CN201240344Y - Embedded integrated vision auxiliary driving safety system - Google Patents

Embedded integrated vision auxiliary driving safety system Download PDF

Info

Publication number
CN201240344Y
CN201240344Y CNU2008201117366U CN200820111736U CN201240344Y CN 201240344 Y CN201240344 Y CN 201240344Y CN U2008201117366 U CNU2008201117366 U CN U2008201117366U CN 200820111736 U CN200820111736 U CN 200820111736U CN 201240344 Y CN201240344 Y CN 201240344Y
Authority
CN
China
Prior art keywords
module
safety system
radar
vehicle body
driving safety
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CNU2008201117366U
Other languages
Chinese (zh)
Inventor
高隽
李钢
张仁斌
薛艳
吴燎原
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hefei University of Technology filed Critical Hefei University of Technology
Priority to CNU2008201117366U priority Critical patent/CN201240344Y/en
Application granted granted Critical
Publication of CN201240344Y publication Critical patent/CN201240344Y/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Traffic Control Systems (AREA)

Abstract

An embedded integrated vision auxiliary steering safety system is characterized by comprising an acquisition module consisting of a video image collector and distance-measuring radar; a bus-based transmission module; a main control module consisting of a message processing module and a memory module; and a man-machine interface module consisting of a sound alarm, a vibration alarm, a video display and an operating button. The system utilizes computer vision and information fusion technologies. One the one hand, the system can inform a driver the potential danger in advance when a vehicle or other object that may cause an accident approaches at a high speed from behind in an adjacent driveway; and once the driver changes the driveway, the system will trigger an alarm, so that the driver can take actions in time to avoid collision. On the other hand, when an automobile deviates from the driveway under no control, the system will trigger an alarm to ensure steering safety.

