JP2019028483A - On-board device and driving support device - Google Patents

Abstract

To suppress the occurrence of processing delay and to make it possible to grasp a problem in driving operation such as an interruption to an own vehicle when a driving condition is grasped by processing rear-view video images of the own vehicle.SOLUTION: An area of a detection frame with reference to the number, location, and size that is predetermined according to the driving condition of an own vehicle is allotted in an image frame, and an image recognition of rear-view video images is performed while being limited in the area of each detection frame. A load to recognition processing is drastically reduced, and it becomes easier to detect other vehicles that are within an important location. In roads such as express highways where a plurality of lanes exist, a dedicated detection frame is allotted so as to be able to distinguish a plurality of driving lanes. A driving is supported by recording an event or outputting a warning in a case of an other vehicle detected in the detection frame, which is regarded as a high-risk interruption driving, when the own vehicle changes its lane to the lane in front of the other vehicle. A trend of driving is grasped based on the frequency of lane changes and the history of interruption frequencies.SELECTED DRAWING: Figure 7

Description

  The present invention relates to a vehicle-mounted device and a driving support device.

  Conventionally, for example, an in-vehicle device such as a digital tachograph recognizes various situations based on images taken by an in-vehicle camera, records the recognition result, and supports driving using the recognition result. It has been broken.

  For example, Patent Document 1 discloses a collision prevention apparatus for a moving body that captures the rear with a camera mounted on the host vehicle, detects another vehicle from the image, and avoids a collision or abnormal approach of the vehicle. Further, it is shown that a vehicle that is overtaking is detected with high accuracy, and the possibility of a collision is predicted in consideration of the turn signal of the own vehicle, the steering angle of the steering wheel, and the like, and an alarm is issued.

  Patent Document 2 discloses a lane change support device that allows a driver to recognize the reliability of an approaching vehicle warning so that a safer lane change can be executed. In addition, an imaging means for imaging the rear of the host vehicle, an approaching vehicle detection means for detecting an approaching vehicle based on the image, an alarming means for issuing an alarm when an approaching vehicle is detected, and an alarm instruction other than an approaching vehicle alarm A warning command means for commanding, and a detection reliability judgment means for judging the detection reliability of the approaching vehicle when the lane side to be changed is instructed by the direction indication means, and the warning command means indicates the detection reliability of the approaching vehicle. It has been shown to issue an alarm.

  Further, Patent Document 3 discloses a driving evaluation device that appropriately evaluates driving operations for changing lanes. Specifically, the position of each lane marking on the road lane marked on the road is recognized from the video taken by the in-vehicle camera, and the distance from the left and right ends of the vehicle to each section line is detected and recorded along with the time. . Further, information indicating whether or not the direction indicator is operating is also recorded along with the time. When analyzing the recorded data, after detecting the lane change start time based on the distance for each lane change event, the data is searched in the direction going back from this point to identify the operation start time of the direction indicator To do. A time difference between two times is set as an evaluation target, and a result of further statistical processing is output as an evaluation result. A list is displayed so that a comparison with the evaluation standard value, a tendency of multiple crew members, and a comparison between individual differences can be made.

JP 2000-285245 A JP 2004-213290 A JP 2017-33270 A

  As shown in Patent Literature 1 to Patent Literature 3, various situations are recognized on the vehicle based on the video captured by the in-vehicle camera, and the recognition result is recorded, or driving is supported using the recognition result. can do. However, in order to recognize video in real time, a huge amount of image data has to be processed in a short time, so it will be recognized unless hardware is installed such as a high-performance expensive CPU. There is concern about the possibility of delays or situations where recognition is difficult.

  Moreover, although the technique of patent document 1 can detect the situation of other vehicles that are overtaking, it is not possible to recognize the problem of the driving operation of the own vehicle driver when the own vehicle changes the traveling lane (lane). Can not. Specifically, a dangerous driving situation in which the distance between the host vehicle and the other vehicle is too close cannot be detected when the host vehicle changes the travel lane and enters the front of the other vehicle. In the case of such an interruption, there is a possibility that the driver of the other vehicle that has been interrupted hurts and suddenly brakes, not only causing trouble to the other vehicle as a driving manner violation, but also causing a contact accident etc. Cause.

  Further, in the technology of Patent Document 2, when the own vehicle changes lanes, an alarm regarding another approaching vehicle can be output. However, after the own vehicle overtakes another vehicle, the own vehicle changes lane and the front of the other vehicle is changed. It is impossible to detect the driving situation that interrupts.

  Further, in the technique of Patent Document 3, it is possible to evaluate whether or not the driver's direction indicator operation is appropriate in time when the own vehicle changes lanes. It is not possible to evaluate whether or not

  The present invention has been made in view of the circumstances described above, and its purpose is to suppress the occurrence of processing delay when trying to grasp the driving situation by processing the video behind the host vehicle, An object of the present invention is to provide an in-vehicle device and a driving support device capable of grasping a driving operation problem such as an interruption of the own vehicle.

