一种基于随机抽样一致性的车道线快速识别算法

上海交通大学学报（自然版） ›› 2014, Vol. 48 ›› Issue (12): 1721-1726.

• 自动化技术、计算机技术 • 上一篇下一篇

一种基于随机抽样一致性的车道线快速识别算法

彭红1，肖进胜1,2，沈三明3，李必军2，程显1

(1. 武汉大学电子信息学院, 武汉 430072; 2. 武汉大学测绘遥感信息工程国家重点实验室, 武汉 430079; 3. 中国科学院深圳先进技术研究院, 广东深圳 518055)

收稿日期:2014-01-03
基金资助:
国家自然科学基金(91120002)资助项目

A Fast Algorithm Based on RANSAC for Vision Lane Detection

PENG Hong1,XIAO Jinsheng1,2，SHEN Sanming3,LI Bijun2,CHEN Xian1

(1. School of Electronic Information, Wuhan University, Wuhan 430072, China; 2. State Key Laboratory of Information Engineering in Surverying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China; 3.Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China)

Received:2014-01-03

摘要/Abstract

摘要：

摘要：针对现有车道线识别算法的有效性、实时性和鲁棒性不高的问题，提出了一种改进的快速随机抽样一致性（RANSAC）的曲线拟合验证的视觉车道线识别算法.该算法首先在进行逆透视变换后选用各向异性的高斯核滤波；然后对不同光照亮度图像采用适应性强的分位数方法进行二值化，并针对车道线在变换图中几乎垂直的特性，再利用直方图统计法检测出初始车道线；最后用改进的快速RANSAC的曲线拟合算法进行曲线修正，找出车道线可能存在的弧度，使检测的曲线更加精确.为提高检测的精度，最后对识别结果进行后处理.实验结果证明，对各种复杂的城市道路，所提出的算法均具有很高的鲁棒性和有效性，且算法处理效率很高，能很好地满足智能车实时检测车道线的要求.
关键词：智能交通；车道线识别；随机抽样一致性；贝兹曲线
中图分类号： TP 391.4文献标志码： A

Abstract:

Abstract： In view of the problems that the real-time, robustness and efficient of the existing lane detection algorithm are low, an improved and fast vision lane detection algorithm based on RANSAC (random sample consensus) was proposed. First, the inverse perspective mapping was conducted. Then, the image was filtered using anisotropic Gasssian filters. The quantile threshold method which has a strong adaptability to different illumination brightness image was used to the filtered image. The initial lines were detected using the histogram statistics method because almost all the lanes in the transform image were vertical. After that, an improved and fast RANSAC curve fitting step was performed to refine the detected initial lines and correctly detect curved lanes. Finally, a postprocessing was conducted to further improve the accuracy of algorithm. The results show that the improved algorithm has a great robustness, strong stability and high efficiency, which can meet the requirements of intelligent vehicle realtime detection.
Key words：

Key words: intelligent transportation, road lane detection, random sample consensus （RANSAC）, Bezier spline

彭红1，肖进胜1,2，沈三明3，李必军2，程显1. 一种基于随机抽样一致性的车道线快速识别算法[J]. 上海交通大学学报（自然版）, 2014, 48(12): 1721-1726.

PENG Hong1,XIAO Jinsheng1,2，SHEN Sanming3,LI Bijun2,CHEN Xian1. A Fast Algorithm Based on RANSAC for Vision Lane Detection[J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1721-1726.

参考文献

［1］Aharon Bar Hillel, Ronen Lerner, Dan Levi, et al. Recent progress in road and lane detection: A survey ［J］. Machine Vision and Applications, 2014,25:727745.

［2］Lee J W, Yi U K. A lanedeparture identification based on LBPE, Hough transform, and linear regression［J］. Computer Vision and Image Understanding, 2005,99(3):359383.

［3］Kang Y, Yamaguchi K, Naito T, et al. Multiband image segmentation and object recognition for understanding road scenes ［J］. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(4):14231433.

［4］许华荣, 王晓栋, 方遒. 基于B样条曲线模型的结构化道路检测算法［J］. 自动化学报, 2011,37(3):270275.

XU Huarong,WANG Xiaodong,FANG Qiu. Structure road detection algorithm based on Bspline curve mode［J］. Acta Automatica Sinica, 2011,37(3):270275.

［5］Park J W, Lee J W, Jhang K Y. A lanecurve detection based on an LCF［J］. Pattern Recognition Letters, 2003, 24(14): 23012313.

［6］Zhao K, Meuter M, Nunn C, et al. A novel multilane detection and tracking system ［C］//IEEE Intelligent Vehicles Symposium. Alcala de Henares:IEEE,2012: 10841089

［7］Truong Q B, Lee B R, Heo N G, et al.Lane boundaries detection algorithm using vector lane concept［C］//Control Automation Robotics & Vision. Hanoi: IEEE, 2008: 23192325.

［8］XU Huarong, WANG Xiaodong, HUANG Hongwu, et al. A fast and stable lane detection method based on Bspline curve［C］//IEEE ComputerAided Industrial Design & Conceptual Design. Wenzhou:IEEE, 2009:10361040.

［9］Watanabe A, Naito T, Ninomiya Y. Lane detection with roadside structure using onboard monocular camera ［C］//IEEE Intelligent Vehicles Symposium. Xi’an: IEEE, 2009: 191196.

［10］Hofmann U, Rieder A, Dickmanns E D. EMSvision: Application to hybrid adaptive cruise control［C］//Proceedings of the IEEE Intelligent Vehicles Symposium. Dearborn: IEEE, 2000: 468473.

［11］Lee J W, Kee C D, Yi U K. A new approach for lane departure identification［C］//Intelligent Vehicles Symposium. Parma Italy: IEEE, 2003: 100105.

［12］Jung C R, Kelber C R. A lane departure warning system based on a linearparabolic lane model［C］//Intelligent Vehicles Symposium. Parma Italy: IEEE, 2004: 891895.

［13］Aly M. Real time detection of lane markers in urban streets ［C］//IEEE Intelligent Vehicles Symposium. Eindhoven: IEEE, 2008: 712.

［14］陈龙,李清泉,毛庆洲.基于成像模型的车道线检测与跟踪方法［J］.中国公路学报, 2011,24(6):96102.

CHEN Long, LI Qingquan,MAO Qingzhou.Lane detection and following algorithm based on image model［J］. China Joural of Highway and Transport, 2011,24(6):96102.