Description

Built-in integrated visual sensation auxiliary driving safety system
Technical field
The utility model relates to visual sensation auxiliary driving safety system, and a kind of being mainly used in of more specifically saying so prevents that vehicle from colliding or the safe driving system of run-off-road.
Background technology
Growing automobile production and growing safety concerns are just promoting initiatively and the development in passive safety system market.According to the research of German insurance association (German Insurance Association), it is absent minded, the response delay of chaufeur that the reason of 25% traffic accident is arranged, even dozes off in car.Make auxiliary this problem of driving safety system of research become particularly important.
At present, as the routine configuration of vehicle, auxiliary driving safety system mainly contains following two kinds of forms, but has problem separately:
1, uses radar to carry out passive detection,, but do not identify the particular location at accident object place intuitively for navigating mate so that survey the accident object in the warning region.
2, with radar application in lane changing ancillary system LCA, but only when the vehicle lane change, detect the existence of accident object, just can give the alarm, can not avoid navigating mate because of the absent minded non-autonomous lane change behavior that causes.
3, there is the vision blind area.3 meters of 3 meters of the power actuated vehicle left and right sides, rear very easily form vision blind area on the exterior mirror with interior zone.
The utility model content
The utility model is for avoiding above-mentioned existing in prior technology weak point, utilize computer vision and information fusion technology, a kind of built-in integrated visual sensation auxiliary driving safety system is provided, on the one hand, when contiguous track has when the approaching vehicle of rear portion high speed or other may cause the object of accident, system can inform the danger that chaufeur is potential in advance; In case the chaufeur lane change, system makes chaufeur can in time react crash-avoidance alerts triggered; On the other hand, if vehicle does not have run-off-road under controlled situation, system can give a warning, to guarantee driving safety.
The utility model technical solution problem adopts following technical scheme:
The characteristics of the embedded integrated vision driver assistance of the utility model safety system are that its system's formation comprises:
An acquisition module of being made up of jointly video image acquisition device and range only radar is gathered vehicle body environmental aspect all around in real time;
Transport module based on bus form communicates between each module of system and communicates between other vehicle electronic device in system and car;
A main control module of forming jointly by message processing module and memory module, acceptance is from the Information Monitoring about the environmental aspect around the vehicle body of described acquisition module, realize the identification and the tracking of driving lane by image stitching, information fusion and synchronous images identification, and catch and follow the tracks of and take precautions against latent defect object in the zone in the driving process, cooperate and detect the action whether driver has active conversion direction of traffic, output is carried out signal to human-machine interface module;
A human-machine interface module of being made up of audible alarm, vibration alarm device, video display unit (VDU) and action button is accepted the output signal of described main control module, carries out corresponding the demonstration or early warning.
The constructional feature of the utility model system also is:
Described strick precaution zone is that 3 meters at 3 meters of the power actuated vehicle left and right sides and rear are with interior zone.
But described video image acquisition device is infrared night vision, visual angle is 105 °~120 ° CMOS camera, is at least four, be installed on car respectively before, car left side, car right side and the tailstock.
Described range only radar adopts the micron wave radar, at least three, is installed on vehicle body left side, vehicle body right side and tail of body respectively.
The described detection range that is installed on the range only radar on vehicle body left side and vehicle body right side is no less than 50 meters, and the detection range that is installed in the range only radar of tail of body is no less than 100 meters.
Screen telltale in the described human-machine interface module is to be installed on the color LCD display on the front panel in the car.
Vibration alarm in the described human-machine interface module is the vibrator that is installed in the vehicle steering.
Described data transmission module based on bus form is to adopt the general CAN bus protocol of automobile interface.
The early warning of being carried out by described human-machine interface module in the utility model system comprises:
A, at chaufeur non-active conversion direction of traffic and during the vehicle body run-off-road, system is with the early warning of audible alarm sounding;
B, initiatively lane change is normal exercises at chaufeur, and video display unit (VDU) shows the video image that merges around the vehicle body, and the latent defect object in the flicker delineation video image;
C, at chaufeur lane change initiatively, when having latent defect object and radar detection in the video image to this accident object, vibration alarm device vibration early warning.
Compared with the prior art, the beneficial effects of the utility model are embodied in:
1, the utility model utilizes the acquired signal of video image acquisition device, through " synthesizing " video in the output search coverage after video stitching and the information fusion; The application image recognition technology is discerned adjacent vehicle and pedestrian synchronously simultaneously, has overcome the passivity and the non-visuality of radar detection; By potential accident object in the flicker delineation video, remind chaufeur to note, realize the active safety driving, for safe driving provides powerful guarantee.