In order to achieve the above-described object, the vehicle-mounted device and the driving support device according to the present invention are characterized by the following (1) to (5).
(1) An image processing unit that inputs and processes at least a video signal output from an in-vehicle camera that captures the rear of the vehicle;
Backward movement detecting a moving body other than the vehicle within a detection frame pre-assigned in an image frame based on a rear image captured by the in-vehicle camera when the vehicle is traveling in a forward direction. A body detection unit;
An output processing unit for controlling data to be recorded for the moving body detected by the backward moving body detection unit;
A vehicle-mounted device characterized by comprising:

  According to the vehicle-mounted device having the configuration (1), the backward moving body detection unit limits the image processing range to the range of the detection frame, so that the processing load is greatly reduced and the occurrence of delay is prevented. The In addition, by assigning a detection frame to an appropriate position, it is possible to easily detect a rear moving body that exists in a highly dangerous position, such as a rear vehicle that is traveling in an adjacent lane and is approaching the host vehicle. Become.

(2) When the vehicle is traveling on a road on which a plurality of travel lanes exist, the backward moving body detection unit travels in another travel lane adjacent to the travel lane in which the vehicle is traveling. A dedicated detection frame for detecting a moving object is used as the detection frame,
The vehicle-mounted device according to (1) above, wherein

  According to the vehicle-mounted device having the configuration of (2) above, by using the dedicated detection frame, the rear that exists in a highly dangerous position, such as a rear vehicle that travels in an adjacent lane and approaches the host vehicle. It is possible to easily detect the moving object.

(3) The output processing unit recognizes the situation in which the vehicle changes lanes and interrupts in front of another moving body based on the presence or absence of another moving body detected by the dedicated detection frame, and reflects the output in the output.
The vehicle-mounted device according to (2) above, wherein

  According to the vehicle-mounted device having the configuration (3), since it is possible to recognize a high-risk interrupt driving operation performed by the driver of the host vehicle, it can be used, for example, for an alarm output for supporting safe driving. In addition, based on the result of analyzing the recorded information, it is possible to give guidance to the driver on safe driving.

(4) The output processing unit records the number of lane changes and the number of interruptions of the vehicle, evaluates the information, and reflects the result in the output.
The on-vehicle device according to (2) or (3) above, wherein

  According to the vehicle-mounted device having the above configuration (4), information on the number of lane changes and the number of interruptions of the vehicle is evaluated, so that a tendency such as whether or not the driver is driving safely on a daily basis is grasped. It becomes possible. Therefore, it is possible to output an alarm to a driver who performs dangerous driving on a daily basis or to specify a driver who needs guidance for safe driving.

(5) The vehicle-mounted device according to any one of (1) to (4) above,
About the moving body detected by the rear moving body detection unit, an alarm generation unit that generates an alarm that supports safe driving of the vehicle;
A driving support apparatus comprising:

  According to the driving support apparatus having the configuration (5), a warning can be output for a driving with high risk such as an interruption due to a lane change of the own vehicle, for example, so that safe driving can be supported.

  According to the vehicle-mounted device and the driving support device of the present invention, it is possible to suppress the occurrence of processing delay when trying to grasp the driving situation by processing the video behind the host vehicle. In addition, it becomes possible to grasp the problem of driving operation such as interruption due to the lane change of the own vehicle.

  The present invention has been briefly described above. Further, the details of the present invention will be further clarified by reading through a mode for carrying out the invention described below (hereinafter referred to as “embodiment”) with reference to the accompanying drawings. .

FIG. 1 is a block diagram illustrating a configuration example of an operation management system according to an embodiment of the present invention. FIG. 2 is a flowchart showing a characteristic operation example-1 of the digital tachograph according to the embodiment of the present invention. FIG. 3 is a flowchart illustrating a specific example of detection frame selection processing. FIG. 4A is a front view showing an example of the relationship between the image frame of the rear image obtained when the host vehicle is traveling backward and each detection frame, and FIG. 4B is obtained when the host vehicle is traveling forward. It is a front view which shows the example of the relationship between the image frame of the back image | video produced | generated, and each detection frame. FIG. 5 is a plan view illustrating an example of each vehicle detection area behind the host vehicle when traveling on a road having a plurality of lanes. FIG. 6 is a plan view showing an example of a positional relationship when the host vehicle cuts in front of another vehicle. FIG. 7 is a flowchart showing a characteristic operation example-2 of the digital tachograph according to the embodiment of the present invention.

Specific embodiments relating to the present invention will be described below with reference to the drawings.
<Outline of system configuration and operation>
A configuration example of the operation management system 5 in the embodiment of the present invention is shown in FIG.

