CN102778223A - License number cooperation target and monocular camera based automobile anti-collision early warning method - Google Patents

License number cooperation target and monocular camera based automobile anti-collision early warning method Download PDF

Info

Publication number
CN102778223A
CN102778223A CN2012101851929A CN201210185192A CN102778223A CN 102778223 A CN102778223 A CN 102778223A CN 2012101851929 A CN2012101851929 A CN 2012101851929A CN 201210185192 A CN201210185192 A CN 201210185192A CN 102778223 A CN102778223 A CN 102778223A
Authority
CN
China
Prior art keywords
vehicle
car
camera
early warning
car plate
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.)
Pending
Application number
CN2012101851929A
Other languages
Chinese (zh)
Inventor
秦丽娟
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.)
Shenyang Ligong University
Original Assignee
Shenyang Ligong University
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 Shenyang Ligong University filed Critical Shenyang Ligong University
Priority to CN2012101851929A priority Critical patent/CN102778223A/en
Publication of CN102778223A publication Critical patent/CN102778223A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Traffic Control Systems (AREA)

Abstract

基于车牌合作目标和单目摄像机的汽车防撞预警方法，通过安装在汽车车头的前视摄像机，汽车尾部的后视摄相机时实图像采集，分别用于定位前方行驶车辆与本车的相对位置和速度和用于定位后方行驶车辆与本车的相对位置和速度，两个前后视摄像机的图像采集与视觉定位系统分别工作，经智能分析综合系统根据前后视两部摄像机获取的前后车辆定位信息以及车辆行驶数据对本车的安全状态进行分析，根据评估结果对驾驶员给出报警和建议，报警形式为声、光、语音三级报警。本发明能通过事先预防，有效的保护驾驶员和道路环境中行人的安全，大大减少汽车碰撞，减少经济损失避免事故的发生，该方法定位精度高，实时性好。

Figure 201210185192

The car collision avoidance warning method based on the license plate cooperation target and the monocular camera, through the front-view camera installed on the front of the car and the rear-view camera at the rear of the car, the real-time image acquisition is used to locate the relative position of the vehicle in front and the car respectively and speed and for locating the relative position and speed of the rear driving vehicle and the vehicle, the image acquisition and visual positioning system of the two front and rear view cameras work separately, and the front and rear vehicle positioning information obtained by the front and rear view cameras according to the intelligent analysis comprehensive system And vehicle driving data to analyze the safety status of the vehicle, and give alarms and suggestions to the driver according to the evaluation results. The alarm forms are three-level alarms of sound, light, and voice. The present invention can effectively protect the safety of drivers and pedestrians in the road environment through prior prevention, greatly reduce automobile collisions, reduce economic losses and avoid accidents. The method has high positioning accuracy and good real-time performance.

