CN103738243B - A kind of lane departure warning method - Google Patents
A kind of lane departure warning method Download PDFInfo
- Publication number
- CN103738243B CN103738243B CN201310520373.7A CN201310520373A CN103738243B CN 103738243 B CN103738243 B CN 103738243B CN 201310520373 A CN201310520373 A CN 201310520373A CN 103738243 B CN103738243 B CN 103738243B
- Authority
- CN
- China
- Prior art keywords
- image
- departure warning
- lane departure
- vehicle yaw
- distance
- 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.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of lane departure warning method, lane departure warning method comprises video acquisition device and installs and parameter calibration step, Image semantic classification step, edge detecting step, Lane detection step and lane departure warning time determining step, and it comprises: vehicle yaw distance calculation procedure: calculate vehicle yaw distance according to ambient parameter, inner parameter and coordinate conversion relation that video acquisition device is demarcated; Precompressed track time estimation step; Deviation determining step: setting deviation time threshold, when the described precompressed track time is less than deviation time threshold, carries out lane departure warning.The present invention can improve the antinoise of deviation warning and jamproof ability, and lane departure warning reliability is improved, and reduces false alarm rate and false dismissed rate, and improves the accuracy estimating the precompressed track time, to provide actv. lane departure warning.
Description
Technical field
The present invention relates to traffic safety ancillary technique field, be specifically related to a kind of lane departure warning method and precompressed track time estimation method.
Background technology
Deviation is reported to the police, and (LaneDepartureWarning is called for short: LDW) system is that (AdvancedDriverAssistanceSystems is called for short: wherein one ADAS) is an automobile driving safe ancillary system senior drive assist system.When sensitive member detects automotive run-off-road, if driver does not lay the indicator signal of crossover lane because of fatigue or carelessness, system can send alerting and return to track to remind driver.Deviation (LDW) system of reporting to the police is main sensors at present with camera, detect based on machine vision technique and follow the tracks of lane mark, judge whether vehicle has the danger deviating from track in conjunction with driver characteristics, for chaufeur provides sound, light and vibrations warning time dangerous.
Because road environment is complicated and changeable, the existing lane departure warning method based on image processing techniques still faces many challenges, also Shortcomings and area for improvement: different weather conditions, day and night light differential, and the factor such as shade affects light change, adds to the difficulties to image procossing; The interference of insulation strip, guardrail, track arrow and vehicle, affects the accuracy of lane detection.Therefore, Lane Departure Warning System functional reliability has much room for improvement, and need reduce false alarm rate and false dismissed rate, and need improve the accuracy estimating the precompressed track time, to provide actv. lane departure warning.
And, current deviation time (TimetoLaneCrossing, be called for short: method of calculating TLC) is generally first calculate vehicle yaw Distance geometry yaw angle, vehicle side is calculated to yawing velocity by yaw angle and the speed of a motor vehicle, the vehicle precompressed track time is estimated again by cross track distance and side direction yawing velocity, but in engineer applied, vehicle can not keep definitely steadily in the process of moving, vehicle-mounted camera there will be jitter phenomenon unavoidably, this directly can affect the calculating of yaw angle, because vehicle is run at high speed, the yaw angle error of two or three degree all may cause the calculation error of TLC to exceed allowed band, therefore, this method is not too reliable in actual applications.
Summary of the invention
For solving the problems of the technologies described above, the invention provides a kind of lane departure warning method, the antinoise of deviation warning and jamproof ability can be improved, lane departure warning reliability is improved, reduce false alarm rate and false dismissed rate, and improve the accuracy estimating the precompressed track time, to provide actv. lane departure warning.