  The operation management system 5 shown in FIG. 1 is introduced as equipment of a business operator such as a trucking company or a bus company. The operation management system 5 manages the operation status of each vehicle such as a truck or a bus. An operation recording device (hereinafter referred to as a digital tachograph) 10 mounted on each vehicle as an in-vehicle device, The office PC 30 is installed in an office or the like. The digital tachograph 10 and the office PC 30 are connected via a network 70 so that they can communicate with each other.

  The office PC 30 is composed of a general-purpose computer device installed in the office, and manages the operation status of the vehicle. The network 70 is a packet communication network such as the Internet to which the radio base station 8 that performs wide area communication with the digital tachograph 10 and the office PC 30 is connected, and relays data communication performed between the digital tachograph 10 and the office PC 30. . Communication between the digital tachograph 10 and the radio base station 8 may be performed by a mobile communication network (portable network) such as LTE (Long Term Evolution) / 4G (4th Generation) or a wireless LAN (Local Area Network). Network).

  The digital tachograph 10 is mounted on a vehicle, and records operation data such as entry / exit time, travel distance, travel time, travel speed, speed over, engine speed over, sudden start, sudden acceleration, sudden deceleration.

  The digital tachograph 10 according to the present embodiment also has a drive recorder function and a driving support function in addition to the above functions. That is, when an abnormal situation such as a collision of a vehicle equipped with the digital tachograph 10 is detected, a trigger signal is output, and data including an image is automatically recorded and stored for a predetermined time in synchronization with the trigger. Can do. In addition, for example, when the host vehicle travels forward or back, if an approaching moving body (another vehicle) is detected, an alarm can be output to assist driving.

  The digital tachograph 10 shown in FIG. 1 includes, as hardware, a CPU (microcomputer) 11, a speed I / F (interface) 12A, an engine rotation I / F 12B, an external input I / F 13, a sensor input I / F 14, and GPS reception. Unit 15, camera I / F 16, nonvolatile memory 26A, volatile memory 26B, recording unit 17, card I / F 18, audio I / F 19, RTC (clock IC) 21, SW input unit 22, communication unit 24, display unit 27, In addition, an analog input I / F 29 is incorporated.

  The CPU 11 comprehensively controls each unit of the digital tachograph 10 according to a program incorporated in advance. The nonvolatile memory 26A holds in advance an operation program executed by the CPU 11, constant data and a table referred to by the CPU 11, and the like. The nonvolatile memory 26A is a rewritable memory, and the stored data can be updated as necessary.

  The recording unit 17 records data such as operation data and video. A memory card 65 possessed by a crew member is detachably connected to the card I / F 18. The CPU 11 writes data such as operation data and video to the memory card 65 connected to the card I / F 18. A built-in speaker 20 is connected to the audio I / F 19. The speaker 20 emits sound such as an alarm.

  The RTC 21 (timer) keeps the current time. The SW input unit 22 is input with ON / OFF signals of various buttons such as a warehousing button and a warehousing button. The display unit 27 is composed of a liquid crystal display (LCD) and displays alarms and the like in addition to communication and operation states.

  A vehicle speed sensor 51 that detects the vehicle speed is connected to the speed I / F 12A, and a speed pulse from the vehicle speed sensor 51 is input. The vehicle speed sensor 51 may be provided as an option in the digital tachograph 10 or may be provided as a device different from the digital tachograph 10. A rotation pulse from an engine rotation speed sensor (not shown) is input to the engine rotation I / F 12B.

  The input of the external input I / F 13 includes a brake signal indicating ON / OFF of the brake of the host vehicle, a winker signal indicating the operating state of the left and right direction indicators (winkers), and a shift state (forward / reverse distinction of the automatic transmission). A shift signal indicating that is included) is applied from an external device (not shown).

  The sensor input I / F 14 is connected to an acceleration sensor (G sensor) 28 that detects acceleration (G value) (senses an impact), and receives a signal from the G sensor 28. Examples of the G sensor include those having a method of reading mechanical displacement due to acceleration as vibration or a method of optically reading, but are not particularly limited. The G sensor detects an impact from the front of the vehicle (detects a deceleration G), may also detect an impact from the left and right directions (detects a lateral G), or an impact from the rear of the vehicle. May be detected (acceleration G may be detected). The G sensor is composed of one or a plurality of sensors so that these accelerations can be detected.

  Signals such as a temperature sensor (not shown) for detecting the engine temperature (cooling water temperature) and a fuel amount sensor (not shown) for detecting the fuel amount are input to the analog input I / F 29. CPU11 detects various driving | running states based on the information input via these I / F.

  The GPS receiving unit 15 is connected to the GPS antenna 15a, receives a radio wave of a signal transmitted from a GPS (Global Positioning System) satellite, calculates and acquires information on a current position (GPS position information).