2, the utility model is monitored the position of the relative traffic lane line of vehicle body in real time by the video image acquisition device, carries out traffic lane line identification and safety rule simultaneously and mates, and effectively whether identification of driver is non-active lane change.At driver's non-active conversion direction of traffic and during the vehicle body run-off-road, system can effectively avoid accident to take place with the early warning of audible alarm sounding.
Active advanced warning grade when 3, the action button in the utility model human-machine interface module can be used to set initialization system operational factor and system's operation.Initiatively advanced warning grade and hazard level associate, and determine three hazard levels according to hazard level, are respectively high, neutralize low three grades.The driver is according to the custom of driving, can be arranged to high security, middle safety and three running statees of low-security to system running state, the decision of three running statees is from the threshold values of hazard level assigning degrees of hazard, the running state safety is high more, the threshold values of hazard level is more little, thereby the safe driving coefficient is high more.According to the threshold values of running state decision, dynamically given high, medium and low three hazard levels by the accident object of flicker delineation in the video image.
Description of drawings
Fig. 1 is the utility model system construction drawing.
Fig. 2 is the utility model device structure block diagram.
Fig. 3 is radar installation site and investigative range scheme drawing.
Fig. 4 surveys BSD and lane changing ancillary system LCA principle schematic for the utility model blind area.
Fig. 5 is the utility model BSD and LCA functional block diagram.
Fig. 6 leaves the principle schematic of track warning system LDW for the utility model.
Fig. 7 is the utility model LDW functional block diagram.
Below, in conjunction with the accompanying drawings the utility model is further described by the specific embodiment.
The specific embodiment
Referring to Fig. 1, present embodiment is based on performance-oriented embedded control platform, adopt COMS camera and range only radar, comprise car left side radar and camera, car right side radar and camera, tailstock radar and camera, and camera is monitored vision in real time and is taken precautions against zone and the vehicle position with respect to the track before the car.With wherein acquisition of signal, storage, transmission, MCU, message processing module are encapsulated as control capsule.Based on the transport module of bus form, between each module of system, communicate and in system and car other car between electronic machine, communicate.The main control module that message processing module and memory module are formed, acceptance is from the Information Monitoring about environmental aspect around the vehicle body of acquisition module, realize the identification and the tracking of driving lane through image stitching, information fusion and synchronous images identification, and catch and follow the tracks of and take precautions against potential accident object in the zone in the driving process.The human-machine interface module formula is made up of audible alarm, vibration alarm device, video display unit (VDU) and action button.
According to the routine techniques in this area, image stitching is based on the adaptive template matching algorithm of Opencv, by Harris operator extraction image angle point, utilizes angle point quantity and location information, adjusts matching template size and position adaptively.This template matches mode can not only adaptively modifying template size and position, and can solve the mistake matching problem that the coloured image illumination variation is caused.Information fusion is for guaranteeing that the image after the stitching can keep the smooth visual effect, at first utilize these two statistical parameters of variance and average to treat stitched image adjustment, the statistical nature of piece image is composed to an other width of cloth to be sewed up, made that brightness of image to be sewed up reaches basically identical.Then by introducing the optimization fusion factor.The synchronous images recognizer is based on the Feature Recognition algorithm, utilizes primitive extraction, feature clustering and coupling to carry out track and moving vehicle, pedestrian's tracking, and the feature of use is the local feature of line segment, angle point.The algorithm fast operation has been realized synchronous images identification.And be applicable to complicated traffic environment, especially when a plurality of targets link to each other or block mutually, can utilize a few unique point to discern, make full use of the high characteristics of local feature signal to noise ratio.
Before four cameras shown in Fig. 2 are installed on car respectively, car left side, car right side and the tailstock.Adopt the COMS camera, have than the dynamic capture range of hi-vision, high-resolution, night vision function arranged and satisfy the needs of environment.Three radars shown in Figure 2 are the micron wave radars that are installed on vehicle body left side, vehicle body right side and tail of body respectively, and its detection range is answered the scope of coverage diagram 3 definition; Digital signal processor 8 is high-performance digital signal processors of peripheral interfaces such as integrated CAN bus interface and video interface, and its processing capacity wants to satisfy the real-time processing requirements of multitask; Memory device 9 is the common memory units formed of SDRAM and FLASH RAM, and SDRAM adopts the bidirectional interface type, and capacity satisfies the needs of video acquisition amount, FLASH RAM storing software, system parameter and other firmware; LCD display 11 adopts colour liquid crystal display device, is installed on gauge panel position in the car, early warning after being used to realize making a strategic decision and the function that shows the blind area video.Vibrator 12 is installed in the vehicle steering, as driver initiatively during lane change and when having potential accidents caused object, produces the vibration early warning; Car inner electronic equipment 10 comprises bearing circle rotation sensor and indicator lamp controller in the car, is used for accepting the initiatively signal of conversion direction of traffic of driver.