Figure 201210185192

Description

Vehicle anti-collision early warning method based on car plate cooperative target and monocular-camera
Technical field
The present invention relates to technical field of vehicle safety, the vehicle anti-collision early warning method more particularly to based on car plate cooperative target and monocular-camera.
Background technology
Vehicle anti-collision early warning system is that the vehicle intelligent system of spacing monitoring, early warning of knocking into the back, anti-collision warning, navigation feature is realized by sensor, computer image processing technology, is a key technology in the unmanned technology of intelligent automobile.The automotive license plate image that vehicle anti-collision early warning system can be shot according to video camera determines the relative distance and relative velocity between front vehicles and Current vehicle by monocular vision location technology.So as to carry out danger judgement, driver is reminded to make corresponding actions to avoid the collision of automobile in time.The research of the system location technology can aid in driver to judge, point out early warning, improve drive safety.Vehicle anti-collision early warning system passes through advance preventing; it is effectively protected the safety of pedestrian in driver and road environment; greatly reduce car crass; reduce the generation that economic loss avoids accident; therefore; it is the priority research areas of vehicle safety, is enhancing vehicle safety, reduces the necessary means of traffic accident.
The number of sensors that existing vehicle anti-collision early warning system is present is more, processing speed is slow, the problem of cost is high, the patent of invention proposes a kind of localization method based on car plate cooperative target and monocular-camera, and intends a kind of vehicle anti-collision early warning system based on monocular-camera of research and development on this basis.The mode processing speed of monocular vision is fast, low cost.Including two aspect problems, one is the car plate in identification and positioning image, and two are to determine the position of car plate and attitude.
For recognizing and positioning the car plate in image, first, front truck and license plate image are tentatively extracted from afterbody image using the method based on mathematical morphology, because car body angle is tilted, the interference of car light image, pseudo- car plate is removed using the method based on characters on license plate textural characteristics rim detection, current hull back image includes many billboards and notice board image, in order to remove the interference of the pseudo- image in this part, car plate type is recognized using the method based on color characteristic, last positioning licence plate region, extracts the frame and angle point of car plate.
Position and the attitude of car plate are determined using the monocular-camera localization method based on cooperative target for Second Problem.Car plate can provide four edges line as cooperative target, and just car plate can be positioned using rectangle cooperative target localization method.All car plates in the visual field are carried out with the profile of the classification each car plate of Simultaneous Extracting Image according to morphology, the length and width data according to known to every kind of car plate, position and attitude of the car plate under bodywork reference frame are calculated using the monocular-camera localization method based on linear feature.
The content of the invention
The technical problem to be solved in the present invention is, there is provided a kind of using the monocular visual positioning method based on car plate frame rectangular characteristic, the relative distance and relative velocity between Current vehicle and front vehicles can be accurately determined, processing speed is fast, the vehicle anti-collision early warning method of low cost.
The technical scheme of use is：
Vehicle anti-collision early warning method based on car plate cooperative target and monocular-camera, pass through the forward looking camera installed in automobile head, real IMAQ during the backsight camera of automobile tail, it is respectively used to position the relative position and speed and relative position and speed for positioning behind vehicle and this car of traveling ahead vehicle and this car, the IMAQ of two front-and rear-view video cameras works respectively with vision positioning system, the fore-aft vehicle location information and vehicle operation data obtained through intellectual analysis integrated system according to two video cameras of front-and rear-view is analyzed the safe condition of this car, alarm is provided to driver according to assessment result and advised, alarm form is sound, light, voice three-level is alarmed.
The above-mentioned vehicle anti-collision early warning method based on car plate cooperative target and monocular-camera, including position and the attitude for recognizing and positioning the car plate in image with determine car plate, by the use of the four edges line of car plate frame as cooperative target, monocular visual positioning method determines the relative distance and relative velocity between Current vehicle and forward and backward side's vehicle.
Above-mentioned forward looking camera method for early warning uses identical localization method with rear view camera method for early warning, the two autonomous working.
The present invention has the following advantages that compared with prior art：
1. positioning precision is high.Relative distance and relative velocity between Current vehicle and front vehicles can accurately be determined using the monocular visual positioning method based on car plate frame rectangular characteristic.
2. it is applied widely.The anti-collision prewarning apparatus for vehicle is used as beasurement base using car plate frame, car plate frame has unification of the motherland standard, all there is consistency under standard Structured environment or under non-standard structure environment, therefore the anti-collision prewarning apparatus for vehicle has wide range of applications, independent of track.
Brief description of the drawings
Fig. 1 is the structural representation of the present invention.
Fig. 2 is the monocular visual positioning method schematic diagram based on car plate frame.
Embodiment
Vehicle anti-collision early warning method based on car plate cooperative target and monocular-camera, the anti-collision early warning structure composition is as shown in Figure 1.Vehicle anti-collision early warning system is by the forward looking camera installed in automobile head, the backsight camera of automobile tail, image capturing system and Vehicle positioning system, intellectual analysis integrated system composition.Forward looking camera is used for the relative position and speed for positioning traveling ahead vehicle and this car；Rear view camera is used for the relative position and speed for positioning behind vehicle and this car.The image capturing system of two front-and rear-view video cameras, vision positioning system independently work.The vehicle anti-collision early warning, using the vehicle anti-collision early warning method based on car plate cooperative target and monocular vision.Including position and the attitude both sides problem for recognizing and positioning the car plate in image with determine car plate.Include being accurately positioned license plate image region based on architectural feature, textural characteristics, color characteristic, and extracting the frame of license plate image using comprehensive characteristics.Car plate frame has unified yardstick.And car plate frame is the rectangle of standard.Use based on the monocular visual positioning method of car plate frame rectangular characteristic to determine the relative distance and relative velocity between Current vehicle and front vehicles in the invention.This method positioning precision is high, and real-time is good.The fore-aft vehicle location information and vehicle operation data obtained again through intellectual analysis integrated system according to front and rear two video cameras, driver's manipulation behavioral data is analyzed the safe condition of this car, manipulation behavior to driver may be estimated to the influence that security is produced, alarm is provided to driver finally according to assessment result and is advised, alarm form is sound, light, the alarm of voice three-level.
The operation principle of the present invention
As shown in Figure 2：If camera model is known to perspective projection model and the intrinsic parameter of video camera.If the four edges of car plate frame
Figure 2012101851929100002DEST_PATH_IMAGE001
Direction vector under world coordinate system is
Figure 758713DEST_PATH_IMAGE002
,
Figure DEST_PATH_IMAGE003
.The coordinate that four edges intersect at four summits is
Figure 410274DEST_PATH_IMAGE004
Figure 517907DEST_PATH_IMAGE003
.Direction vector of the four edges under camera coordinate system be
Figure DEST_PATH_IMAGE005
Figure 37750DEST_PATH_IMAGE003
.Four summits
Figure 586544DEST_PATH_IMAGE006
Figure DEST_PATH_IMAGE007
Coordinate under camera coordinate system is
Figure 674585DEST_PATH_IMAGE008
Figure 3935DEST_PATH_IMAGE007
.The straight line that four edges are imaged under image coordinate system
Figure 265152DEST_PATH_IMAGE003
Equation is
Figure 668452DEST_PATH_IMAGE010
Figure 927395DEST_PATH_IMAGE003
.Direction vector is
Figure DEST_PATH_IMAGE011
, the coordinate put on graph line is
Figure 744041DEST_PATH_IMAGE012
Figure DEST_PATH_IMAGE013
Figure 481053DEST_PATH_IMAGE007
.Four summits
Figure 496600DEST_PATH_IMAGE007
The picture point under image coordinate system
Figure 472646DEST_PATH_IMAGE014
Figure 13349DEST_PATH_IMAGE007
Coordinate be
Figure DEST_PATH_IMAGE015
Figure 722066DEST_PATH_IMAGE007
.Car plate frame side
Figure 57232DEST_PATH_IMAGE016
Length be
Figure DEST_PATH_IMAGE017
.Orientation problem is to determine the rigid body translation between object coordinates system and camera coordinate system
Figure 848471DEST_PATH_IMAGE018
。
Perspective projection model is by space line
Figure DEST_PATH_IMAGE019
And graph line
Figure 927285DEST_PATH_IMAGE009
And video camera photocentre is tied to a plane, this plane is called to explain plane
Figure 487580DEST_PATH_IMAGE020
.Assuming that perpendicular to explanation planeNormal vector be
Figure 993647DEST_PATH_IMAGE022
, then normal vector
Figure 209865DEST_PATH_IMAGE022
With graph line
Figure 154687DEST_PATH_IMAGE009
And graph line
Figure 507171DEST_PATH_IMAGE009
On any point
Figure 449720DEST_PATH_IMAGE014
With the line of photocentre
Figure DEST_PATH_IMAGE023
It is all vertical, therefore normal vector
Figure 949971DEST_PATH_IMAGE022
It can be expressed as
Figure 370588DEST_PATH_IMAGE009
Direction vector
Figure 843158DEST_PATH_IMAGE024
With
Figure DEST_PATH_IMAGE025
Direction vector apposition.
   