The invention provides a kind of lane departure warning method, comprising:
I. video acquisition device is installed and parameter calibration step, specifically comprises:
I () installs camera in automobile lateral center position, the ambient parameter of recording of video harvester: camera and level ground height D, camera are to the vertical distance dl of vehicle right and left both sides and dr, camera angle of depression θ °;
(ii) demarcate video acquisition device inner parameter, determine the mapping relations of image coordinate system and world coordinate system;
II. Image semantic classification step, comprises the coloured image in acquisition testing region, determines surveyed area, carries out gray processing process and medium filtering denoising to image;
It is characterized in that, also comprise:
III. edge detecting step, comprises and adopts locally maximal difference extraction Image edge gradient, employing maximum variance between clusters edge image to carry out binary conversion treatment, carry out refinement, noise Transformatin to the edge image after binaryzation;
IV. Lane detection step, detects many straight lines by Hough transform, selected satisfactory lane mark;
V. lane departure warning time determining step, specifically comprises:
(i) vehicle yaw distance calculation procedure: calculate vehicle yaw distance according to ambient parameter, inner parameter and coordinate conversion relation that video acquisition device is demarcated;
(ii) precompressed track time estimation step, specifically comprises:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence trend model is set up, the estimation precompressed track time;
(iii) deviation determining step: setting deviation time threshold, when the described precompressed track time is less than deviation time threshold, carries out lane departure warning.
As improvement project of the present invention, described I. video acquisition device is installed and the mapping relations of image coordinate system and world coordinate system are defined as by parameter calibration step:
Wherein, definition intrinsic parameters of the camera a=f × Ny, b=Ny ÷ Nx, if Nx, Ny represent the proportionality coefficient of two coordinate directions respectively; F is camera focal length; (xc, yc) is image coordinate system, and (Xw, Yw, Zw) is world coordinate system;
(i) vehicle yaw distance calculation procedure in described v. lane departure warning time determining step is specially:
Lane mark equation in coordinates under image coordinate system is:
x=ky+b’
Lane mark equation in coordinates under world coordinate system is:
X
w=KY
w+B,Z
w=0
Mapping relations according to image coordinate system and world coordinate system calculate:
In world coordinate system, K and cos θ tends to 0, then camera is to lane mark distance: d ≈ B=Dkb;
L, W are the horizontal and vertical size of computer picture, k, b ' be the equation of straight line slope under image coordinate system and intercept;
Thus, the distance Ll=d-dl to left-hand lane line, right side Lr=d-dr on the left of car body is calculated.
As improvement project of the present invention, local maximal difference is adopted to extract Image edge gradient in described III. edge detecting step, be specially: the border adopting texture filter detected image, arranges template size, the difference of maxima and minima in output template neighborhood.
As improvement project of the present invention, in described III. edge detecting step to the concrete steps that the edge image after binaryzation carries out refinement be: with image median vertical line for boundary, detected image is divided into left half-image and right half-image; Left half-image is carried out by picture element scan from horizontal and vertical direction, when running into white point, if rear be some white point just by this point deletion, otherwise retain, last often capable pixel does not make a decision, and pixel value is directly set to 0; Right half-image is carried out by picture element scan from horizontal and vertical direction, if run into white point, if more front be also white point just by this point deletion, otherwise retain, often row first pixel be directly set to stain.
As improvement project of the present invention, in described III. edge detecting step, the concrete steps of image noise Transformatin are: remove noise by being communicated with scale of notation, line scanning is from bottom to top carried out to the image border after refinement, when finding white point, with this point for starting point grows, and record is communicated with white point number, if be communicated with white point number to be less than 3, think shot noise, remove white point, retain connected pixel count be more than or equal to 3 white point be communicated with edge.
The present invention also provides a kind of precompressed track time estimation method based on cross track distance, it is characterized in that, comprising:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence trend model is set up, the estimation precompressed track time.