  A plurality of in-vehicle cameras 23 and 23B are connected to the input of the camera I / F 16. In the present embodiment, one on-vehicle camera 23 is installed in the vehicle interior in a state where it is fixed in a direction in which a scene such as a road ahead in the traveling direction of the host vehicle can be photographed. Accordingly, in the video imaged by the in-vehicle camera 23, a preceding vehicle existing ahead of the host vehicle, a white line indicating a traveling lane boundary during traveling, and traffic regulation indications (such as a speed limit) on the road surface appear. The other in-vehicle camera 23B is installed in the passenger compartment in a state where it is fixed in a direction that allows photographing of a scene such as a road behind the host vehicle.

  The in-vehicle cameras 23 and 23B include image sensors in which, for example, 300,000, 1,000,000, and 2,000,000 pixels are arranged on an imaging surface that is imaged through a fisheye lens. The image sensor includes a known sensor such as a CMOS (complementary metal oxide semiconductor) sensor or a CCD (charge coupled device) sensor.

  The video signals output from the in-vehicle cameras 23 and 23B are converted into digital signals representing gradation and color for each pixel by the internal circuit of the camera I / F 16 and output from the camera I / F 16 as image data for each frame. The

  The video (image data) taken by each of the in-vehicle cameras 23 and 23B is recorded as time series data by the operation of the recording unit 17, but is repeatedly overwritten so as to be recorded for a predetermined time. The predetermined time is a time corresponding to several seconds (for example, 2 seconds, 4 seconds, 10 seconds, etc.) before and after the accident so that the situation of the accident can be understood when the accident occurs. Images captured by the cameras 23 and 23B may be recorded as a set of still image data or may be recorded as moving image data. Images before and after the accident are stored in the memory card 65 and further displayed on the display unit 33 of the office PC 30.

Moreover, the digital tachograph 10 of this embodiment is equipped with a driving support function such as (1) to (5) shown below.
(1) A function for outputting an alarm when the distance between the host vehicle and the preceding vehicle is too close.
(2) A function of outputting an alarm when the vehicle deviates from the range of the traveling lane in which the host vehicle is traveling.
(3) A function of outputting an overspeed warning when the traveling speed of the host vehicle exceeds the speed limit of the road marking.
(4) A function of notifying the driver of the presence of another vehicle approaching from behind when the host vehicle is moving forward.
(5) A function that informs the driver of the presence of surrounding obstacles when the host vehicle is moving backward.

  In order to realize the functions (1) to (5) described above, it is necessary to perform predetermined image recognition by processing image data of videos taken by the in-vehicle cameras 23 and 23B. In other words, the position and distance of the preceding vehicle is identified by image recognition, the relative position between the white line of the lane boundary and the host vehicle is detected, the speed limit of the road marking is detected, the vehicle behind and various obstacles It becomes necessary to detect objects. For example, the image recognition is performed by extracting the movement amount and the moving direction of the shape feature from the previously captured video and the current captured video.

  Image recognition as described above can be realized by executing a predetermined recognition algorithm according to a program in which the CPU 11 is incorporated. However, when the amount of data of the image to be processed is large, the load on the CPU 11 required for image recognition becomes very large, so that processing in real time becomes difficult and detection delay may occur. In particular, when images from a plurality of in-vehicle cameras 23 and 23B are processed simultaneously or a plurality of recognition targets are detected at the same time, there is a concern about the occurrence of delay. Therefore, in the present embodiment, when performing image recognition, a detection frame is provided as described later to limit the data range to be processed.

  When the communication unit 24 performs wide area communication and is connected to the wireless base station 8 via a mobile network (mobile communication network), the communication unit 24 communicates with the office PC 30 via the network 70 such as the Internet connected to the wireless base station 8. Communicate. The power supply unit 25 supplies power to each unit of the digital tachograph 10 when the ignition switch is turned on.

  On the other hand, the office PC 30 is configured by a PC (personal computer) that operates on a general-purpose operating system. The office PC 30 functions as an operation management device and includes a CPU 31, a communication unit 32, a display unit 33, a storage unit 34, a card I / F 35, an operation unit 36, an output unit 37, a voice I / F 38, and an external I / F 48. .

  The CPU 31 comprehensively controls each unit of the office PC 30. The communication unit 32 can communicate with the digital tachograph 10 via the network 70. Further, the communication unit 32 can be connected to various databases (not shown) connected to the network 70 and can acquire necessary data.

  In addition to the operation management screen, the display unit 33 displays an accident video, a hazard map, and the like. The storage unit 34 holds various programs such as system analysis software for displaying video received from the digital tachograph 10 and displaying vehicle position information on a map.

  A memory card 65 is detachably attached to the card I / F 35. The card I / F 35 receives operation data measured by the digital tachograph 10 and stored in the memory card 65. The operation unit 36 includes a keyboard, a mouse, and the like, and accepts operations of an office manager. The output unit 37 outputs various data. A microphone 41 and a speaker 42 are connected to the audio I / F 38. The manager of the office can also make a voice call using the microphone 41 and the speaker 42. When a vehicle accident occurs, the manager of the office makes an emergency call or contacts the police.