Figure 753345DEST_PATH_IMAGE026
                             (1)
Under world coordinate system, side
Figure DEST_PATH_IMAGE027
And sideIt is parallel, side
Figure DEST_PATH_IMAGE029
And side
Figure 965200DEST_PATH_IMAGE030
Parallel, by perspective projection consistency, under camera coordinate system, this property keeps constant.Normal vector
Figure DEST_PATH_IMAGE031
With explanation plane
Figure 292277DEST_PATH_IMAGE032
On any straight line it is all vertical, therefore
Figure 638944DEST_PATH_IMAGE031
Perpendicular to side
Figure 51471DEST_PATH_IMAGE028
.Known side
Figure 813891DEST_PATH_IMAGE028
And side
Figure 995473DEST_PATH_IMAGE027
It is parallel, therefore can be derived from normal vector
Figure 510113DEST_PATH_IMAGE031
Perpendicular to side
Figure 409936DEST_PATH_IMAGE027
.Because normal vector
Figure DEST_PATH_IMAGE033
And side
Figure 38363DEST_PATH_IMAGE027
Vertically, therefore side
Figure 74452DEST_PATH_IMAGE027
Direction vector under camera coordinate system is equal to normal vector
Figure 700606DEST_PATH_IMAGE033
And normal vectorApposition.I.e.：
    