By adopting, local maximal difference extracts Image edge gradient, edge image carries out binary conversion treatment, carries out refinement, noise Transformatin to the edge image after binaryzation in the present invention, improve the antinoise of deviation warning and jamproof ability, lane departure warning reliability is improved, reduce false alarm rate and false dismissed rate, and improved the accuracy estimating the precompressed track time by precompressed track time estimation method, to provide actv. lane departure warning.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of lane departure warning method of the present invention;
Fig. 2 is the schematic flow sheet of the squeeze time estimation steps in lane departure warning method of the present invention;
Fig. 3 is the schematic diagram of the image detection region determined in the present invention;
Fig. 4 is the computation process schematic diagram of the employing local maximal difference extraction Image edge gradient in the present invention;
Fig. 5 is that frame data schematic diagram is read in the circulation of precompressed track time estimation method in the present invention;
Fig. 6 is the cross track distance point sequence trend model schematic diagram of the precompressed track time estimation method in the present invention;
Fig. 7 shows the whole implementation schematic flow sheet of lane departure warning method provided by the invention;
Fig. 8-1 to Fig. 8-3 shows under different road conditions environment, uses the effect schematic diagram of lane departure warning method inspection vehicle diatom provided by the invention.
Detailed description of the invention
Specifically illustrate embodiments of the present invention below in conjunction with accompanying drawing, accompanying drawing is only for reference and use is described, does not form the restriction to scope of patent protection of the present invention.
As shown in Figure 1, 2, the embodiment of the present invention provides a kind of lane departure warning method, comprising:
I. video acquisition device is installed and parameter calibration step, specifically comprises:
I () installs camera in automobile lateral center position, the ambient parameter of recording of video harvester: camera and level ground height D, camera are to the vertical distance dl of vehicle right and left both sides and dr, camera angle of depression θ °; In the present embodiment, after video acquisition camera is arranged on windshield, near vehicle mirrors, ensure that camera is in automobile lateral center position as far as possible, and shooting direction and car body parallel longitudinal so that the calculating of video acquisition and deviation;
(ii) demarcate video acquisition device inner parameter, determine the mapping relations of image coordinate system and world coordinate system;
II. Image semantic classification step, comprises the coloured image in acquisition testing region, determines surveyed area, carries out gray processing process and medium filtering denoising to image;
Fig. 3 shows image detection region.Using the image-region between more than automobile engine cover and below the visual end horizon of road as lane detection region, to reduce sky, branch, high mountain and traffic indication map picture to the interference of lane detection.The determination in region when device normalization, can be arranged in the enterprising pedestrian's work of software interface.
The lane departure warning method that the embodiment of the present invention provides also comprises:
III. edge detecting step, comprises and adopts locally maximal difference extraction Image edge gradient, employing maximum variance between clusters edge image to carry out binary conversion treatment, carry out refinement, noise Transformatin to the edge image after binaryzation; In an embodiment of the present invention, by maximum variance between clusters (OTSU) binary conversion treatment, white point value 255, stain value 0.
IV. Lane detection step, detects many straight lines by Hough transform, selected satisfactory lane mark;
V. lane departure warning time determining step, specifically comprises:
(i) vehicle yaw distance calculation procedure: calculate vehicle yaw distance according to ambient parameter, inner parameter and coordinate conversion relation that video acquisition device is demarcated;
(ii) precompressed track time estimation step, specifically comprises:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence trend model is set up, the estimation precompressed track time;
(iii) deviation determining step: setting deviation time threshold, when the described precompressed track time is less than deviation time threshold, carries out lane departure warning.
As improvement project of the present invention, video camera imaging is that real three-dimensional world is projected to two-dimensional camera plane, obtain the movable information of vehicle at real world, needs the coordinate conversion relation determining real world and image.