  An external storage device (storage memory) 54 is connected to the external I / F 48. The external storage device 54 stores an accident point database (DB) 55, an operation data DB 56, and a hazard map DB 57. In the accident point database (DB) 55, GPS position information (latitude and longitude) of the vehicle at the time of the accident transmitted from the digital tachograph 10 is registered. In the operation data DB 56, as the operation data, in addition to loading / unloading time, speed, travel distance, etc., rapid acceleration / deceleration, sudden steering, speed over, engine speed over, etc. are recorded. Registered in the hazard map DB 57 is map data in which marks representing points where accidents have occurred in the past (accident points) are superimposed on the map. In addition, the hazard map may describe an area where a disaster such as a natural disaster is expected, an evacuation site, or the like.

  When the CPU 31 reads out the hazard map of the designated area (for example, the area including the accident point) from the hazard map DB 57 and displays it on the display unit 33, the CPU 31 acquires the data of the accident point registered in the accident point DB 55, Marks representing these accident points are superimposed on the map to generate a new hazard map. The manager of the office can immediately see the latest accident location on the map (hazard map).

<Description of characteristic functions>
<Operation example-1>
FIG. 2 shows a characteristic operation example-1 of the digital tachograph 10 according to the embodiment of the present invention. That is, when the CPU 11 of the digital tachograph 10 executes the operation shown in FIG. 2, the other vehicle approaching from the rear is detected from the rear image while the host vehicle is moving forward, and the event information is recorded. Or output an alarm to support driving. The operation of FIG. 2 will be described below.

  In the case where the CPU 11 processes a rear image obtained by shooting by the in-vehicle camera 23B, in order to reduce the processing load, the processing target area is set to a predetermined number of detection frames (multiple) in each image frame. Limited to each area. Further, the CPU 11 automatically selects an appropriate detection frame in step S11 according to the situation of the host vehicle. This process will be described later in detail.

  In step S12, the CPU 11 processes the image data within the range of each detection frame selected in S11 for the rear video, and executes predetermined image recognition. Thereby, moving bodies, such as other vehicles which exist behind, can be detected at the time of advance of the own vehicle. Further, when a moving body is detected within the range of each detection frame, it is possible to identify whether or not the moving body is approaching by monitoring changes in the size and changes in the relative position with the host vehicle. . In addition, when using a specific detection frame for monitoring a range close to the host vehicle, a moving body detected in the detection frame may be unconditionally regarded as an “approaching moving body”. .

  If the “moving body approaching” is detected based on the rear image when the host vehicle is moving forward, the CPU 11 proceeds from S13 to S14. Then, the CPU 11 outputs a warning indicating that there is a moving body (another vehicle) approaching the host vehicle from behind, for example, as a voice message from the speaker 20 to notify the driver, thereby supporting safe driving. At the same time, the CPU 11 records event information indicating that “an approaching moving body” has been detected, for example, on the memory card 65 (S14).

<Selection of detection frame>
A specific example of the “detection frame selection” process executed by the CPU 11 in S11 of FIG. 2 is shown in FIG. By this processing, an appropriate detection frame can be automatically selected according to the situation. The processing of FIG. 3 will be described below.

  In step S21, the CPU 11 identifies forward / reverse of the host vehicle by referring to, for example, a signal indicating a shift state of the automatic transmission. If the host vehicle is in the forward state, the process proceeds from S21 to S22. If the host vehicle is in the reverse state, the process proceeds to S25.

  In step S <b> 22, the CPU 11 selects the detection frames (plurality) assigned in advance for advancement. In step S25, the CPU 11 selects the detection frames (plurality) assigned in advance for backward movement.

  In step S23, the CPU 11 identifies whether or not there is a plurality of traveling lanes on the road on which the host vehicle is currently traveling. For example, the number of driving lanes may be acquired as road information specified based on the current position of the host vehicle and road map information, or the driving lane information may be acquired based on the recognition result of the in-vehicle camera 23 or 23B. The number may be specified. Further, when the vehicle speed is equal to or higher than a predetermined value such as when driving on a highway, it may be considered that a plurality of driving lanes exist.

  When there are a plurality of travel lanes, the CPU 11 proceeds to the processing from S23 to S24, and selects a predetermined dedicated detection frame for identifying a plurality of travel lanes as the detection frame. By using this dedicated detection frame, it is possible to individually detect the presence or absence of a moving body traveling in each traveling lane.

<Specific examples of detection frames>
FIG. 4A shows an example of the relationship between the image frame 100A of the rear image obtained when the host vehicle is traveling in the back and each detection frame. FIG. 4B shows an example of the relationship between the rear image frame 100B obtained in a state where the host vehicle travels forward and each detection frame.