Figure 254264DEST_PATH_IMAGE034
          (2)
Similarly, side
Figure 410438DEST_PATH_IMAGE029
Direction vector under camera coordinate system is equal to normal vector
Figure DEST_PATH_IMAGE035
And normal vector
Figure 207493DEST_PATH_IMAGE036
Apposition.I.e.：
   
Figure DEST_PATH_IMAGE037
          (3)
Assuming that there is one and side under object coordinates system
Figure 878646DEST_PATH_IMAGE027
And side
Figure 52138DEST_PATH_IMAGE029
All vertical straight line, then straight line
Figure 93093DEST_PATH_IMAGE038
Direction vectorEqual to side
Figure 189225DEST_PATH_IMAGE027
And side
Figure 697566DEST_PATH_IMAGE029
The apposition of direction vector under object coordinates system.I.e.：
             
Figure 828333DEST_PATH_IMAGE040
                 (4)
Under camera coordinate system, straight lineAnd side
Figure 550619DEST_PATH_IMAGE027
And side
Figure 862651DEST_PATH_IMAGE029
Position relationship keep constant, its direction vector
Figure DEST_PATH_IMAGE041
Equal to sideAnd side
Figure 220000DEST_PATH_IMAGE029
The apposition of direction vector under camera coordinate system.I.e.：
             
Figure 290725DEST_PATH_IMAGE042
                  (5)
Known three sides
Figure 344131DEST_PATH_IMAGE027
、
Figure 183911DEST_PATH_IMAGE029
、（They are not parallel to each other, also do not pass through the camera light heart）Direction vector under object coordinates system, and this direction vector of three straight lines under camera coordinate system is calculated, by Screw theory, it is easy to calculate the spin matrix between camera coordinate system and object coordinates system.
As Fig. 2 shows, point、
Figure 22259DEST_PATH_IMAGE044
With corresponding picture point
Figure DEST_PATH_IMAGE045
、
Figure 941673DEST_PATH_IMAGE046
And video camera photocentre also constitutes a closing triangle
Figure DEST_PATH_IMAGE047
.
Figure 635960DEST_PATH_IMAGE047
In, straight line
Figure 349838DEST_PATH_IMAGE048
、
Figure DEST_PATH_IMAGE049
Direction vector, it is known that be respectively
Figure 395154DEST_PATH_IMAGE050
、
Figure DEST_PATH_IMAGE051
.Assuming that straight line
Figure 852680DEST_PATH_IMAGE048
With straight line
Figure 401473DEST_PATH_IMAGE049
Between folder cosine of an angle be, therefore obtain：
     
