CN105224909A - Lane line confirmation method in lane detection system - Google Patents
Lane line confirmation method in lane detection system Download PDFInfo
- Publication number
- CN105224909A CN105224909A CN201510513985.2A CN201510513985A CN105224909A CN 105224909 A CN105224909 A CN 105224909A CN 201510513985 A CN201510513985 A CN 201510513985A CN 105224909 A CN105224909 A CN 105224909A
- Authority
- CN
- China
- Prior art keywords
- lane line
- image
- lane
- detection system
- confirmation method
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000012790 confirmation Methods 0.000 title claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000283070 Equus zebra Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Abstract
The invention discloses the lane line confirmation method in a kind of lane detection system, the method comprises the following steps: step one, camera collection image; Step 2, edge enhancing is carried out to the image of camera collection; Image after step 3, edge strengthen is selected to carry out binaryzation; Step 4, need to filter out candidate marginal inside lane line according to lane line characteristic rule; Step 5, employing fitting technique lane line inward flange carry out matching, obtain straight line or the curve model in track; Step 6, lane line confirm.The image of described step one camera collection is gray level image or coloured image, if coloured image, turns gray level image formula, be translated into gray level image by coloured image.
Description
Technical field
The invention belongs to intelligent vehicle field, be specifically related to the lane line confirmation method in a kind of lane detection system.
Background technology
Automobile has become the more and more important vehicles in people's life at present, in order to better improve the comfortableness of security in vehicle traveling process and driver, the vehicle intellectualized main flow having become current development of automobile.Wherein Lane Keeping System detects the lane line of vehicle front according to the image of camera collection, and when vehicle generation sideslip, system can regulate wheel steering automatically, makes vehicle come back to track central authorities and travels.Lane detection technology in this system determines that whether lane detection is effective, directly determines the validity that later stage bearing circle controls.Therefore the accuracy of lane detection is directly connected to the correctness of the control of whole system.In order to make this system more accurately run, improve the work that lane detection accuracy is the most important thing.When roadway scene is complicated, there is flase drop phenomenon in traditional vehicle diatom detection system, lane line confirms inaccurate.
Summary of the invention
According to above the deficiencies in the prior art, improve lane line and confirm accuracy, solve traditional vehicle diatom detection system when roadway scene is complicated, there is flase drop phenomenon, propose a kind of lane line confirmation method herein.First the image of camera collection is strengthened by edge, then by binaryzation, image is carried out binaryzation, then extract through lane line inside edge point and obtain effective inward flange, carry out matching through hough transfer pair lane line, then carry out lane line confirmation according to lane line characteristic information in the picture.
In order to solve the problems of the technologies described above, the technical solution used in the present invention is: the lane line confirmation method in a kind of lane detection system, and the method comprises the following steps: step one, camera collection image; Step 2, edge enhancing is carried out to the image of camera collection; Image after step 3, edge strengthen is selected to carry out binaryzation; Step 4, need to filter out candidate marginal inside lane line according to lane line characteristic rule; Step 5, employing fitting technique lane line inward flange carry out matching, obtain straight line or the curve model in track; Step 6, lane line confirm.The image of described step one camera collection is gray level image or coloured image, if coloured image, turns gray level image formula, be translated into gray level image by coloured image.Described step 2 image edge enhancement method adopts based on the sobel algorithm in the edge detection method of first differential.Image after edge strengthens by described step 3 image binaryzation selects suitable threshold value to carry out binaryzation, the pixel portion higher than this threshold value is set to most high grade grey level, the gray portion lower than this threshold value is set to minimum gray level.The image that described step 4 obtains according to step 3 carries out binaryzation, lane line marginal portion will be highlighted in binary image.The matching of described step 5 lane line adopts corresponding fitting technique to adopt hough transfer pair lane line to carry out fitting a straight line to the lane line inward flange that step 4 obtains, and obtains straight line or the curve model in track.Lane line confirms: described step 6 lane line confirms that object is that getting rid of hough converts matching false lane line interference out.Lane line in the picture three features comprises: lane line width, end point position, lane width constraint condition.
Beneficial effect of the present invention is: this method can effectively improve lane detection discrimination, by lane line constraint condition, can remove numeral on road surface.The interference of the non-lane line such as word, zebra stripes, has extraordinary removal effect to the slot line of cement pavement simultaneously.
Accompanying drawing explanation
Below the content expressed by this Figure of description and the mark in figure are briefly described:
Fig. 1 is the workflow diagram of the specific embodiment of the present invention.
Embodiment
Contrast accompanying drawing below, by the description to embodiment, the specific embodiment of the present invention is as the effect of the mutual alignment between the shape of involved each component, structure, each several part and annexation, each several part and principle of work, manufacturing process and operation using method etc., be described in further detail, have more complete, accurate and deep understanding to help those skilled in the art to inventive concept of the present invention, technical scheme.