Referring to Fig. 3, adopt the micron wave radar, be installed on two sidepiece radars 31 on vehicle body left side and vehicle body right side respectively and be installed on a tail radar 32 of tail of body, provide the vehicle body both sides to be respectively 50 meters, tail of body at least and be at least 100 meters detection range, regional A as shown in Figure 3; According to radar wave emission and received signal, accurately calculate the relative velocity and the distance of the object and the vehicle body of certain volume magnitude range in this zone, this relative velocity and the foundation of distance as the calculating of object hazard level.
Referring to Fig. 4,, in the zone that 3 meters of left and right vehicle wheel both sides and rear are 3 meters the vision blind spot on the exterior mirror by prior art.β is a car back mirror angular field of view among the figure.At present, Audi, benz and TRW etc. all adopt medium range radar or the short-range radar sensor as detection blind area, but can only provide the result whether search coverage exists pedestrian or adjacent vehicle this " whether being ".
In the present embodiment, adopt the monitoring of video with great visual angle blind area mode to remedy the deficiency of radar detection.For whether dangerous chaufeur provide the blind area single information, and allow the chaufeur situation that is well understood to pedestrian and adjacent vehicle in the blind area more directly perceived for not only.Adopting visual angle α is 105 °~120 °, the infrared CMOS camera of small sized colour, be separately positioned on vehicle body left side, vehicle body right side and tail of body, i.e. two sidepiece cameras 41 and an afterbody camera 42, according to the vehicle body size, adjust the angle of three CMOS cameras synchronously, make the video pictures overlapping region greater than 20% of single width video, and less than 50% of single width video.Three whole blind areas that CMOS camera real-time detection back mirror is left over.
Referring to Fig. 5, BSD and LCA are made of three CMOS cameras, range only radar, acquisition of signal memory module, information fitting module, image fitting module, siren horn, video display unit (VDU), wherein:
The CMOS camera is the small sized colour infrared camera, and the camera angle can be adjusted.
Range only radar adopts the micron wave radar.In order to reduce the cost, improve cost performance, therefore must improve the performance of radar, reduce the cost of radar, and the consumption of radar in the minimizing system.
The acquisition of signal memory module is used to the video information gathering dead zone information and store various drivings, application software and collect.BSD and LCA share signal acquisition module.
The information fitting module is based on the measurement of image.Utilize image processing and image fitting technique that the dead zone information of three CMOS camera monitorings is stitched into the more complete image of a width of cloth, really realize the non-blind area driving.
The image fitting module be based on image recognition and with cut apart.The application image recognition technology identifies accident object position potential in the blind area more intuitively.Promptly the multisensor to the output of information fitting module " synthesizes " image, and identification synchronously, estimation close on (shortest distance) accident object, reminds chaufeur to note by the identified latent defect object of flicker delineation.
Siren horn is at chaufeur active lane change, and when having latent defect object and radar detection to this accident object in the video image, the vibration alarm device vibrates early warning.This vibration alarm is installed on the vibrator in the vehicle steering.BSD and LCA share annunciator.
Video display unit (VDU) is " synthesizing " video of the search coverage that is used for showing that 3 CMOS cameras obtain.This video display unit (VDU) is to be installed on the color LCD display on the front panel in the car.
Referring to Fig. 6, leave track warning LDW, by being installed in a CMOS front end camera 61 of car front end bumper, implement the position of the relative traffic lane line of monitoring vehicle body, the angular field of view γ of this front end camera 61 is 105 °~120 °.When non-active lane change takes place under scatterbrained situation chaufeur, annunciator will send warning, remind chaufeur to note.
Referring to Fig. 7, LDW is made of a camera, signal acquisition module, storage, traffic lane line identification safety rule matching module and siren horn, wherein:
Signal acquisition module is used to gather the location information of the relative traffic lane line of vehicle body;
Memory module is used to the video information storing various drivings, application software and collect;
Traffic lane line identification safety rule matching module comprise parallel carry out traffic lane line recognizer, image fitting algorithm, proximate vehicle/pedestrian discern extraction algorithm, based on the image measurement algorithm;
Siren horn is at chaufeur non-active conversion direction of traffic and during the vehicle body run-off-road, system is with the early warning of audible alarm sounding, with the generation that avoids traffic accident.

