehicle in front or behind can be totaled, making it possible to make a more accurate judgment on reckless driving. (35) A drive recorder that has one or more cameras and functions as any of the above systems. By configuring it in this way, it is possible to provide a drive recorder equipped with a mechanism for determining whether the subject vehicle in the video is likely to be driving recklessly. (36) The plurality of cameras may include at least a first camera with a wide angle of view for capturing an image of a wide area including the target vehicle, and a second camera with a narrow angle of view for capturing an image of the target vehicle's license plate number, all of which are mounted in the same housing. By configuring the drive recorder in this manner, it is possible to provide a drive recorder that can capture an image of a wide area including the target vehicle while accurately detecting the license plate number of the target vehicle. (37) A program for causing a computer to realize the functions of the control unit of any of the above systems is provided.

[0224] The inventions described in (1) to (37) above can be combined in any way. For example, a configuration may be created by adding at least a portion of the configuration of at least one of the inventions described in (2) and subsequent items to all or a portion of the configuration of the invention described in (1). In particular, an invention may be created by adding at least a portion of the configuration of at least one of the inventions described in (2) and subsequent items to the invention described in (1). Furthermore, any configuration may be extracted from the inventions described in (1) to (37) and combined. The applicant of this application intends to obtain rights to inventions including these configurations. Furthermore, even if a description is made of "in the case of..." or "when...," it is not intended to describe a configuration limited to that case or time. These are merely examples of better configurations, and the applicant intends to obtain rights to configurations other than these cases or times. Furthermore, any descriptions that specify an order are not limited to this order. Configurations in which some parts are deleted or the order is changed are also disclosed, and the applicant intends to obtain rights to them. [Explanation of symbols]

[0225] 101F...Front drive recorder, 101R...Rear drive recorder, 102...Vehicle photographing camera, 103...Vehicle number detection camera, 105...Management terminal, 106...Management server, 107...User terminal, 301...Microcomputer, 302...Communication processing unit, 303...Control unit, 304...DVR controller, 305...Acceleration sensor, 306...SD card, 307...GNSS antenna, 308...Wireless communication antenna, 309...Speaker, 321...Image processing unit, 322...Counting unit, 324...Timekeeping unit, 326...Determination unit

Claims

1. a control unit having a function of determining the possibility of dangerous driving of a target vehicle based on the number of times that the target vehicle, which is identified based on image information acquired by one or more cameras, has entered a predetermined proximity area; The control unit does not determine that the target vehicle is driving recklessly when the acceleration of the target vehicle satisfies a predetermined condition, The predetermined condition is: The acceleration corresponds to a predetermined sudden deceleration, and the target vehicle is a rear vehicle, or the acceleration corresponds to a predetermined sudden acceleration, and the target vehicle is a forward vehicle; At least one of A system characterized by:

2. The system of claim 1 , wherein the acceleration is corrected based on information obtained from a gyro sensor.

3. a control unit having a function of determining the possibility of dangerous driving of a target vehicle identified based on image information acquired by one or more cameras; the target vehicle is a vehicle that is present on the same lane as the host vehicle, If the lane on which the vehicle is traveling is curved, the vehicle present at a position in the image information corrected based on information acquired from a gyro sensor is determined to be the vehicle present on the same lane. A system characterized by:

4. a control unit having a function of determining the possibility of dangerous driving of a target vehicle identified based on image information acquired by a plurality of cameras; The plurality of cameras include a first camera and a second camera as cameras for photographing the target vehicle, the first camera has a larger angle of view than the second camera; The control unit performs at least one of measuring the distance to the target vehicle, detecting the target vehicle, and recognizing the vehicle number of the target vehicle using the second camera when the distance to the target vehicle is greater than a first distance, and using the first camera when the distance to the target vehicle is equal to or less than the first distance. A system characterized by:

5. When the distance to the target vehicle is greater than a second distance, the control unit recognizes the vehicle number of the target vehicle using the second camera, and when the distance to the target vehicle is less than the second distance, the control unit recognizes the vehicle number of the target vehicle using the first camera and the second camera. The system of claim 4.

6. The control unit specifies the installation height of the first camera and the second camera, and measures the distance to the target vehicle based on the specified height, a reference position set for image information acquired by the first camera, and a reference position set for image information acquired by the second camera.

6. A system according to claim 4 or 5.

7. The control unit continuously performs a process of recognizing the vehicle number while the vehicle is traveling, and records the result of the recognition and data indicating the situation when the recognition process was performed, regardless of whether the vehicle number was recognized or not. The system according to any one of claims 4 to 6.

8. the control unit detects a person outside the vehicle using a third camera installed inside the vehicle, and performs processing according to the detection result; The control unit has a function of setting an area corresponding to the outside of the vehicle as a detection target area among the image areas indicated by the image information acquired by the third camera, and detects a person appearing within the set detection target area as a person outside the vehicle. The system according to any one of claims 4 to 6.

9. The control unit performs a first process to make the faces of people inside the vehicle less visible in the image area indicated by the image information acquired by the third camera, and a second process to cancel the first process and make the image information acquired by the third camera reproducible, as predetermined processes, and then records the image information. The system of claim 8.

10. the image information acquired by the third camera is image information of a celestial sphere image, The control unit performs a predetermined coordinate transformation on an image of the detection target area in the celestial sphere image, and detects a person outside the vehicle based on the transformed image.

10. The system according to claim 8 or 9.

11. a control unit having a function of determining the possibility of dangerous driving of a target vehicle identified based on image information acquired by one or more cameras; The likelihood of risky driving is expressed as a plurality of risky driving levels; The control unit has a function of changing a process after the determination depending on the level of the dangerous driving, the control unit has a function of storing recording information corresponding to the image information in different storage areas of the storage unit according to the level of the dangerous driving, The control unit stores the recorded information in a first storage area when the level of the dangerous driving is high, and stores the recorded information in a second storage area having a shorter storage period than the first storage area when the level of the dangerous driving is low. A system characterized by:

12. a control unit having a function of determining the possibility of dangerous driving of a target vehicle identified based on image information acquired by one or more cameras; The likelihood of risky driving is expressed as a plurality of risky driving levels; The control unit has a function of changing a process after the determination depending on the level of the dangerous driving, the control unit has a function of storing recording information corresponding to the image information in different storage areas of the storage unit according to the level of the dangerous driving, The control unit stores the recorded information in a first storage area that does not overwrite the recorded information when the level of the dangerous driving is high, and stores the recorded information in a second storage area that overwrites the recorded information when the level of the dangerous driving is low. A system characterized by:

13. a control unit having a function of determining the possibility of dangerous driving of a target vehicle identified based on image information acquired by one or more cameras; The likelihood of risky driving is expressed as a plurality of risky driving levels; The control unit has a function of changing a process after the determination depending on the level of the dangerous driving, the control unit has a function of storing recording information corresponding to the image information in different storage areas of the storage unit according to the level of the dangerous driving, The control unit When the determination indicates that the level of the dangerous driving is high, the recording information is newly stored separately from the recording information that has already been stored. When the determination indicates that the level of dangerous driving is low, the already stored recorded information is deleted and the new recorded information is stored. A system characterized by:

14. The control unit determines the possibility of dangerous driving of the target vehicle based on the number of times the target vehicle has entered a predetermined proximity area. A system according to any one of claims 3 to 13.

15. A program for causing a computer to realize the functions of the control unit of the system according to any one of claims 1 to 14.

Images