Described I. video acquisition device is installed and the mapping relations of image coordinate system and world coordinate system are defined as by parameter calibration step:
Wherein, definition intrinsic parameters of the camera a=f × Ny, b=Ny ÷ Nx, if Nx, Ny represent the proportionality coefficient of two coordinate directions respectively, is that the inner parameters such as the photosensitive distance of CCD determine jointly by the uncertain graphical rule factor of camera; The value of a, b can by the pavement marker priori value of background image and coordinate conversion relation be counter releases.F is camera focal length; Computer picture resolution is L × W, and (xc, yc) is image coordinate system, and (Xw, Yw, Zw) is world coordinate system;
(i) vehicle yaw distance calculation procedure in described v. lane departure warning time determining step is specially:
Lane mark equation in coordinates under image coordinate system is:
x=ky+b’
Lane mark equation in coordinates under world coordinate system is:
X
w=KY
w+B,Z
w=0
Mapping relations according to image coordinate system and world coordinate system calculate:
In world coordinate system, K and cos θ tends to 0, then camera is to lane mark distance: d ≈ B=Dkb;
L, W are the horizontal and vertical size of computer picture, k, b ' be the equation of straight line slope under image coordinate system and intercept;
Thus, the distance Ll=d-dl to left-hand lane line, right side Lr=d-dr on the left of car body is calculated.
In the present embodiment, adopt local maximal difference to extract Image edge gradient in described III. edge detecting step, be specially: the border adopting texture filter detected image, arranges template size, the difference of maxima and minima in output template neighborhood.As shown in Figure 4, acquiescence template size is 3 × 3 to the computation process of local maximal difference, and each numerical value gets the difference of maxim Nmax in neighborhood inside circumference 8 numerals and minimum value Nmin.
From the binary image that edge gradient image splits, the edge obtained is relatively thicker, and noise is also many, and be unfavorable for next step straight-line detection, the present invention respectively edge has carried out refinement and denoising.
In an embodiment of the present invention, in described III. edge detecting step to the concrete steps that the edge image after binaryzation carries out refinement be: with image median vertical line for boundary, detected image is divided into left half-image Img_Left and right half-image Img_Right; To left half-image Img_Left from bottom to top, from left to right carry out by picture element scan, when running into white point, if rear be some white point just by this point deletion, otherwise retain, last often capable pixel does not make a decision, and pixel value is directly set to 0; To right half-image Img_Right from bottom to top, from left to right carry out by picture element scan, if run into white point, if more front be also white point just by this point deletion, otherwise retain, often row first pixel be directly set to stain.
In an embodiment of the present invention, in described III. edge detecting step, the concrete steps of image noise Transformatin are: remove noise by being communicated with scale of notation, line scanning is from bottom to top carried out to the image border after refinement, when finding white point, with this point for starting point grows, and record is communicated with white point number, if be communicated with white point number to be less than 3, think shot noise, remove white point, retain connected pixel count be more than or equal to 3 white point be communicated with edge.In order to prevent double counting, by being judged as that the white point value being communicated with edge is set to 100, to distinguish untreated edge, after having traveled through a frame detected image, can value be set as 255 connection edge again.
The present invention also provides a kind of precompressed track time estimation method based on cross track distance, without the need to knowing yaw angle, comprising:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence; Fig. 5 is that frame data schematic diagram (frame data comprise time t and camera to lane mark distance d) is read in circulation, when data amount check is less than n, successively by data stored in stack, when data are greater than n, be shifted renewal successively, completes the estimation to yaw angle by n group data, realizes detecting in real time;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence is set up
Trend model, the estimation precompressed track time.Fig. 6 is the distance d of vehicle avris to lane mark and the coordinate relation of time t, carries out matching with straight line to point sequence.Also the curve model that applicable accuracy is higher carries out matching, but in practical engineering application, straight line model can meet the demands, and calculates, it is fairly simple to realize.
Draw range points Sequence Trend model, just in the hope of t coordinate axle intersection point t ', setting threshold thr, as precompressed track time t ' <thr, lane departure warning can have been provided.
Fig. 7 shows the whole implementation schematic flow sheet of lane departure warning method provided by the invention.
Precompressed track time estimation step shown in Fig. 2 is the schematic flow sheet of the precompressed track time estimation method based on cross track distance provided by the invention.
Fig. 8-1 to Fig. 8-3 shows under different road conditions environment, uses the effect schematic diagram of lane departure warning method inspection vehicle diatom provided by the invention.Fig. 8-1 to Fig. 8-3 respectively illustrates the lane detection design sketch under three kinds of road conditions environment, and road conditions environment is: daytime-front have car, evening-have street lamp, evening-without street lamp.