Claims (7)

1, a kind of built-in integrated visual sensation auxiliary driving safety system is characterized in that system's formation comprises:
An acquisition module of being made up of jointly video image acquisition device and range only radar is gathered vehicle body environmental aspect all around in real time;
Transport module based on bus form communicates between each module of system and communicates between other vehicle electronic device in system and car;
A main control module of forming jointly by message processing module and memory module, acceptance is from the Information Monitoring about the environmental aspect around the vehicle body of described acquisition module, realize the identification and the tracking of driving lane by image stitching, information fusion and synchronous images identification, and catch and follow the tracks of and take precautions against latent defect object in the zone in the driving process, cooperate and detect the action whether driver has active conversion direction of traffic, output is carried out signal to human-machine interface module;
A human-machine interface module of being made up of audible alarm, vibration alarm device, video display unit (VDU) and action button is accepted the output signal of described main control module, carries out corresponding the demonstration or early warning.
2, built-in integrated visual sensation auxiliary driving safety system according to claim 1, it is characterized in that described video image acquisition device is but that infrared night vision, visual angle are 105 °~120 ° CMOS camera, be at least four, be installed on car respectively before, car left side, car right side and the tailstock.
3, built-in integrated visual sensation auxiliary driving safety system according to claim 1 is characterized in that described range only radar adopts the micron wave radar, at least three, is installed on vehicle body left side, vehicle body right side and tail of body respectively.
4, built-in integrated visual sensation auxiliary driving safety system according to claim 3, it is characterized in that the described detection range that is installed on the range only radar on vehicle body left side and vehicle body right side is no less than 50 meters, the detection range that is installed in the range only radar of tail of body is no less than 100 meters.
5, built-in integrated visual sensation auxiliary driving safety system according to claim 1 is characterized in that the screen telltale in the described human-machine interface module is to be installed on the color LCD display on the front panel in the car.
6, built-in integrated visual sensation auxiliary driving safety system according to claim 1 is characterized in that the vibration alarm in the described human-machine interface module is the vibrator that is installed in the vehicle steering.
7, built-in integrated visual sensation auxiliary driving safety system according to claim 1 is characterized in that described data transmission module based on bus form is to adopt the general CAN bus protocol of automobile interface.
CNU2008201117366U 2008-05-14 2008-05-14 Embedded integrated vision auxiliary driving safety system Expired - Fee Related CN201240344Y (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNU2008201117366U CN201240344Y (en) 2008-05-14 2008-05-14 Embedded integrated vision auxiliary driving safety system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNU2008201117366U CN201240344Y (en) 2008-05-14 2008-05-14 Embedded integrated vision auxiliary driving safety system

Publications (1)

Publication Number Publication Date
CN201240344Y true CN201240344Y (en) 2009-05-20

Family

ID=40713634

Family Applications (1)

Application Number Title Priority Date Filing Date
CNU2008201117366U Expired - Fee Related CN201240344Y (en) 2008-05-14 2008-05-14 Embedded integrated vision auxiliary driving safety system

Country Status (1)

Country Link
CN (1) CN201240344Y (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102303605A (en) * 2011-06-30 2012-01-04 中国汽车技术研究中心 Multi-sensor information fusion-based collision and departure pre-warning device and method
CN102542634A (en) * 2012-01-13 2012-07-04 北京理工大学 Measuring system of driving state of target vehicle
CN102700472A (en) * 2012-06-13 2012-10-03 博立码杰通讯(深圳)有限公司 Equipment and method for assisting in vehicle driving
CN103390281A (en) * 2013-07-29 2013-11-13 西安科技大学 Double-spectrum night vision instrument vehicle-mounted system and double-spectrum fusion design method
CN103625405A (en) * 2012-08-24 2014-03-12 能晶科技股份有限公司 Driving assisting system and starting method thereof
CN105398389A (en) * 2015-12-23 2016-03-16 安徽安凯汽车股份有限公司 Automobile safe driving auxiliary detection system and method
CN107244320A (en) * 2017-05-17 2017-10-13 吉利汽车研究院(宁波)有限公司 A kind of method and device for avoiding vehicle collision
CN108471500A (en) * 2009-10-16 2018-08-31 奥林巴斯株式会社 Camera, method for imaging and storage medium
CN108847026A (en) * 2018-05-31 2018-11-20 安徽四创电子股份有限公司 A method of it is converted based on matrix coordinate and realizes that data investigation is shown
CN109753843A (en) * 2017-11-02 2019-05-14 郭宇铮 The driving DAS (Driver Assistant System) of view-based access control model sensor
CN114194108A (en) * 2020-09-16 2022-03-18 宝能汽车集团有限公司 Safety early warning device and method for vehicle and vehicle