A lane line confirmation method in lane detection system, the method comprises the following steps: step one, camera collection image; Step 2, edge enhancing is carried out to the image of camera collection; Image after step 3, edge strengthen is selected to carry out binaryzation; Step 4, need to filter out candidate marginal inside lane line according to lane line characteristic rule; Step 5, employing fitting technique lane line inward flange carry out matching, obtain straight line or the curve model in track; Step 6, lane line confirm.The image of described step one camera collection is gray level image or coloured image, if coloured image, turns gray level image formula, be translated into gray level image by coloured image.Described step 2 image edge enhancement method adopts based on the sobel algorithm in the edge detection method of first differential.Image after edge strengthens by described step 3 image binaryzation selects suitable threshold value to carry out binaryzation, the pixel portion higher than this threshold value is set to most high grade grey level, the gray portion lower than this threshold value is set to minimum gray level.The image that described step 4 obtains according to step 3 carries out binaryzation, lane line marginal portion will be highlighted in binary image.The matching of described step 5 lane line adopts corresponding fitting technique to adopt hough transfer pair lane line to carry out fitting a straight line to the lane line inward flange that step 4 obtains, and obtains straight line or the curve model in track.Lane line confirms: described step 6 lane line confirms that object is that getting rid of hough converts matching false lane line interference out.Lane line in the picture three features comprises: lane line width, end point position, lane width constraint condition.
Step1: camera image inputs: the image of camera collection is gray level image or coloured image, if coloured image, needs to turn gray level image formula by coloured image, is translated into gray level image.This is because lane detection does not relate to color space, only need gray level image just can meet system processing requirements.
Step2: image border strengthens: edge refers to the most significant part of image local intensity change.The object that image border strengthens is the edge details part in image to be highlighted, as rising edge and the negative edge of lane line.Edge enhancing method has many, mainly contain the edge detection method based on first differential, the edge detection method based on second-order differential, based on the edge detection method of wavelet transformation and wavelet packet, the edge detection method based on mathematical morphology, fuzzy theory and neural network.What the edge detection method based on second-order differential was the most frequently used is Canny operator, but Canny operator will complete the multistage process of filtering, enhancing and detection, and step is complicated, causes arithmetic speed very slow, cannot meet the requirement of system real time.Because the edge detection method operand based on first differential is little, can real time handling requirement be met, adopt herein based on the sobel algorithm in the edge detection method of first differential.
Step3: image binaryzation: the image after edge strengthens by image binaryzation selects suitable threshold value to carry out binaryzation, the pixel portion higher than this threshold value is set to most high grade grey level, the gray portion lower than this threshold value is set to minimum gray level.The core of image binaryzation is how to select rational threshold value.The size of threshold value determines the quality of image binaryzation.In lane line Binarization methods, generally adopt self-adaption binaryzation method.General conventional self-adaption binaryzation system of selection is gradation of image averaging method, maximum entropy method (MEM).Adopt a kind of method based on image histogram definite threshold herein.
Step4: lane line inside edge point extracts: the image binaryzation image obtained according to Step3, lane line marginal portion will be highlighted in binary image, in order to correctly determine lane line inside edge point, need to filter out candidate marginal inside lane line according to lane line characteristic rule.Can obtain from binary image, the interior outside general gray-scale value of bianry image in track can reach 255, be then 0, and the distance between interior outside has isometry, according to these features, effectively can select the inward flange of lane line in the middle of interior outside.
Step5: lane line matching: namely lane line matching adopts corresponding fitting technique to carry out matching to the lane line inward flange that Step4 obtains, and obtains straight line or the curve model in track.Hough transfer pair lane line is adopted to carry out fitting a straight line herein.Adopting classical hough to convert existing problems is technically need to open up larger two-dimensional array for storing middle accumulated variables in hough conversion, calculates more consuming time.Propose herein to adopt two-stage hough converter technique, greatly can reduce calculated amount and taking system memory space in hough conversion process.First namely the core concept of two-stage hough conversion adopt first order hough to convert coarse positioning lane line polar coordinate position, then adopts fine positioning technology accurate positioning car diatom polar coordinates information.
Step6: lane line confirms: lane line confirms that object is that getting rid of hough converts matching false lane line interference out.Lane line presents oneself more distinctive feature in the picture.Adopt three features wherein herein: lane line width, end point position, lane width constraint condition.China's lane line width is generally 15cm, and lane width is generally 3.75m.End point, in two straight lines joining in the picture, is flat road solstics in real scene.Program is first according to detecting the lane line position, left and right obtained, and left, right lane expands 15cm width to the right to left-lane respectively, judges whether there is lane line edge since then, if there is no, be then judged to be it is not lane line.If there is lane line edge, then judge the row coordinate position that straight line is corresponding in vanishing line is capable.If row coordinate is outside our setting range, then it not lane line.If row coordinate is within our setting range, and two lane lines all exist, then calculate the width between two lane lines, judge that whether the width of two lane lines is at about 3.75m.Two lane line width threshold values are set as 3.5-4.2m.If within this scope, be then lane line, if not within this scope, be then judged to be it is not lane line.
