CN108052908A - Track keeping method - Google Patents

Track keeping method Download PDF

Info

Publication number
CN108052908A
CN108052908A CN201711343500.5A CN201711343500A CN108052908A CN 108052908 A CN108052908 A CN 108052908A CN 201711343500 A CN201711343500 A CN 201711343500A CN 108052908 A CN108052908 A CN 108052908A
Authority
CN
China
Prior art keywords
calibration
point
formula
coordinate
camera
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
CN201711343500.5A
Other languages
Chinese (zh)
Inventor
李阳
曹文平
乔敏
李昆鹏
王光
李�远
孙欢
唐马政
黄启慧
张强
王云涛
贾进超
张倩
蒋龙飞
姚鹏莉
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.)
Zhengzhou Nissan Automobile Co Ltd
Original Assignee
Zhengzhou Nissan Automobile Co Ltd
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 Zhengzhou Nissan Automobile Co Ltd filed Critical Zhengzhou Nissan Automobile Co Ltd
Priority to CN201711343500.5A priority Critical patent/CN108052908A/en
Publication of CN108052908A publication Critical patent/CN108052908A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B62LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62DMOTOR VEHICLES; TRAILERS
    • B62D15/00Steering not otherwise provided for
    • B62D15/02Steering position indicators ; Steering position determination; Steering aids
    • B62D15/025Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation

Abstract

The invention discloses a kind of track keeping methods of the present invention, comprise the following steps:The installation of the first step, camera:Camera is provided at the upper middle position of front windshield glass of car, so as to the wide end point for monitoring lane line of clear visual field, end point, that is, lane line is in the intersection point in a road distant place;The calibration of second step, image:The acquisition of image and the car body coordinate of calibration point and the acquisition of pixel coordinate;Calibrating parameters obtain;The acquisition of disappearance point coordinates;3rd step, signal output:4th step, steering wheel angle amendment:When steering motor receives the signal of camera output, the steering motor action carries out the amendment of steering wheel angle, and vehicle is revert among left and right lane line.The invention has the advantages that constantly being calculated by end point into row distance, and judge with the comparison of target range, then export corresponding signal to realize vehicle heading modified function automatically.

