摘要
车道线识别是智能交通系统(intelligent transport system,ITS)实现的重要组成部分。为了解决道路图像中光源干扰、阴影遮挡、车道线破损、标志线不连续等因素导致道路识别方法鲁棒性较差的问题,提出一种基于粒子滤波框架的Catmull-Rom样条的车道线侦测及跟踪算法,这种算法利用Catmull-Rom样条数学模型能够灵活且精确的标定车道线,且基于粒子滤波框架的滤波器保障了系统的稳定性及鲁棒性。实地测试结果显示在9种路况环境下算法侦测及跟踪性能准确稳定;该方法与近远景分割算法比较,路况侦测及跟踪边界更清晰;进行基于影像序列的量化稳定性评估,正确识别率接近98%。
Lane detection is an important part of the intelligent transportation system.In order to solve the problem that light interference,shadow,worn out lane resulting in the robustness of lane detection bad,even worse,a spline-based multi-lane detection and tracking system is proposed in this paper.The major novelty of the proposed approach is the usage of the so-called Catmull-Rom in combination with the particle filtering framework.The new spline-based model enables an accurate and flexible modeling of the lane markings.At the same time the application of the filter based on particle filtering framework contributes significantly to the system robustness and stability.The test results under nine kinds of road environment show the stability and accuracy of the detection and tracking algorithm.Compared with so-called close-range and vision algorithm,the algorithm proposed in the paper detects boundary more clearly and gets nearly 98%correct identification rate in stability assessment based on video sequence.
引文
[1]SHI X,KONG B,ZHENG F.A new lane detection method based on feature pattern[C].2nd International Congress on Image and Signal Processing,2009.CISP09.IEEE,2009:1-5.
[2]SUN T Y,HUANG W C.Embedded vehicle lane-marking tracking system[C].2009 IEEE 13th International Symposium on Consumer Electronics.2009:627-631.
[3]TSAI L W,HSIEH J W,CHUANG C H,et al.Lane detection using directional random walks[C].Intelligent Vehicles Symposium,2008 IEEE.IEEE,2008:303-306.
[4]SHEN H,LI S,BO F,et al.Intelligent vehicles oriented lane detection approach under bad road scene[C].Ninth IEEE International Conference on Computer and Information Technology,2009.CIT'09.IEEE,2009,1:177-182.
[5]施晓东,刘格.一种光学遥感图像海陆分割方法[J].国外电子测量技术,2014,33(11):29-32.SHI X D,LIU G.Method of water and land segmentation in optical remote sensing images[J].Foreign Electronic Measurement Technology,2014,33(11):29-32.
[6]LIU W,ZHANG H,DUAN B,et al.Vision-based real-time lane marking detection and tracking[C].11th International IEEE Conference on Intelligent Transportation Systems,2008.ITSC 2008.IEEE,2008:49-54.
[7]戴映炘,朱磊,邱桢,等.图像网格法及应用[J].电子测量技术,2013,36(3):58-61.DAI Y X,ZHU L,QIU ZH,et al.Image grid method and its application[J].Electronic Measurement Technology,2013,36(3):58-61.
[8]TRUONG Q B,LEE B R,HEO N G,et al.Lane boundaries detection algorithm using vector lane concept[C].10th International Conference on Control,Automation,Robotics and Vision,2008.ICARCV2008.IEEE,2008:2319-2325.
[9]MEUTER M,MULLER-SCHNEIDERS S,MIKA A,et al.A novel approach to lane detection and tracking[C].12th International IEEE Conference on Intelligent Transportation Systems,2009.ITSC'09.IEEE,2009:1-6.
[10]朱霞,陈仁文,徐栋霞,等.基于改进粒子群的焊点检测路径规划方法[J].仪器仪表学报,2014,35(11):2484-2493.ZHU X,CHEN R W,XU D X,et al.Welding spot detection path planning method based on a novel particle swarm algorithm[J].Chinese Journal of Scientific Instrument,2014,35(11):2484-2493.
[11]李小红,武敬飞,张国富,等.结合分水岭和区域合并的彩色图像分割[J].电子测量与仪器学报,2013,27(3):247-252.LI X H,WU J F,ZHANG G F,et al.New color image segmentation based on watershed and region merging[J].Journal of Electronic Measurement and Instrument,2013,27(3):247-252.
[12](美)冈萨雷斯.数字图像处理[M].阮秋琦,译.2版.北京:电子工业出版社,2007.8.GONZALEZ R C.Digital image processing[M].YUAN Q Q trans.2nd.ed.Beijing:Publishing House of Electronics Industry,2007.8.
[13]胡敏,李梅,汪荣贵.改进的Otsu算法在图像分割中的应用[J].电子测量与仪器学报,2010,24(5):443-449.HU M.LI M,WANG R G.Application of an improved Otsu algorithm in image segmentation[J].Journal of Electronic Measurement and Instrument,2010,24(5):443-449.
[14]陈仁文,朱霞,徐栋霞,等.基于改进型粒子群算法的卡箍直径检测算法研究[J].仪器仪表学报,2014,35(8):1837-1843.CHEN R W,ZHU X,XU D X,et al.Spring clamp diameter detection algorithm based on the improved particle swarm optimization[J].Chinese Journal of Scientific Instrument,2014,35(8):1837-1843.
[15]陈国良,王煦法,庄镇泉,等.遗传算法及其应用[M].北京:科学出版社,2006.CHEN G L,WANG X F,ZHUANG ZH Q,et al.Genetic algorithm and its application[M].Beijing:science press,2006.
[16]KIM Z W.Robust lane detection and tracking in challenging scenarios[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(1):16-26.
[17]GOPALAN R,HONG T,SHNEIER M,et al.A learning approach towards detection and tracking of lane markings[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(3):1088-1098.
[18]CHANG C Y,LIN C H.An efficient method for lanemark extraction in complex conditions[C].2012 9th International Conference on Ubiquitous Intelligence&Computing and 9th International Conference on Autonomic&Trusted Computing(UIC/ATC).IEEE,2012:330-336.
[19]SMITH K,GATICA-PEREZ D,ODOBEZ J M,et al.Evaluating multi-object tracking[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops,2005.CVPR Workshops.IEEE,2005.
[20]Leissi Castaneda Leon,Roberto Hirata Jr.Vehicle detection using mixture of deformable parts models:static and dynamic camera[C].25th SIBGRAPI Conference on Graphics,Patterns and Images,2012:237-244.