Above by reference to the accompanying drawings to invention has been exemplary description; obvious specific implementation of the present invention is not subject to the restrictions described above; as long as have employed the improvement of the various unsubstantialities that method of the present invention is conceived and technical scheme is carried out; or design of the present invention and technical scheme directly applied to other occasion, all within protection scope of the present invention without to improve.The protection domain that protection scope of the present invention should limit with claims is as the criterion.
Claims (8)
1. the lane line confirmation method in lane detection system, it is characterized in that, the method comprises the following steps: step one, camera collection image; Step 2, edge enhancing is carried out to the image of camera collection; Image after step 3, edge strengthen is selected to carry out binaryzation; Step 4, need to filter out candidate marginal inside lane line according to lane line characteristic rule; Step 5, employing fitting technique lane line inward flange carry out matching, obtain straight line or the curve model in track; Step 6, lane line confirm.
2. the lane line confirmation method in lane detection system according to claim 1, it is characterized in that, the image of described step one camera collection is gray level image or coloured image, if coloured image, turn gray level image formula by coloured image, be translated into gray level image.
3. the lane line confirmation method in lane detection system according to claim 1, is characterized in that, described step 2 image edge enhancement method adopts based on the sobel algorithm in the edge detection method of first differential.
4. the lane line confirmation method in lane detection system according to claim 1, it is characterized in that, image after edge strengthens by described step 3 image binaryzation selects suitable threshold value to carry out binaryzation, pixel portion higher than this threshold value is set to most high grade grey level, the gray portion lower than this threshold value is set to minimum gray level.
5. the lane line confirmation method in lane detection system according to claim 1, is characterized in that, the image that described step 4 obtains according to step 3 carries out binaryzation, lane line marginal portion will be highlighted in binary image.
6. the lane line confirmation method in lane detection system according to claim 1, it is characterized in that, the matching of described step 5 lane line adopts corresponding fitting technique to adopt hough transfer pair lane line to carry out fitting a straight line to the lane line inward flange that step 4 obtains, and obtains straight line or the curve model in track.
7. the lane line confirmation method in lane detection system according to claim 1, is characterized in that, lane line confirms: described step 6 lane line confirms that object is that getting rid of hough converts matching false lane line interference out.
8. the lane line confirmation method in lane detection system according to claim 1, is characterized in that, lane line in the picture three features comprises: lane line width, end point position, lane width constraint condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510513985.2A CN105224909A (en) | 2015-08-19 | 2015-08-19 | Lane line confirmation method in lane detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510513985.2A CN105224909A (en) | 2015-08-19 | 2015-08-19 | Lane line confirmation method in lane detection system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105224909A true CN105224909A (en) | 2016-01-06 |
Family
ID=54993869
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510513985.2A Pending CN105224909A (en) | 2015-08-19 | 2015-08-19 | Lane line confirmation method in lane detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105224909A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105741559A (en) * | 2016-02-03 | 2016-07-06 | 安徽清新互联信息科技有限公司 | Emergency vehicle lane illegal occupation detection method based on lane line model |
CN105824314A (en) * | 2016-03-17 | 2016-08-03 | 奇瑞汽车股份有限公司 | Lane keeping control method |
CN105868696A (en) * | 2016-03-23 | 2016-08-17 | 奇瑞汽车股份有限公司 | Method and device for detecting multiple lane lines |
CN106407893A (en) * | 2016-08-29 | 2017-02-15 | 东软集团股份有限公司 | Method, device and equipment for detecting lane line |
CN106778551A (en) * | 2016-11-30 | 2017-05-31 | 南京理工大学 | A kind of fastlink and urban road Lane detection method |
CN107832674A (en) * | 2017-10-16 | 2018-03-23 | 西安电子科技大学 | A kind of method for detecting lane lines |
CN107958225A (en) * | 2017-12-14 | 2018-04-24 | 阜阳裕晟电子科技有限公司 | A kind of lane line extracting method based on Computer Vision |
CN108090401A (en) * | 2016-11-23 | 2018-05-29 | 株式会社理光 | Line detecting method and line detection device |