Above disclosedly be only preferred embodiment of the present invention, the scope of the present invention can not be limited with this, therefore according to the equivalent variations that the present patent application the scope of the claims is done, still belong to the scope that the present invention is contained.
Claims (5)
1. a lane departure warning method, comprising:
I. video acquisition device is installed and parameter calibration step, specifically comprises:
I () installs camera in automobile lateral center position, the ambient parameter of recording of video harvester: camera and level ground height D, camera are to the vertical distance dl of vehicle right and left both sides and dr, camera angle of depression θ °;
(ii) demarcate video acquisition device inner parameter, determine the mapping relations of image coordinate system and world coordinate system;
II. Image semantic classification step, comprises the coloured image in acquisition testing region, determines surveyed area, carries out gray processing process and medium filtering denoising to image;
It is characterized in that, also comprise:
III. edge detecting step, comprises and adopts locally maximal difference extraction Image edge gradient, employing maximum variance between clusters edge image to carry out binary conversion treatment, carry out refinement, noise Transformatin to the edge image after binaryzation;
IV. Lane detection step, detects many straight lines by Hough transform, selected satisfactory lane mark;
V. lane departure warning time determining step, specifically comprises:
(i) vehicle yaw distance calculation procedure: calculate vehicle yaw distance according to ambient parameter, inner parameter and coordinate conversion relation that video acquisition device is demarcated;
(ii) precompressed track time estimation step, specifically comprises:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence trend model is set up, the estimation precompressed track time;
(iii) deviation determining step: setting deviation time threshold, when the described precompressed track time is less than deviation time threshold, carries out lane departure warning.
2. lane departure warning method according to claim 1, is characterized in that:
(i) vehicle yaw distance calculation procedure in described v. lane departure warning time determining step is specially:
Calculate the distance Ll=d-dl to left-hand lane line, right side Lr=d-dr on the left of car body;
Wherein, camera is to lane mark distance: d ≈ B=Dkb; The expression formula of the Linear intercept B under world coordinate system is:
Wherein, L, W are the horizontal and vertical size of computer picture, k, b ' be the equation of straight line slope under image coordinate system and intercept, a, b are intrinsic parameters of the camera.
3. lane departure warning method according to claim 1, is characterized in that:
In described III. edge detecting step to the concrete steps that the edge image after binaryzation carries out refinement be: with image median vertical line for boundary, detected image is divided into left half-image and right half-image; Left half-image is carried out by picture element scan from horizontal and vertical direction, when running into white point, if rear be some white point just by this point deletion, otherwise retain, last often capable pixel does not make a decision, and pixel value is directly set to 0; Right half-image is carried out by picture element scan from horizontal and vertical direction, if run into white point, if more front be also white point just by this point deletion, otherwise retain, often row first pixel be directly set to stain.
4. lane departure warning method according to claim 1, is characterized in that:
In described III. edge detecting step, the concrete steps of image noise Transformatin are:
Noise is removed by being communicated with scale of notation, line scanning is from bottom to top carried out to the image border after refinement, when finding white point, with this point for starting point grows, and record is communicated with white point number, if be communicated with white point number to be less than 3, think shot noise, remove white point, retain connected pixel count be more than or equal to 3 white point be communicated with edge.