Description

Track keeping method
Technical field
The present invention relates to automobile active safety technical field, more particularly, to a kind of track keeping method.
Background technology
With the raising that people require automobile active safety, lane departure warning device is more and more applied common It on car, is reminded using lane departure warning device, auxiliary driver corrects vehicle heading or automatic vehicle of correcting travels Direction has become the important method for reducing traffic accident, particularly with the drop of the traffic accident of the vehicle of running on expressway It is low play the role of it is very big.
The content of the invention
Present invention aims at provide it is a kind of can interpolate that vehicle whether deviate and carry out travel direction adjustment track guarantor Hold method.
To achieve the above object, the present invention can take following technical proposals:
Track keeping method of the present invention, comprises the following steps:
The installation of the first step, camera:
S1.1:Camera is provided at the upper middle position of front windshield glass of car, so as to the wide monitoring of clear visual field To the end point of lane line, end point, that is, lane line is in the intersection point in a road distant place;
The calibration of second step, image:
S2.1:The acquisition of image:The acquisition of picture, it is desirable that the Calibration Field of acquisition using camera progress Calibration Field Lane line is clear and legible in ground picture;By continuously changing the pitch angle of camera, the calibration place under different pitch angles is gathered Picture is simultaneously numbered, and number is respectively:Scene 1.1, scene 1.2, scene 1.3, scene 1.4, scene 1.5, scene 1.6, field Scape 1.7 and scene 1.8;
S2.2:The car body coordinate of calibration point and the acquisition of pixel coordinate(Calibration point is for demarcating the point of disappearance point coordinates):
If the intersection point for drawing vertical line and ground from camera lens is the coordinate origin of bodywork reference frame, headstock front horizontal direction is Positive direction of the y-axis, horizontal vertical are x-axis in the y-axis, and the right is positive direction, and overall height direction is z-axis, is upwards positive direction, from And form bodywork reference frame;With opening the Calibration Field respectively in drawing software picture, each mark is respectively moved to by cursor Determine the position of each calibration point in the picture of place, each picture of the calibration point in two-dimensional coordinate system is read in drawing software Plain coordinate(x,y)And it is recorded;The pixel coordinate for defining i-th of calibration point is(xi,yi), unit pixel is corresponding Bodywork reference frame(That is point coordinate under in kind state of the Calibration Field ground in picture)Car body coordinate be denoted as(Xi,Yi), unit For m;
S2.3:Calibrating parameters obtain:If arbitrary point in current bodywork reference frame(X,Y,Z)Seat on two dimensional image coordinate system Mark(x,y)If the arbitrary point(X,Y,Z)All on x/y plane, i.e. Z is constant, then arbitrary point(X,Y,Z)And pixel coordinate (x,y)Coordinate meet following formula:
Formula(1);
Formula(2);
In formula,For the unknowm coefficient required by required 8;By formula(1)、 Formula(2)It understands, if the space point coordinates of known 4 or more calibration points and its on the image the image point coordinates of corresponding points, uses 8 unknowm coefficients of Non-linear least-square curve fitting, so that it is determined that the space point coordinates and described image point coordinates are corresponded to and closed System;Coordinate based on each calibration point in bodywork reference frame and image coordinate system uses least square method using Matlab softwares Fit formula(1)And formula(2)In 8 unknown parametersValue;
S2.4:The acquisition of disappearance point coordinates:Choose two left and right symmetrical lane lines, and the pixel that will be obtained in S2.2 Coordinate carries out linear fit, obtains the left and right lane line(The traveling auxiliary line of vehicle i.e. on highway)Equation formulations, respectively For:
Formula(3);
Formula(4);
In formulaFor fitting parameter;According to the equation formulations of left-lane line(3)It is public with the equation of right-lane line Formula(4)The intersecting point coordinate of two straight lines is obtained, as disappear point coordinates;
3rd step, signal output:
S3.1:After calibration is completed, corrected range limit value is set, that is, is demarcated between disappearance point coordinates and actual disappearance point coordinates Distance L(It is a standard value to demarcate disappearance point coordinates, and actual disappearance point coordinates is to calculate value in vehicle actual travel);
S3.2:When demarcating distance >=L of disappearance point coordinates and actual disappearance point coordinates, camera output pulse or voltage letter Number;
4th step, steering wheel angle amendment:
S4.1:When steering motor receives the pulse or the voltage signal of camera output, the steering motor action carries out The amendment of steering wheel angle;
S4.2:When being adapted to calibration the distance between disappearance point coordinates and actual disappearance point coordinates < L, camera stop signal Output, angle modification stop, and steering wheel self-return, vehicle is revert among left and right lane line.
The invention has the advantages that constantly being calculated by end point into row distance, and judge with the comparison of target range, Corresponding signal is exported again to realize vehicle heading modified function automatically.Ranging uses the ordinate based on end point Coordinate transform is carried out, and data computation model is simple, signal processing and transmission are simple, improve the modified reaction of steering wheel angle Speed;Ranging speed is fast, precision is high.First, the image of road ahead is shot by camera, and identifies left and right in the picture The lane line of both sides;Then, the coordinate system of image and the correspondence of lane line are obtained based on vehicle-mounted camera calibration technique, from And the target disappearance point coordinates in image is calculated with demarcating the distance of disappearance point coordinates;Finally, this distance and setting are compared Corrected range limit value, and then judge whether to need the steering mechanism for outputing signal to steering wheel, and by adjusting the angle of steering wheel Degree corrects the direction of vehicle traveling, realizes the function that track is kept.The present invention will liberate the both hands of user completely, there is lane line Road on when driving vehicle can carry out automatically traveling angle amendment, frequently need not artificially adjust vehicle traveling side To.