CN109583280A (en) * | 2017-09-29 | 2019-04-05 | 比亚迪股份有限公司 | Lane detection method, apparatus, equipment and storage medium |
CN109946708A (en) * | 2017-12-21 | 2019-06-28 | 北京万集科技股份有限公司 | A kind of method for detecting lane lines and device based on laser radar scanning |
CN112027566A (en) * | 2020-09-30 | 2020-12-04 | 武汉科技大学 | Conveying belt deviation type judging and deviation measuring and calculating system based on laser scanning |
CN113525368A (en) * | 2021-06-23 | 2021-10-22 | 清华大学 | Lane keeping emergency control strategy and safety control method and device for vehicle |
-
2015
- 2015-08-19 CN CN201510513985.2A patent/CN105224909A/en active Pending
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105741559B (en) * | 2016-02-03 | 2018-08-31 | 安徽清新互联信息科技有限公司 | A kind of illegal occupancy Emergency Vehicle Lane detection method based on track line model |
CN105741559A (en) * | 2016-02-03 | 2016-07-06 | 安徽清新互联信息科技有限公司 | Emergency vehicle lane illegal occupation detection method based on lane line model |
CN105824314A (en) * | 2016-03-17 | 2016-08-03 | 奇瑞汽车股份有限公司 | Lane keeping control method |
CN105868696A (en) * | 2016-03-23 | 2016-08-17 | 奇瑞汽车股份有限公司 | Method and device for detecting multiple lane lines |
CN105868696B (en) * | 2016-03-23 | 2019-06-14 | 奇瑞汽车股份有限公司 | A kind of method and apparatus detecting multilane lane line |
CN106407893A (en) * | 2016-08-29 | 2017-02-15 | 东软集团股份有限公司 | Method, device and equipment for detecting lane line |
CN108090401B (en) * | 2016-11-23 | 2021-12-14 | 株式会社理光 | Line detection method and line detection apparatus |
CN108090401A (en) * | 2016-11-23 | 2018-05-29 | 株式会社理光 | Line detecting method and line detection device |
CN106778551A (en) * | 2016-11-30 | 2017-05-31 | 南京理工大学 | A kind of fastlink and urban road Lane detection method |
CN109583280A (en) * | 2017-09-29 | 2019-04-05 | 比亚迪股份有限公司 | Lane detection method, apparatus, equipment and storage medium |
CN107832674B (en) * | 2017-10-16 | 2021-07-09 | 西安电子科技大学 | Lane line detection method |
CN107832674A (en) * | 2017-10-16 | 2018-03-23 | 西安电子科技大学 | A kind of method for detecting lane lines |
CN107958225A (en) * | 2017-12-14 | 2018-04-24 | 阜阳裕晟电子科技有限公司 | A kind of lane line extracting method based on Computer Vision |
CN109946708A (en) * | 2017-12-21 | 2019-06-28 | 北京万集科技股份有限公司 | A kind of method for detecting lane lines and device based on laser radar scanning |
CN112027566A (en) * | 2020-09-30 | 2020-12-04 | 武汉科技大学 | Conveying belt deviation type judging and deviation measuring and calculating system based on laser scanning |
CN113525368A (en) * | 2021-06-23 | 2021-10-22 | 清华大学 | Lane keeping emergency control strategy and safety control method and device for vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105224909A (en) | Lane line confirmation method in lane detection system | |
CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
CN104657727B (en) | A kind of detection method of lane line | |
Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
CN101750049B (en) | Monocular vision vehicle distance measuring method based on road and vehicle information | |
CN103177246B (en) | Based on the dual model Lane detection method of dynami c block division | |
CN104008645A (en) | Lane line predicating and early warning method suitable for city road | |
CN105426864A (en) | Multiple lane line detecting method based on isometric peripheral point matching | |
CN104392212A (en) | Method for detecting road information and identifying forward vehicles based on vision | |
CN103996053A (en) | Lane departure alarm method based on machine vision | |
CN103839264A (en) | Detection method of lane line | |
CN105631414A (en) | Vehicle-borne multi-obstacle classification device and method based on Bayes classifier | |
CN103077384A (en) | Method and system for positioning and recognizing vehicle logo | |
CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
CN104008377A (en) | Ground traffic sign real-time detection and recognition method based on space-time correlation | |
CN106384085A (en) | Calculation method for yaw angle of unmanned vehicle | |
CN103902985B (en) | High-robustness real-time lane detection algorithm based on ROI | |
CN103978978A (en) | Inversion projection transformation based lane keeping method | |
CN103914701B (en) | A kind of vehicle detection at night method based on image | |
CN105654073A (en) | Automatic speed control method based on visual detection | |
CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
CN103996031A (en) | Self adaptive threshold segmentation lane line detection system and method | |
CN104537348A (en) | Special vehicle recognition method and system | |
Wang et al. | The research on edge detection algorithm of lane | |
Wang et al. | Lane detection based on two-stage noise features filtering and clustering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160106 |
|
RJ01 | Rejection of invention patent application after publication |