5., based on a precompressed track time estimation method for cross track distance, it is characterized in that, comprising:
1. vehicle yaw range points sequence is obtained: when vehicle starts to depart from non-zone of alarm, often process a two field picture, obtain the vehicle yaw distance in this moment;
2. analyze vehicle yaw range points sequence, some distribution near linear in its short time, when vehicle yaw distance reaches default driftage threshold value, start circulation and obtain vehicle yaw range points sequence;
3. according to the cross track distance point sequence in the setting-up time section obtained, cross track distance point sequence trend model is set up, the estimation precompressed track time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310520373.7A CN103738243B (en) | 2013-10-29 | 2013-10-29 | A kind of lane departure warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310520373.7A CN103738243B (en) | 2013-10-29 | 2013-10-29 | A kind of lane departure warning method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103738243A CN103738243A (en) | 2014-04-23 |
CN103738243B true CN103738243B (en) | 2015-12-30 |
Family
ID=50495343
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310520373.7A Active CN103738243B (en) | 2013-10-29 | 2013-10-29 | A kind of lane departure warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103738243B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108437987A (en) * | 2018-03-30 | 2018-08-24 | 吉利汽车研究院(宁波)有限公司 | A kind of method and system preventing deviation |
Families Citing this family (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103985131B (en) * | 2014-05-28 | 2017-01-18 | 大连理工大学 | Camera fast-calibration method for highway lane departure warning system |
CN104691333B (en) * | 2015-03-30 | 2017-03-15 | 吉林大学 | Coach driver fatigue state evaluation method based on the deviation frequency |
CN104859563B (en) * | 2015-05-28 | 2017-07-04 | 北京汽车股份有限公司 | lane departure warning method and system |
CN105141824B (en) * | 2015-06-17 | 2019-01-01 | 广州杰赛科技股份有限公司 | Image-pickup method and device |
CN105447956A (en) * | 2015-11-06 | 2016-03-30 | 东方通信股份有限公司 | Spliced banknote detection method |
CN105574277A (en) * | 2015-12-23 | 2016-05-11 | 大陆泰密克汽车系统(上海)有限公司 | Safety line related parameter calibration method based on road vehicle function safety |
CN105539293B (en) * | 2016-02-03 | 2018-01-09 | 北京中科慧眼科技有限公司 | Lane departure warning method and device and car steering accessory system |
JP6481648B2 (en) * | 2016-03-22 | 2019-03-13 | 株式会社デンソー | Lane departure avoidance system |
CN105868469A (en) * | 2016-03-28 | 2016-08-17 | 湖南大学 | Lane departure forewarning method based on perspective image and forewarning model construction method |
CN106515742B (en) * | 2016-07-22 | 2019-04-26 | 北京兴科迪科技有限公司 | A kind of lane departure warning method and system |
CN106295560B (en) * | 2016-08-09 | 2019-06-18 | 浙江零跑科技有限公司 | Lane keeping method based on vehicle-mounted binocular camera and segmented PID control |
CN108082192B (en) * | 2016-11-22 | 2020-06-19 | 比亚迪股份有限公司 | Lane departure early warning method and device |
CN106740841B (en) * | 2017-02-14 | 2018-07-10 | 驭势科技(北京)有限公司 | Method for detecting lane lines, device and mobile unit based on dynamic control |
US10604179B2 (en) * | 2017-04-21 | 2020-03-31 | Danfoss Power Solutions Inc. | Machine stability control system |
CN109086650B (en) * | 2017-06-14 | 2022-04-12 | 现代摩比斯株式会社 | Calibration method and calibration apparatus |
CN107451566B (en) * | 2017-08-02 | 2020-07-24 | 海信集团有限公司 | Lane line display method and device and computer-readable storage medium |
CN108297867B (en) * | 2018-02-11 | 2019-12-03 | 江苏金羿智芯科技有限公司 | A kind of lane departure warning method and system based on artificial intelligence |
CN108776767B (en) * | 2018-04-18 | 2019-12-17 | 福州大学 | System for effectively judging vehicle line pressing and prompting in advance |
CN109147368A (en) * | 2018-08-22 | 2019-01-04 | 北京市商汤科技开发有限公司 | Intelligent driving control method device and electronic equipment based on lane line |
CN109871776B (en) * | 2019-01-23 | 2023-04-14 | 昆山星际舟智能科技有限公司 | All-weather lane line deviation early warning method |