Description of the drawings
Fig. 1 is 8 scene graph in present invention calibration place.
Fig. 2 is the enlarged drawing of Fig. 1 Scenes 1.1.
Fig. 3 is the calibration calibrated parameter corresponding diagram in place in Fig. 1.
Fig. 4 is the flow chart of the present invention.
Specific embodiment
As shown in Figure 1,2,3, 4, track keeping method of the present invention, comprises the following steps:
It is laid with the first step, the installation of camera and Calibration Field:
S1.1:Camera is installed at the upper middle position of front windshield glass of car, so as to the wide monitoring of clear visual field To the end point of lane line, end point, that is, lane line is in the intersection point in a road distant place;Horizontal calibration place is selected, by each calibration object A is placed according to Fig. 2.
The calibration of second step, image:
S2.1:The acquisition of image:The acquisition of picture, it is desirable that the Calibration Field of acquisition using camera progress Calibration Field Lane line B is clear and legible in ground picture;By continuously changing the pitch angle of camera, the calibration place under different pitch angles is gathered Picture is simultaneously numbered, and number is respectively:Scene 1.1, scene 1.2, scene 1.3, scene 1.4, scene 1.5, scene 1.6, field Scape 1.7 and scene 1.8;
S2.2:The car body coordinate of calibration point C and the acquisition of pixel coordinate(Calibration point is for demarcating the point of disappearance point coordinates):
If the intersection point for drawing vertical line and ground from camera lens is the coordinate origin of bodywork reference frame, headstock front horizontal direction is Positive direction of the y-axis, horizontal vertical are x-axis in the y-axis, and the right is positive direction, and overall height direction is z-axis, is upwards positive direction, from And form bodywork reference frame;With opening the Calibration Field respectively in drawing software picture, each mark is respectively moved to by cursor Determine the position of each calibration point C in the picture of place, each calibration point C is read in drawing software in two-dimensional coordinate system Pixel coordinate(x,y)And it is recorded;The pixel coordinate for defining i-th of calibration point is(xi,yi), unit pixel is right with it The bodywork reference frame answered(That is calibration point C coordinate under in kind state of the Calibration Field ground in picture)Car body coordinate be denoted as(Xi, Yi), unit m, specific coordinate values see the table below 1(Note:It is referred to interposition, the second from left is intermediate left side secondary series, during the first from left is Between left side first row, the right side one be right middle first row, the right side two be right middle secondary series;Demarcate object A coordinates from top to bottom according to It is secondary to be included in table);
Table 1:
S2.3:Calibrating parameters obtain:If arbitrary point in current bodywork reference frame(X,Y,Z)Seat on two dimensional image coordinate system Mark(x,y)If the arbitrary point(X,Y,Z)All on x/y plane, i.e. Z is constant, then arbitrary point(X,Y,Z)And pixel coordinate (x,y)Coordinate meet following formula:
Formula(1);
Formula(2);
In formula,For the unknowm coefficient required by required 8;By formula(1)、 Formula(2)It understands, if the space point coordinates of known 4 or more calibration point B and its on the image the image point coordinates of corresponding points, uses 8 unknowm coefficients of Non-linear least-square curve fitting, so that it is determined that the space point coordinates and described image point coordinates are corresponded to and closed System;Coordinate based on each calibration point B in bodywork reference frame and image coordinate system uses least square method using Matlab softwares Fit formula(1)And formula(2)In 8 unknown parametersValue, it is specific to intend Add up to what is calculatedNumerical value see the table below 2;
S2.4:The acquisition of disappearance point coordinates:Choose two left and right symmetrical lane lines, and the pixel that will be obtained in S2.2 Coordinate carries out linear fit, obtains left and right lane line(The traveling auxiliary line of vehicle i.e. on highway)Equation formulations, be respectively:
Formula(3);
Formula(4);
In formulaFor fitting parameter;According to the equation formulations of left-lane line(3)It is public with the equation of right-lane line Formula(4)The intersecting point coordinate of two straight lines is obtained, as disappear point coordinates;
3rd step, signal output:
S3.1:After calibration is completed, corrected range limit value is set, that is, is demarcated between disappearance point coordinates and actual disappearance point coordinates Distance L(It is a standard value to demarcate disappearance point coordinates, and actual disappearance point coordinates is to calculate value in vehicle actual travel);
S3.2:When demarcating distance >=L of disappearance point coordinates and actual disappearance point coordinates, camera output pulse or voltage letter Number;
4th step, steering wheel angle amendment:
S4.1:When steering motor receives the pulse or the voltage signal of camera output, the steering motor action carries out The amendment of steering wheel angle;
S4.2:When being adapted to calibration the distance between disappearance point coordinates and actual disappearance point coordinates < L, camera stop signal Output, angle modification stop, and steering wheel self-return, vehicle is revert among left and right lane line.