Figure DEST_PATH_IMAGE053
                 (6)
By formula（2）Obtain side
Figure 818865DEST_PATH_IMAGE027
Direction vector, it is assumed that straight line
Figure 752186DEST_PATH_IMAGE049
With sideBetween folder cosine of an angle be
Figure 742325DEST_PATH_IMAGE054
, obtain：
          
Figure DEST_PATH_IMAGE055
                 (7)
Under object coordinates system, 2 points
Figure 231075DEST_PATH_IMAGE043
、
Figure 233666DEST_PATH_IMAGE044
Distance be
Figure 819368DEST_PATH_IMAGE056
, according to perspective projection consistency, under camera coordinate system, distance between two points value keeps constant.As Fig. 2 shows, point
Figure 983633DEST_PATH_IMAGE043
、
Figure 225259DEST_PATH_IMAGE044
With corresponding picture point
Figure 765962DEST_PATH_IMAGE045
、
Figure 206170DEST_PATH_IMAGE046
And video camera photocentre also constitutes a closing triangle
Figure 806916DEST_PATH_IMAGE047
.
Figure 329645DEST_PATH_IMAGE047
In, straight line
Figure 674039DEST_PATH_IMAGE048
、
Figure 172017DEST_PATH_IMAGE049
Direction vector known to.Respectively
Figure 678084DEST_PATH_IMAGE050
、.Side
Figure 839124DEST_PATH_IMAGE027
Direction vector, it is known that
Figure 191608DEST_PATH_IMAGE047
In, obtained using sine：
  
Figure DEST_PATH_IMAGE057
                       (8)
By formula（8）, obtain：
                   
Figure 930894DEST_PATH_IMAGE058
                         (9)
Postulated point
Figure 368829DEST_PATH_IMAGE043
Coordinate is under camera coordinate system, here
Figure 55025DEST_PATH_IMAGE060
It is unknown number, therefore, obtains：
        
Figure DEST_PATH_IMAGE061
                 (10)
By（10）, obtain：                                   
Figure 324332DEST_PATH_IMAGE062
                      （11）
Car plate is located at the front of video camera, thereforeTake on the occasion of reasonable, obtain：
             
Figure DEST_PATH_IMAGE063
                  (12)
Calculating more than, is obtained a littleCoordinate under camera coordinate system, therefore, it is possible to determine translation matrix of the car plate relative to camera coordinate system, you can determine coordinate of the car plate in camera coordinate system.Because car plate and automobile position relation are determined, the position pass degree relation of video camera and automobile.Therefore system, it is known that can obtain the distance between Ben Che and other vehicles and angular relationship.

Claims (3)

1. the vehicle anti-collision early warning method based on car plate cooperative target and monocular-camera, it is characterized in that passing through the forward looking camera installed in automobile head, real IMAQ during the backsight camera of automobile tail, it is respectively used to position the relative position and speed and relative position and speed for positioning behind vehicle and this car of traveling ahead vehicle and this car, the IMAQ of two front-and rear-view video cameras works respectively with vision positioning system, the fore-aft vehicle location information and vehicle operation data obtained through intellectual analysis integrated system according to two video cameras of front-and rear-view is analyzed the safe condition of this car, alarm is provided to driver according to assessment result and advised, alarm form is sound, light, voice three-level is alarmed.
2. the vehicle anti-collision early warning method according to claim 1 based on car plate cooperative target and monocular-camera, it is characterized in that described vehicle anti-collision early warning method, including position and the attitude for recognizing and positioning the car plate in image with determine car plate, by the use of the four edges line of car plate frame as cooperative target, monocular visual positioning method determines the relative distance and relative velocity between Current vehicle and forward and backward side's vehicle.
3. the vehicle anti-collision early warning method according to claim 1 based on car plate cooperative target and monocular-camera, it is characterised in that described forward looking camera method for early warning uses identical localization method with rear view camera method for early warning, the two autonomous working.
CN2012101851929A 2012-06-07 2012-06-07 License number cooperation target and monocular camera based automobile anti-collision early warning method Pending CN102778223A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012101851929A CN102778223A (en) 2012-06-07 2012-06-07 License number cooperation target and monocular camera based automobile anti-collision early warning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012101851929A CN102778223A (en) 2012-06-07 2012-06-07 License number cooperation target and monocular camera based automobile anti-collision early warning method