  In the image frame 100A shown in FIG. 4A, seven mutually independent rectangular detection frames F11, F12, F13, F14, F15, F16, and F17 are assigned to different positions in the frame.

  That is, when the host vehicle moves backward, as in the detection frames F11 to F17 shown in FIG. 4A, attention is paid to various places in the rear image, that is, the periphery of the host vehicle and the destination in the traveling direction. As a result, it is possible to sufficiently ensure safety during the backward movement without monitoring the entire image frame.

  Further, in the image frame 100B shown in FIG. 4B, two mutually independent rectangular detection frames F21 and F22 are assigned to different positions in the frame. For example, when the vehicle is traveling in a forward direction in a normal state where a plurality of lanes are adjacent to each other like an expressway, a rear image as shown in FIG. Since the image is taken, a plurality of detection frames F21 and F22 are allocated so that the moving body can be detected individually for each traveling lane.

  In FIG. 4B, the detection frame F21 on the left side is a dedicated area for detecting other vehicles traveling on the adjacent traveling lane on the right side (left side in the rear image) of the traveling lane on which the host vehicle is traveling. It is. The detection frame F22 on the right side is a dedicated area for detecting other vehicles that are traveling in the adjacent traveling lane on the left side (right side in the rear image) of the traveling lane in which the host vehicle is traveling.

  The parameters of the number of detection frames F11 to F17 in FIG. 4A and the number of detection frames F21 and F22 in FIG. 4B, the position and size in the frame, for example, attach the in-vehicle camera 23B to the host vehicle. Immediately thereafter, adjustment is performed by an operator using adjustment software executable by the CPU 11 and stored as constant data on the nonvolatile memory 26A.

  For example, when the CPU 11 executes the “detection frame selection” process shown in FIG. 3, when the host vehicle travels backward, the combination of the detection frames F11 to F17 shown in FIG. Selected. When the host vehicle is traveling in the forward direction on an expressway or the like, the combination of the detection frames F21 and F22 shown in FIG. 4B is selected in S24.

  Therefore, when the CPU 11 recognizes the rear video image in S12 shown in FIG. 2, the inside of each of the detection frames F11 to F17 in the image frame 100A shown in FIG. 4A, or FIG. Only the area inside each of the detection frames F21 to F22 in the image frame 100B shown in FIG. Therefore, the load on the CPU 11 is greatly reduced and the time required for processing is shortened compared to the case where the entire area of the image frames 100A and 100B is processed.

  Furthermore, by processing only within a predetermined detection frame, it becomes easy to detect important objects. For example, the presence or absence of an important other vehicle that the driver of the own vehicle should approach from behind while traveling forward can be easily determined only by information in the areas of the detection frames F21 and F22 shown in FIG. (S13).

<Specific example of relationship between driving lane and detection area>
FIG. 5 shows an example of the vehicle detection areas ARL and ARR behind the host vehicle ca when traveling on a road 200 having a plurality of lanes (travel lanes). In the example shown in FIG. 5, when the host vehicle ca travels forward as indicated by an arrow on a road 200 where three independent travel lanes 200L, 200M, and 200R exist adjacent to each other. Is assumed.

  As shown in FIG. 5, the CPU 11 of the digital tachograph 10 mounted on the host vehicle ca executes image recognition within the detection frame F21 shown in FIG. 4B in the video of the in-vehicle camera 23B. Only the vehicle detection area ARR within the travel lane 200R can be recognized. Further, the CPU 11 executes image recognition within the range of the detection frame F22 shown in FIG. 4B in the video of the in-vehicle camera 23B, so that the vehicle detection area ARL in the travel lane 200L shown in FIG. Only within the range can be recognized.

  On the other hand, FIG. 6 shows an example of the positional relationship when the host vehicle ca cuts ahead of the other vehicle cb on the road 200. In the example shown in FIG. 6, the other vehicle cb travels in the travel lane 200M, and the own vehicle ca traveling in the travel lane 200R adjacent thereto changes the lane (lane change) slightly ahead of the other vehicle cb. It is assumed that the vehicle moves to the traveling lane 200M and interrupts.

  Also in the situation shown in FIG. 6, the digital tachograph 10 of the host vehicle ca recognizes an image within the detection frame F22 in FIG. 4B, thereby detecting a moving body such as another vehicle cb in the vehicle detection area ARL. it can. Here, when the driver of the own vehicle ca performs a highly dangerous interrupt driving operation, the digital tachograph 10 detects the other vehicle cb in the vehicle detection area ARL at the timing before and after the lane change. Become. That is, when the own vehicle ca changes lanes when the digital tachograph 10 detects the other vehicle cb in the vehicle detection area ARL or ARR, it can be regarded as dangerous driving.