Claims (1)

1. a kind of track keeping method, it is characterised in that:Comprise the following steps:
The installation of the first step, camera:
S1.1:Camera is provided at the upper middle position of front windshield glass of car, so as to the wide monitoring of clear visual field To the end point of lane line;
The calibration of second step, image:
S2.1:The acquisition of image:The acquisition of picture, it is desirable that the Calibration Field of acquisition using camera progress Calibration Field Lane line is clear and legible in ground picture;By continuously changing the pitch angle of camera, the calibration place under different pitch angles is gathered Picture is simultaneously numbered, and number is respectively:Scene 1.1, scene 1.2, scene 1.3, scene 1.4, scene 1.5, scene 1.6, field Scape 1.7 and scene 1.8;
S2.2:The car body coordinate of calibration point and the acquisition of pixel coordinate:
If the intersection point for drawing vertical line and ground from camera lens is the coordinate origin of bodywork reference frame, headstock front horizontal direction is Positive direction of the y-axis, horizontal vertical are x-axis in the y-axis, and the right is the positive direction of the x-axis, and overall height direction is z-axis, upwards for just Direction, so as to form bodywork reference frame;With opening the Calibration Field respectively in drawing software picture, cursor is respectively moved to Each Calibration Field ground position of each calibration point in picture, reads each calibration point in two-dimensional coordinate system in drawing software In pixel coordinate(x,y)And it is recorded;The pixel coordinate for defining i-th of calibration point is(xi,yi), unit pixel, with The car body coordinate of its corresponding bodywork reference frame is denoted as(Xi,Yi), unit m;
S2.3:Calibrating parameters obtain:If arbitrary point in current bodywork reference frame(X,Y,Z)Seat on two dimensional image coordinate system Mark(x,y)If the arbitrary point(X,Y,Z)All on x/y plane, i.e. Z is constant, then arbitrary point(X,Y,Z)And pixel coordinate (x,y)Coordinate meet following formula:
Formula(1);
Formula(2);
In formula,For the unknowm coefficient required by required 8;By formula(1), it is public Formula(2)It understands, if the space point coordinates of known 4 or more calibration points and its image point coordinates of corresponding points, use are non-on the image 8 unknowm coefficients of linear least squares fit, so that it is determined that the space point coordinates and described image point coordinates correspondence; Coordinate based on each calibration point in bodywork reference frame and image coordinate system uses least square fitting using Matlab softwares Go out formula(1)And formula(2)In 8 unknown parametersValue;
S2.4:The acquisition of disappearance point coordinates:Choose two left and right symmetrical lane lines, and the pixel that will be obtained in S2.2 Coordinate carries out linear fit, obtains the equation formulations of the left and right lane line, is respectively:
Formula(3);
Formula(4);
In formulaFor fitting parameter;According to the equation formulations of left-lane line(3)It is public with the equation of right-lane line Formula(4)The intersecting point coordinate of two straight lines is obtained, as disappear point coordinates;
3rd step, signal output:
S3.1:After calibration is completed, corrected range limit value is set, that is, is demarcated between disappearance point coordinates and actual disappearance point coordinates Distance L;
S3.2:When demarcating distance >=L of disappearance point coordinates and actual disappearance point coordinates, camera output pulse or voltage letter Number;
4th step, steering wheel angle amendment:
S4.1:When steering motor receives the pulse or the voltage signal of camera output, the steering motor action carries out The amendment of steering wheel angle;
S4.2:When being adapted to calibration the distance between disappearance point coordinates and actual disappearance point coordinates < L, camera stop signal Output, angle modification stop, and steering wheel self-return, vehicle is revert among left and right lane line.
CN201711343500.5A 2017-12-15 2017-12-15 Track keeping method Pending CN108052908A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711343500.5A CN108052908A (en) 2017-12-15 2017-12-15 Track keeping method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711343500.5A CN108052908A (en) 2017-12-15 2017-12-15 Track keeping method