Publications (1)

Publication Number Publication Date
CN102778223A true CN102778223A (en) 2012-11-14

Family

ID=47123222

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012101851929A Pending CN102778223A (en) 2012-06-07 2012-06-07 License number cooperation target and monocular camera based automobile anti-collision early warning method

Country Status (1)

Country Link
CN (1) CN102778223A (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103837872A (en) * 2012-11-22 2014-06-04 株式会社电装 Object detection apparatus
CN105956567A (en) * 2016-05-06 2016-09-21 安凯 Method for determining coordinates of four vertexes of vehicle license plate by using digital image
CN106802144A (en) * 2016-12-28 2017-06-06 深圳市美好幸福生活安全系统有限公司 A kind of vehicle distance measurement method based on monocular vision and car plate
CN107038875A (en) * 2017-05-22 2017-08-11 南宁学院 A kind of automobile dynamic speed testing device based on image recognition
CN105279760B (en) * 2015-10-26 2017-12-19 宁波裕兰信息科技有限公司 Automobile and obstacle detection method based on single dual camera information fusion
CN107622500A (en) * 2017-09-29 2018-01-23 吉林大学 A visual sensor-based rear collision warning method and device for heavy vehicles
CN108064401A (en) * 2016-12-29 2018-05-22 深圳市柔宇科技有限公司 Vehicle early warning method, apparatus and system
CN109141373A (en) * 2017-06-28 2019-01-04 西克股份公司 For protecting the sensor of machine
CN109318893A (en) * 2018-10-30 2019-02-12 南京邮电大学 Method and system for safe driving assistance based on pixel height change of license plate
CN110209178A (en) * 2019-07-08 2019-09-06 徐熊键 Automatic driving vehicle control method based on big data
CN110648427A (en) * 2018-06-26 2020-01-03 上海蔚兰动力科技有限公司 Driving assistance system and operation method thereof
CN111391861A (en) * 2018-12-29 2020-07-10 北京奇虎科技有限公司 A vehicle driving assistance method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050195383A1 (en) * 1994-05-23 2005-09-08 Breed David S. Method for obtaining information about objects in a vehicular blind spot
CN101135558A (en) * 2007-09-28 2008-03-05 深圳先进技术研究院 A method and device for vehicle collision avoidance warning based on machine vision
US20090147996A1 (en) * 2007-12-10 2009-06-11 Hon Hai Precision Industry Co., Ltd. Safe following distance warning system and method for a vehicle
US20090322480A1 (en) * 2008-06-30 2009-12-31 Robert Leon Benedict Rfid tag and method of vehicle attachment thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050195383A1 (en) * 1994-05-23 2005-09-08 Breed David S. Method for obtaining information about objects in a vehicular blind spot
CN101135558A (en) * 2007-09-28 2008-03-05 深圳先进技术研究院 A method and device for vehicle collision avoidance warning based on machine vision
US20090147996A1 (en) * 2007-12-10 2009-06-11 Hon Hai Precision Industry Co., Ltd. Safe following distance warning system and method for a vehicle
US20090322480A1 (en) * 2008-06-30 2009-12-31 Robert Leon Benedict Rfid tag and method of vehicle attachment thereof