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108471500A (en) * 2009-10-16 2018-08-31 奥林巴斯株式会社 Camera, method for imaging and storage medium
CN102303605A (en) * 2011-06-30 2012-01-04 中国汽车技术研究中心 Multi-sensor information fusion-based collision and departure pre-warning device and method
CN102542634A (en) * 2012-01-13 2012-07-04 北京理工大学 Measuring system of driving state of target vehicle
CN102542634B (en) * 2012-01-13 2014-05-21 北京理工大学 Measuring system of driving state of target vehicle
CN102700472A (en) * 2012-06-13 2012-10-03 博立码杰通讯(深圳)有限公司 Equipment and method for assisting in vehicle driving
CN102700472B (en) * 2012-06-13 2015-04-15 博立码杰通讯(深圳)有限公司 Equipment and method for assisting in vehicle driving
CN103625405A (en) * 2012-08-24 2014-03-12 能晶科技股份有限公司 Driving assisting system and starting method thereof
CN103625405B (en) * 2012-08-24 2015-12-16 能晶科技股份有限公司 Driving ancillary system and enable method
CN103390281A (en) * 2013-07-29 2013-11-13 西安科技大学 Double-spectrum night vision instrument vehicle-mounted system and double-spectrum fusion design method
CN105398389A (en) * 2015-12-23 2016-03-16 安徽安凯汽车股份有限公司 Automobile safe driving auxiliary detection system and method
CN105398389B (en) * 2015-12-23 2018-08-14 安徽安凯汽车股份有限公司 A kind of vehicle security drive assisted detection system and method
CN107244320A (en) * 2017-05-17 2017-10-13 吉利汽车研究院(宁波)有限公司 A kind of method and device for avoiding vehicle collision
CN107244320B (en) * 2017-05-17 2019-12-27 吉利汽车研究院(宁波)有限公司 Method and device for avoiding vehicle collision
CN109753843A (en) * 2017-11-02 2019-05-14 郭宇铮 The driving DAS (Driver Assistant System) of view-based access control model sensor
CN108847026A (en) * 2018-05-31 2018-11-20 安徽四创电子股份有限公司 A method of it is converted based on matrix coordinate and realizes that data investigation is shown
CN114194108A (en) * 2020-09-16 2022-03-18 宝能汽车集团有限公司 Safety early warning device and method for vehicle and vehicle

Similar Documents

Publication Publication Date Title
CN201240344Y (en) Embedded integrated vision auxiliary driving safety system
CN101318491A (en) Built-in integrated visual sensation auxiliary driving safety system
CN106708040B (en) Sensor module, automated driving system and the method for automated driving system
JP5769163B2 (en) Alarm device
US9586525B2 (en) Camera-assisted blind spot detection
CN105966312B (en) A kind of advanced driving assistance system of multifunctional vehicle and method
US7272477B2 (en) Vehicle parking assisting system and method
CN201824950U (en) Automobile safe running anti-collision system
CN103802728B (en) Automatically the drive assist system selecting scape to show based on Helmet Mounted Display and method
JP6307895B2 (en) Vehicle periphery monitoring device
CN105216727A (en) A kind of vehicle distances detection active safety system and control method
TW201416268A (en) Automobile warning method and automobile warning system utilizing the same
CN102424017A (en) Intelligent automobile lane change warning system and warning method thereof
CN202345534U (en) Intelligent warning system for lane changing of automobiles
CN105599682A (en) Automobile driving assisting system and method based on dead zone detection and looking-around image monitoring
CN108961839A (en) Driving lane change method and device
CN101782646A (en) All-round environment sensing system and method
CN108032809B (en) Reverse side auxiliary system and data fusion and control method thereof
CN201400129Y (en) Automobile safety rear-view device
US8184018B2 (en) Image-based vehicle safety warning system
CN102785667A (en) Binocularly-based driveway deviation and front anti-collision early-warning system and method
CN109552174A (en) Full visual field camera master machine control unit
CN218949048U (en) Intelligent blind area pedestrian detection and early warning device for garbage truck
CN207712036U (en) A kind of intelligent automobile drive assistance device
CN103448670A (en) Vehicle monitoring system

Legal Events

Date Code Title Description
C14 Grant of patent or utility model
GR01 Patent grant
C17 Cessation of patent right
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20090520

Termination date: 20100514