Publications (1)

Publication Number Publication Date
CN108052908A true CN108052908A (en) 2018-05-18

Family

ID=62132231

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711343500.5A Pending CN108052908A (en) 2017-12-15 2017-12-15 Track keeping method

Country Status (1)

Country Link
CN (1) CN108052908A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108860016A (en) * 2018-07-04 2018-11-23 广东猪兼强互联网科技有限公司 A kind of intelligent robot coach DAS (Driver Assistant System)
CN109345593A (en) * 2018-09-04 2019-02-15 海信集团有限公司 A kind of detection method and device of video camera posture
CN109472843A (en) * 2018-10-29 2019-03-15 上海伟世通汽车电子系统有限公司 A kind of auxiliary line generation method
CN110570475A (en) * 2018-06-05 2019-12-13 上海商汤智能科技有限公司 vehicle-mounted camera self-calibration method and device and vehicle driving method and device
CN112525147A (en) * 2020-12-08 2021-03-19 北京嘀嘀无限科技发展有限公司 Distance measurement method for automatic driving equipment and related device
CN113515973A (en) * 2020-04-09 2021-10-19 北京地平线机器人技术研发有限公司 Data acquisition method, training method, adjustment method and device
CN113963060A (en) * 2021-09-22 2022-01-21 腾讯科技(深圳)有限公司 Vehicle information image processing method and device based on artificial intelligence and electronic equipment
WO2022078074A1 (en) * 2020-10-16 2022-04-21 广州大学 Method and system for detecting position relation between vehicle and lane line, and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103927754A (en) * 2014-04-21 2014-07-16 大连理工大学 Calibration method of on-board camera
CN104143192A (en) * 2014-08-06 2014-11-12 中电海康集团有限公司 Calibration method and device of lane departure early warning system
CN104742912A (en) * 2013-12-27 2015-07-01 比亚迪股份有限公司 Lane deviation detection method and device
CN104835324A (en) * 2015-05-22 2015-08-12 吉林大学 Road deviation monitoring method and system
CN107161146A (en) * 2017-04-05 2017-09-15 吉利汽车研究院(宁波)有限公司 A kind of highway accessory system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104742912A (en) * 2013-12-27 2015-07-01 比亚迪股份有限公司 Lane deviation detection method and device
CN103927754A (en) * 2014-04-21 2014-07-16 大连理工大学 Calibration method of on-board camera
CN104143192A (en) * 2014-08-06 2014-11-12 中电海康集团有限公司 Calibration method and device of lane departure early warning system
CN104835324A (en) * 2015-05-22 2015-08-12 吉林大学 Road deviation monitoring method and system
CN107161146A (en) * 2017-04-05 2017-09-15 吉利汽车研究院(宁波)有限公司 A kind of highway accessory system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
化雅静: "智能车辆辅助驾驶系统中车道偏离预警算法的研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *
郭子逸: "一种基于单目视觉的车道偏离检测与预警方法", 《机械制造》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110570475A (en) * 2018-06-05 2019-12-13 上海商汤智能科技有限公司 vehicle-mounted camera self-calibration method and device and vehicle driving method and device
CN108860016A (en) * 2018-07-04 2018-11-23 广东猪兼强互联网科技有限公司 A kind of intelligent robot coach DAS (Driver Assistant System)
CN109345593A (en) * 2018-09-04 2019-02-15 海信集团有限公司 A kind of detection method and device of video camera posture
CN109472843A (en) * 2018-10-29 2019-03-15 上海伟世通汽车电子系统有限公司 A kind of auxiliary line generation method
CN109472843B (en) * 2018-10-29 2022-09-16 上海伟世通汽车电子系统有限公司 Auxiliary line generation method
CN113515973A (en) * 2020-04-09 2021-10-19 北京地平线机器人技术研发有限公司 Data acquisition method, training method, adjustment method and device
WO2022078074A1 (en) * 2020-10-16 2022-04-21 广州大学 Method and system for detecting position relation between vehicle and lane line, and storage medium
CN112525147A (en) * 2020-12-08 2021-03-19 北京嘀嘀无限科技发展有限公司 Distance measurement method for automatic driving equipment and related device
CN112525147B (en) * 2020-12-08 2022-11-08 北京嘀嘀无限科技发展有限公司 Distance measurement method for automatic driving equipment and related device
CN113963060A (en) * 2021-09-22 2022-01-21 腾讯科技(深圳)有限公司 Vehicle information image processing method and device based on artificial intelligence and electronic equipment
CN113963060B (en) * 2021-09-22 2022-03-18 腾讯科技(深圳)有限公司 Vehicle information image processing method and device based on artificial intelligence and electronic equipment