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103837872B (en) * 2012-11-22 2017-05-24 株式会社电装 Object detection apparatus
CN103837872A (en) * 2012-11-22 2014-06-04 株式会社电装 Object detection apparatus
CN105279760B (en) * 2015-10-26 2017-12-19 宁波裕兰信息科技有限公司 Automobile and obstacle detection method based on single dual camera information fusion
CN105956567A (en) * 2016-05-06 2016-09-21 安凯 Method for determining coordinates of four vertexes of vehicle license plate by using digital image
CN106802144A (en) * 2016-12-28 2017-06-06 深圳市美好幸福生活安全系统有限公司 A kind of vehicle distance measurement method based on monocular vision and car plate
CN108064401A (en) * 2016-12-29 2018-05-22 深圳市柔宇科技有限公司 Vehicle early warning method, apparatus and system
CN107038875A (en) * 2017-05-22 2017-08-11 南宁学院 A kind of automobile dynamic speed testing device based on image recognition
CN109141373A (en) * 2017-06-28 2019-01-04 西克股份公司 For protecting the sensor of machine
CN107622500A (en) * 2017-09-29 2018-01-23 吉林大学 A visual sensor-based rear collision warning method and device for heavy vehicles
CN107622500B (en) * 2017-09-29 2023-05-23 吉林大学 Visual sensing-based rear collision early warning method and device for heavy vehicle
CN110648427A (en) * 2018-06-26 2020-01-03 上海蔚兰动力科技有限公司 Driving assistance system and operation method thereof
CN109318893A (en) * 2018-10-30 2019-02-12 南京邮电大学 Method and system for safe driving assistance based on pixel height change of license plate
CN111391861A (en) * 2018-12-29 2020-07-10 北京奇虎科技有限公司 A vehicle driving assistance method and device
CN110209178A (en) * 2019-07-08 2019-09-06 徐熊键 Automatic driving vehicle control method based on big data
CN110209178B (en) * 2019-07-08 2020-09-15 陈坤燕 Unmanned vehicle control method based on big data

Similar Documents

Publication Publication Date Title
CN102778223A (en) License number cooperation target and monocular camera based automobile anti-collision early warning method
CN110077399B (en) Vehicle anti-collision method based on road marking and wheel detection fusion
CN110065494B (en) Vehicle anti-collision method based on wheel detection
CN112389466B (en) Method, device and equipment for automatically avoiding vehicle and storage medium
US10380433B2 (en) Method of detecting an overtaking vehicle, related processing system, overtaking vehicle detection system and vehicle
KR102613839B1 (en) Detection of emergency vehicles
US9978276B2 (en) Vehicle exterior environment recognition device
CN105922990B (en) A kind of vehicle environmental based on high in the clouds machine learning perceives and control method
US20200074192A1 (en) Vehicle-Mounted Image Processing Device
CN113487874B (en) A system and method for data collection, recognition, classification and extraction of car-following behavior scenarios
CN112292286A (en) Rider assistance system and method
CN106324618B (en) Realize the method based on laser radar detection lane line system
CN106696960B (en) A kind of vehicle collision prewarning method and device
CN106515582A (en) Safe driving early warning method and device
CN106537180A (en) Method for mitigating radar sensor limitations with video camera input for active braking for pedestrians
CN102632839A (en) Vehicle-mounted blind area early warning system and method based on rear view image cognition
CN103287372A (en) Automobile anti-collision safe protecting method based on image processing
CN102685516A (en) Active safety type assistant driving method based on stereoscopic vision
CN103308056A (en) Road marking detection method
CN107229906A (en) A kind of automobile overtaking's method for early warning based on units of variance model algorithm
US20150039202A1 (en) Vehicle exterior environment recognition device
JP6547785B2 (en) Target detection device
JP7507930B2 (en) Accident Analysis Equipment
CN106570487A (en) Method and device for predicting collision between objects
Lamprecht et al. Extrinsic camera calibration for an on-board two-camera system without overlapping field of view

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20121114