<Operation example-2>
FIG. 7 shows a characteristic operation example-2 of the digital tachograph 10 according to the embodiment of the present invention. The operation example-2 shown in FIG. 7 is a modification of the operation example-1 shown in FIG. 2, and a function for monitoring the driving operation of a dangerous interrupt as shown in FIG. 6 is added. .

  That is, the operation shown in FIG. 7 is executed by the CPU 11 of the digital tachograph 10 to detect a driving operation in which the host vehicle ca changes its lane and interrupts in front of the other vehicle cb while the host vehicle ca is moving forward. The event can be recorded and an alarm can be output. The operation of FIG. 7 will be described below.

  In step S31 of FIG. 7, the CPU 11 executes the “detection frame selection” process of FIG. That is, the CPU 11 automatically selects an appropriate detection frame according to the situation of the host vehicle. For example, when the host vehicle ca is traveling forward and traveling on a road having a plurality of travel lanes such as an expressway, the combination of the detection frames F21 and F22 shown in FIG. Is selected as the target range of processing.

  In step S32, the CPU 11 processes the image data within the range of each detection frame selected in S31 for the rear video and executes the moving object detection. Thereby, for example, in the situation shown in FIG. 6, the digital tachograph 10 mounted on the host vehicle ca can determine whether or not a moving body such as the other vehicle cb exists in the vehicle detection area ARL (or ARR). .

  In step S33, the CPU 11 identifies whether or not there is a lane change in the host vehicle ca. Specifically, the state of the blinker signal indicating the operation state of each of the left and right direction indicators is monitored, and when one of the blinker signals is switched from off to on, the driving operation for changing the lane is started. Consider it a thing. When the lane change is started, the CPU 11 proceeds to the process from S33 to S34.

  In step S34, the CPU 11 identifies whether or not a dangerous interrupt driving operation (the inter-vehicle distance is too small) in the host vehicle ca is detected. For example, in the own vehicle ca shown in FIG. 6, when the digital tachograph 10 detects a moving body within the range of the detection frame F22 in the image recognition of S32, it is within the range of the vehicle detection area ARL shown in FIG. The other vehicle cb and the like are present in the vehicle, which is regarded as a high-risk interrupt driving operation.

  If the CPU 11 detects a high-risk interrupt, the CPU 11 outputs an alarm sound or a voice message from the speaker 20 in the next S35 to notify the driver of the danger.

  In step S36, the CPU 11 records the lane change event information of the host vehicle ca detected in S33 and the dangerous interrupt event information detected in S34 in the memory card 65 together with the event type, time, current position, and the like. Further, information on the number Na of occurrences of lane change events and the number Nb of occurrences of dangerous interrupt events is recorded or updated (counted up) as a history.

In step S37, the CPU 11 calculates a value Vx representing a tendency of dangerous driving by the following equation based on the number of lane changes Na and the number of interruptions Nb recorded in S36.
Vx = Nb / Na

  In step S38, the CPU 11 compares the value Vx calculated in S37 with a predetermined threshold value, thereby identifying whether or not the driver of the own vehicle has a daily tendency for dangerous driving. If there is a tendency for dangerous driving, the CPU 11 outputs a special warning in the next S39.

  In other words, when the frequency (Vx) of dangerous interrupted driving accompanying lane change is greater than or equal to a predetermined value, it is considered necessary to instruct the driver of the host vehicle to perform safe driving. Then, for example, the CPU 11 outputs a voice message such as “Interrupt driving is dangerous. Let's change the lane after securing more distance between vehicles” in S39.

<Advantages of digital tachograph 10>
The above-described digital tachograph 10 processes only the range of each detection frame selected in S11 when recognizing a moving body such as another vehicle in S12 of FIG. 2 from the rear image captured by the in-vehicle camera 23B. The load of image recognition can be greatly reduced. For this reason, for example, even when the CPU 11 simultaneously processes the forward image captured by the in-vehicle camera 23, the detection delay can be suppressed.

  In addition, by executing the “detection frame selection” process shown in FIG. 3, a detection frame having an appropriate position and size can be automatically selected according to the situation, which may affect the driving of the host vehicle. It is possible to easily recognize certain important moving objects. In particular, on a road 200 having a plurality of travel lanes such as an expressway, by selecting dedicated detection frames F21 and F22 for each travel lane, another vehicle cb that travels in an adjacent travel lane and is close in distance. The presence or absence of can be easily detected in a short time.

  When the digital tachograph 10 executes the operation shown in FIG. 7, a dangerous driving operation that the own vehicle ca interrupts in front of the other vehicle cb is automatically detected, and information on the event is recorded in S36. be able to. Further, by outputting an alarm in S35, the driver can be alerted to assist driving. Furthermore, since it is possible to grasp the tendency of dangerous interruption driving based on the history of the number of lane changes and the number of interruptions in S37 and output an alarm, safe driving can be efficiently supported. In addition, the driver recognizes the alarm output from the digital tachograph 10 in S36 and S39 during the interrupting operation, thereby confirming whether the distance between the host vehicle ca and the other vehicle cb is appropriate when the lane is changed. can do. Thus, information useful for the driver to improve manners when changing lanes or to reduce the occurrence of contact accidents between the host vehicle ca and the other vehicle cb is obtained.

  For example, when an alarm is output in S14 of FIG. 2 or S36 of FIG. 7, it may be controlled so that the recording function of the drive recorder is triggered by this, or alarm information is digital tachograph by wireless communication. 10 may be transmitted to the office PC 30.

Here, the features of the vehicle-mounted device and the driving support device according to the embodiment of the present invention described above are briefly summarized and listed in the following [1] to [5], respectively.
[1] An image processing unit (camera I / F 16) that inputs and processes a video signal output from an on-vehicle camera that captures at least the rear of the vehicle;
Backward movement detecting a moving body other than the vehicle within a detection frame pre-assigned in an image frame based on a rear image captured by the in-vehicle camera when the vehicle is traveling in a forward direction. A body detection unit (CPU11, S12);
An output processing unit (CPU 11, S14) for controlling data to be recorded for the moving body detected by the backward moving body detection unit;
A vehicle-mounted device (digital tachograph 10) characterized by comprising:

[2] When the vehicle is traveling on a road having a plurality of traveling lanes, the backward moving body detection unit travels in another traveling lane adjacent to the traveling lane in which the vehicle is traveling. A dedicated detection frame for detecting a moving body is used as the detection frame (see FIG. 4B),
The on-vehicle device according to [1] above, wherein

[3] The output processing unit recognizes a situation in which the vehicle changes lanes and interrupts in front of another moving body based on the presence or absence of another moving body detected by the dedicated detection frame (S32 to S34). Reflect in the output (S35, S36),
The on-vehicle device according to [2] above,

[4] The output processing unit records the number of lane changes and the number of interruptions generated by the vehicle, evaluates the information (S37, S38), and reflects the result in the output (S39).
The in-vehicle device according to [2] or [3] above, wherein

[5] The vehicle-mounted device according to any one of [1] to [4],
An alarm generation unit (CPU 11, S14, S35, S39) that generates an alarm for supporting safe driving of the vehicle for the moving body detected by the backward moving body detection unit;
A driving support device (digital tachograph 10) characterized by comprising:

5 Operation management system 8 Wireless base station 10 Digital tachograph 11, 31 CPU
12A Speed I / F
12B Engine rotation I / F
13 External input I / F
14 Sensor input I / F
15 GPS receiver 15a GPS antenna 16 Camera I / F
17 Recording unit 18 Card I / F
19 Voice I / F
20, 42 Speaker 21 RTC
22 SW input unit 23, 23B Car-mounted camera 24, 32 Communication unit 25 Power supply unit 26A Non-volatile memory 26B Volatile memory 27 Display unit 28 G sensor 29 Analog input I / F
30 office PC
33 Display unit 34 Storage unit 35 Card I / F
36 Operation unit 37 Output unit 38 Audio I / F
41 Microphone 48 External I / F
51 Vehicle speed sensor 54 External storage device 55 Accident point DB
56 Operation data DB
57 Hazard Map DB
65 Memory card 70 Network 100A, 100B Image frame 200 Road 200L, 200M, 200R Driving lane F11, F12, F13, F14, F15, F16, F17 Detection frame F21, F22 Detection frame ca Own vehicle cb Other vehicle ARL, ARR Vehicle detection region

Claims (5)

An image processing unit that inputs and processes at least a video signal output by an in-vehicle camera that captures the rear of the vehicle;
Backward movement detecting a moving body other than the vehicle within a detection frame pre-assigned in an image frame based on a rear image captured by the in-vehicle camera when the vehicle is traveling in a forward direction. A body detection unit;
An output processing unit for controlling data to be recorded for the moving body detected by the backward moving body detection unit;
A vehicle-mounted device characterized by comprising: In the state where the vehicle is traveling on a road having a plurality of traveling lanes, the backward moving body detection unit travels traveling in another traveling lane adjacent to the traveling lane in which the vehicle is traveling. Use a dedicated detection frame for detecting the body as the detection frame,
The on-vehicle device according to claim 1. The output processing unit recognizes the situation in which the vehicle changes its lane and interrupts in front of another moving body based on the presence or absence of another moving body detected by the dedicated detection frame, and reflects the output in the output.
The vehicle-mounted device according to claim 2. The output processing unit records the number of lane changes and the number of interrupt occurrences of the vehicle, evaluates the information, and reflects the result in the output.
The on-vehicle device according to claim 2 or claim 3, wherein The vehicle-mounted device according to any one of claims 1 to 4,
About the moving body detected by the rear moving body detection unit, an alarm generation unit that generates an alarm that supports safe driving of the vehicle;
A driving support apparatus comprising:

Images