Similar Documents

Publication Publication Date Title
CN108052908A (en) Track keeping method
CN103927754B (en) A kind of scaling method of vehicle-mounted vidicon
CN107963077B (en) Control method, device and system for vehicle to pass through intersection
US8192036B2 (en) Rearview mirror adjustment system for trailer attached vehicle
US8167444B2 (en) Road curvature estimation for rearview mirror adjustment system
US8306700B2 (en) Vehicle travel support device, vehicle, and vehicle travel support program
CN107133985A (en) A kind of vehicle-mounted vidicon automatic calibration method for the point that disappeared based on lane line
US10005493B2 (en) Vehicle traveling control apparatus
US20160272243A1 (en) Travel control apparatus for vehicle
US8489287B2 (en) Vehicle roll over prevention safety driving system and method
CN104742959A (en) Lane Keeping Control Device Of Vehicle
US10023198B2 (en) Method for determining a relative gradient of a roadway
US8297763B2 (en) Road-adaptive side mirror adjustment system
CN202716870U (en) Automobile forward track auxiliary device
CN108445886B (en) Automatic driving vehicle lane change planning method and system based on Gaussian equation
CN103182984A (en) Vehicle image display system and correction method thereof
CN106696956A (en) Vehicle trajectory tracking device and method with path error correction
CN111559308B (en) Vehicle adaptive curve lighting system and control method thereof
CN102745198A (en) Auxiliary forward track device for vehicle
CN105629968B (en) A kind of self- steering control method of trackless self- steering truck combination
CN112265548A (en) Automatic driving control strategy adjustment method considering road surface condition
CN109552319B (en) Night intelligent auxiliary driving system and method
CN109814115A (en) A kind of angle recognition bearing calibration vertically parked
CN109774581A (en) A kind of headlight for vehicles steering following control system and method based on high-precision map
WO2022153795A1 (en) Signal processing device, signal processing method, and signal processing system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180518

RJ01 Rejection of invention patent application after publication