CN109902758B (en) * | 2019-03-11 | 2022-05-31 | 重庆邮电大学 | Deep learning-based lane area identification data set calibration method |
CN110171354B (en) * | 2019-05-15 | 2021-01-19 | 北京汽车股份有限公司 | Active warning method and system for roadside parking |
CN110466453B (en) * | 2019-08-28 | 2021-02-23 | 安徽江淮汽车集团股份有限公司 | Lane width threshold value adjusting method of blind spot monitoring system |
CN111060071B (en) * | 2019-12-16 | 2022-07-08 | 中公高科养护科技股份有限公司 | Road slope measuring method and system |
CN111402609A (en) * | 2020-03-17 | 2020-07-10 | 北京百度网讯科技有限公司 | Special lane driving reminding method, device, equipment and storage medium |
CN111914747A (en) * | 2020-07-31 | 2020-11-10 | 长江三峡通航管理局 | Ship lock miter gate gap video monitoring system and method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7444224B2 (en) * | 2003-11-14 | 2008-10-28 | Nissan Motor Co., Ltd. | Lane departure prevention apparatus |
DE102005014954A1 (en) * | 2005-04-01 | 2006-10-05 | Audi Ag | Measured yaw angle deviation determining method for motor vehicle, involves determining measured yaw angle and distance of assigned point of vehicle to lane limit, from data and determining real yaw angle from distance and speed information |
CN101470801B (en) * | 2007-12-24 | 2011-06-01 | 财团法人车辆研究测试中心 | Vehicle shift inspection method |
CN102288121B (en) * | 2011-05-12 | 2012-11-07 | 电子科技大学 | Method for measuring and pre-warning lane departure distance based on monocular vision |
-
2013
- 2013-10-29 CN CN201310520373.7A patent/CN103738243B/en active Active
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108437987A (en) * | 2018-03-30 | 2018-08-24 | 吉利汽车研究院(宁波)有限公司 | A kind of method and system preventing deviation |
CN108437987B (en) * | 2018-03-30 | 2020-04-28 | 吉利汽车研究院(宁波)有限公司 | Method and system for preventing lane departure |
Also Published As
Publication number | Publication date |
---|---|
CN103738243A (en) | 2014-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103738243B (en) | A kind of lane departure warning method | |
US10949684B2 (en) | Vehicle image verification | |
CN105922991B (en) | Based on the lane departure warning method and system for generating virtual lane line | |
KR101680023B1 (en) | Method for combining a road sign recognition system and lane detection system of a motor vehicle | |
US9740942B2 (en) | Moving object location/attitude angle estimation device and moving object location/attitude angle estimation method | |
US20140009615A1 (en) | In-Vehicle Apparatus | |
CN102806913B (en) | Novel lane line deviation detection method and device | |
US9912933B2 (en) | Road surface detection device and road surface detection system | |
WO2016031494A1 (en) | Object detecting device | |
US10023198B2 (en) | Method for determining a relative gradient of a roadway | |
WO2018059586A1 (en) | A vehicle identification method, device, and vehicle | |
CN107389084B (en) | Driving path planning method and storage medium | |
CN104732774B (en) | A kind of vehicle retrograde detection method and detecting system | |
CN103593649A (en) | Lane line detection method for lane departure early warning | |
EP2416303B1 (en) | Method for forming a road mark | |
CN104509100B (en) | Three-dimensional body detection device and three-dimensional body detection method | |
KR20140109990A (en) | Determining a vertical profile of a vehicle environment by means of a 3d camera | |
CN107628032A (en) | Automatic Pilot control method, device, vehicle and computer-readable recording medium | |
US9792509B2 (en) | Method and device for determining a lane course of a vehicle | |
CN104111058A (en) | Vehicle distance measuring method and device and vehicle relative speed measuring method and device | |
CN104648403A (en) | Method, apparatus and system for detecting narrow road | |
CN106324618A (en) | System for detecting lane line based on laser radar and realization method thereof | |
CN104115188A (en) | Three-dimensional object detection device | |
CN109635737A (en) | Automobile navigation localization method is assisted based on pavement marker line visual identity | |
US20100045449A1 (en) | Method for detecting a traffic space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |