摘要
视觉导航是智能车辆导航的一项关键技术，本文针对智能车辆视觉导航系统研究了基于图像检测的道路检测算法。
论文介绍了智能车辆视觉导航系统研究背景、意义和现状，分析了常用道路图像预处理算法，提出了一种新的道路检测算法。文中算法采用基于线段的区域增长法将道路边缘图像分割成道路区域和非道路区域，对于多车道的检测，根据道路标志的边缘，恢复道路标志并根据其特征进行定位，最后采用数据拟合的方法找出道路轨迹线。按照本文算法在复杂路况下可以准确、快速估算出车道的延伸方向，从而可以实现车辆的防偏预报。
利用采集的200幅实际道路图像对本文提出的算法进行验证，正确识别率达81.2％，仿真结果表明本文提出的道路检测算法是可行和有效的。
Vision navigation is the key technique of intelligent vehicle guidance, this paper researches the algorithm of lane detection for intelligent vehicles vision navigation system based image process.
In the paper, research background, meaning and current status of vision navigation is firstly introduced, and currently algorithm of image process is analyzed; secondly, new algorithm for lane detection is presented, real road image can be divided into road region and non-road region based line region growing, for lane detection with multiple driveways, lane markings are renewed with method similar to road image segmentation based lane marks edge, marking line can be detected based lane marking shape, finally it applies linear data fitting to find lane markings. It can figure out the way stretching correctly and give warning of vehicle-deviation under the complicated lane conditions.
The algorithm proposed by the paper are used to process 200 actual lane image, thus obtaining right rate close to 81.2%, simulated results show that the algorithm is right and effective.
引文
[1] Figueiredo, L., Jesus, I., Machado, J. A. T. Towards the development of intelligent transportation systems[C]. Intelligent Transportation Systems, Proceedings IEEE, 2001, 1206-1211.
[2] 杨东凯，吴今培，张其善，智能交通系统(ITS)的发展及其模型化研究[J]．北京航空航天大学学报，2000，26(1)：22-25
[3] 吴小强，李鹏，曲卫民，智能交通系统研究回顾与展望[J]．国外公路，2000，20(4)：36-40
[4] 王荣本，李兵，施树明．世界智能车辆概述[J]．公路交通科技，2001，18(5)：30-34
[5] 王荣本，李斌，储江伟．世界智能车辆行驶安全保障技术的研究发展[J]．公路交通科技，2002，19(2)：88-92
[6] Dickmanns E D. Exportation-Based Multi Focal Vision for Vehicle Guidance[C]. Proc of Signal Processing Conference, 1995, 1023-1026.
[7] Jochen T M, Baluja S. A Massively Parallel Road Follower[J]. Computer Architecture for Machine Perception, 1993, (11):2-12.
[8] Richard Bishop. A Survey of Intelligent Vehicle Applications Worldwide[C]. IEEE Intelligent Vehicle Symposium, 2000, 25-30.
[9] Massimo Bertozzi, Alberto Broggi, Massimo Cellario. Artificial Vision in Road Vehicles[C], Proceedings of the IEEE, 2002, 90(7):1258-1261.
[10] Juan Pableo Gonzalez, Umit Ozguner, Lane Detection Using Histogram-Based Segmentation and Decision Trees[C]. IEEE Intelligent Transportation System Conference Proceedings, 2000, 346-351.
[11] Yajun Fang, Ichiro Masaki, Berthold Horn. Depth-Based Target Segmentation for Intelligent Vehicles: Fusion of Radar and Binocular Stereo[C]. IEEE transactions on intelligent transportation systems, 2002, 3(3): 196-202.
[12] 王宏，何克忠，张钹，智能车辆的自主驾驶与辅助导航[J]．机器人，1997，3：155-160
[13] 杨明，陆建业，王宏等 基于视觉的道路跟踪[J]．模式识别与人工智能．2001，2(14)：185-192
[14] Massimo Bertozzi, Alberto Broggi, Massimo Cellario. Artificial Vision in Road Vehicles[C]. Proceedings of the IEEE, 2002, 90(7): 1258-1271.
[15] Ran, B., Liu, H.. Development of A Vision-based Vehicle Detection and Recognition System for Intelligent Vehicle[R]. Transportation Research Record 79th Annual Meeting, Washington DC, 2000, 130-138.
[16] Stefan K. Gehrig, Axel Gem, Stefan Heinrich. Lane Recognition on Poorly Structured Roads-the Bots Dot Problem in California[C]. IEEE 5th Intelligent Conference on Intelligent Transportation System, 2002, 67-71.
[17] Bing Ma, Sridhar Lakshmanan, Alfred O. Hero. Pavement Boundary Detection Via Circular Shape Models[C]. Proceedings of the IEEE Intelligent Vehicles Symposium, 2000, 644-649.
[18] Dean P omerleau. RALPH: Rapidly Adapting Lateral Position Handler[J]. the Robotics Institute,
1995,506-511.
[19] P. Bellutta, R.Manduchi, L Matthies. Terrain Perception for DEMO Ⅲ[C]. Proceedings of the IEEE Intelligent Vehicles Symposium, 2000,326-331.
[20] Mei Chen,Jochem T., Pomerleau D. AURORA: a vision-based roadway departure warning system[C]. Intelligent Robots and Systems 95. 'Human Robot Interaction and Cooperative Robots' Proceedings, 1995, 1:243-248.
[21] Crisman.J.D, C.E.Thorpe. SCARF: A color vision system that tracks roads and intersection[C]. IEEE Trans. Robotics and Automation, 1993,9:49-58.
[22] Jochem T etal. PANS: A Portable Navigation Platform. Proc 1995 IEEE Symposia on Intelligent Vehicles, 1995, Detroit, Michigan, USA. 1995:107-112.
[23] Feng, D., Singh, S., Krogh, B .H.. Implementation of dynamic obstacle avoidance on the CMU NavLab[C]. Systems Engineering, IEEE International Conference, 1990, 208-211.
[24] Jochem,T.,Pomerleau D.. Life in the Fast Lane: The Evolution of an Adaptive Vehicle Control System[J]. AI magazine, 1996,11-50.
[25] James S. Albus. 4-D/RCS: A Reference Model Architecture for Demo Ⅲ~*[C], Intelligent Systems and Semiotics (ISAS), Proceedings of the 1998 IEEE International Symposium, 1998, 634-639.
[26] Dickmanns E D, etc. The Seeing Passenger Car 'VaMoRs-P'[C]. Proc 1994 IEEE Symposia on Intelligent Vehicles. IEEE Press Piscataway, N J, 1994:68-73.
[27] Maurer M etc. VaMoRs-P—An Advanced Platform for Visual Autonomous Road Vehicle Guidance[C]. Proc SPIE Confon Mobile Robots IX, Boston, 1994,(4).
[28] Rudolf Gregor, M. Ltzeler, M. Pellkofer. EMS-Vision: A Perceptual System for Autonomous Vehicles[C], IEEE Transactions On Intelligent Transportation Systems, 2002, 3(1):48-59.
[29] Ernst D. Dickmanns. Expectation-based, multi-focal, saccadic (EMS) vision for dynamic scene understanding[C], Universitaet der Bundeswehr Munich, Germany, 2002.
[30] Alberto Broggi, Massimo Bertozzi, Alessandra Fascioli. Automatic Vehicle Guiance: the Experience of the ARGO Autonomous Vehicle[M],USA,World Science PuNishing Co.Ltd. 1999.
[31] Massimo Be rtozzi, Alberto Broggi. GOLD: A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection[C]. IEEE Transactions on Image Processing, 1998, 7(1):62-81.
[32] Jin Woo Lee, Jung Ho Kin, Young Jin Lee. A Study on Recognition of Lane and Movement of Vehicles for port AGV Vision System[C]. Proc.IEEE, 2002, 463-466.
[33] Jin-Woo Lee, Sung-UK Choi, Young-Jin Lee. A Study on Recognition of Road and Movement of Vehicles using Vision System[C], Proc.SICE, 2001,38-41.
[34] Seung Gweon Jeong, Chang Sup Kim, Kang Sup Yoon. Real-Time Lane Detection for Autonomous Navigation, IEEE Intelligent Transportation System Conference Proceedings, 2001,508-513.
[35] Gang Yi Jiang, Tae Young Choi, Suk Kyo Hong. Lane and Obstacle Detection Based on Fast
Inverse Perspective Mapping Algorithm[C]. Proc,IEEE, 2000, 2969-2974.
[36] Jeong, D.Y., Park, S.J., Han, S.H.. A study on neural networks for vision-based road following of autonomous vehicle[C]. Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium, 2001, (3): 1609-1614
[37] Kim, K.L, Oh, S.Y., Kim, S.W.. An autonomous land vehicle PRV Ⅲ[C]. Intelligent Vehicles Symposium, Proceedings of the IEEE, 1996, 159-164.
[38] Park, S.T., Yang, S.Y., Jung, J.H.. Real-time lane recognition by simulated annealing algorithm[C].Science and Technology, 2000. KORUS 2000. Proceedings. The 4th Korea-Russia International Symposium, 2000,(3):95-98.
[39] Seung Gweon Jeong, Chang Sup Kim, Dong Youp Lee, Real-Time Lane Detection for Autonomous Vehicle[C], Proc.IEEE, 2001,1466-1471.
[40] Masatoshi Okutomi, Katsuyuki Nakano, Junichi Maruyama. Robust Estimation of Planar Regions for Vision Navigation using Sequential Stereo Images[C], Proceedings of the IEEE International Conference on Robotics &Automation, 2002,3321-3327.
[41] Inhyuk Moon 1, Jun Miura, Yoshiaki Shirai. On-line Viewpoint and Motion Planning for Efficient Visual Navigation under Uncertainty[J]. Robotics and Autonomous Systems, 1999,(28): 237-248.
[42] W.S.Wijesoma, K.R.S.Kodagoda, A.P.Balasuriya. Road Edge and Lane Boundary Detection using Laser and Vision[C], Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001,1140-1145.
[43] 李伟，王彦昕．基于模糊逻辑推理的室外机器人视觉导航方法[J]．电子学报，1996，24(11)：99-101．
[44] 郭木河，杨磊，陶西平．视觉导航中基于模糊神经网的消阴影算法研究[J]．软件学报，1999，10(2)：15-159．
[45] Lin, X., Chen, S. Color image segmentation u sing modified H SIs ystem for road following[C].Robotics and Automation Proceedings, IEEE International Conference, 1991,(3): 1998-2003.
[46] 郭木河，孙健，何可忠．室外智能移动机器人导航中路标识别算法的研究[J]．清华大学学报，1998，51(38)：104-107．
[47] 朱志刚，徐光，林学闫．多尺度全覆盖视觉导航方法[J]．机器人，1998，20(4)：266-272．
[48] 朱志刚，徐光，林学闫．视觉导航的多尺度全方位时空图像综合理解[J]．清华大学学报(自然科学版)，1997，37(3)：12-15．
[49] 李岩，林学闫．颠簸环境下的快速障碍物检测算法[J]．软件学报，2000，12(11)：1666-1673．
[50] 朱志刚，、石定机，杨波．基于重投影变换的实时障碍物检测视觉系统[J]．计算机研究与发展，1999，1(36)：77-84．
[51] 孙振平，安向京，贺汉根．CITAVT—Ⅳ——视觉导航的自主车[J]．机器人，2002，24(2)：115-121．
[52] 王荣本，徐友春，李兵．基于线性模型的导航路径图像检测算法研究[J]，公路交通科技，
2001, 18(1): 40-44
[53] Rongben Wang, Youchun Xu, Libin. A vision-based road edge detection algorithm [C]. Intelligent Vehicle Symposium, IEEE, 2002, (1):141-147.
[54] Xu Youchun, Wang Rongben, Libing. A Vision Navigation Algorithm Based on Linear Lane Model[C]. Proc.IEEE Intelligent Vehicles Symposium, 2000, 240-245.
[55] 吴东晖，叶秀清，顾伟康．基于不确定性知识的实时道路场景理解[J]．中国图像图形学报，2002，7(1)：69-74．
[56] 徐文渊，朱淼良．分布式系统调试器IVD的系统实现[J]．浙江大学学报(理学版)，2001，28(6)：645-652．
[57] 徐文渊，朱淼良．分布式系统调试器IVD的系统实现[J]．浙江大学学报(工学版)，2002，36(2)：1-6．
[58] 苏开娜，任文君，丰丽军．公路视觉导航中基于卡尔曼滤波器的3D运动参数估计[J]．电子测量与仪器学报，2000，14(2)：15-21．
[59] 苏开娜，任文君，易小琳．基于运动模型的道路识别与跟踪算法的研究[J]．中国图像图形学报，2000，5(3)：226-231．
[60] 苏开娜，丰丽军，刘忠云．公路汽车视觉导航中运动目标的检测与跟踪方法的研究[J]．计算机工程，200l，27(4)：46—49．
[61] 黄席樾，柴毅，汪先矩．汽车安全行驶智能辅助操作系统中的道路检测[J]．重庆大学学报(自然科学版)，2000，23(2)：26-30．
[62] 廖传锦，黄席樾，柴毅．基于边缘提取和特征跟踪的道路检测算法[J]．重庆大学学报，2002，25(1)：61-64．
[63] 黄席樾，汪先矩，柴毅．基于道路几何模型的单目测距算法[J]．重庆大学学报(自然科学版)，2000，23(3)：70-73．
[64] 黄席樾，汪先矩，柴毅．汽车智能辅助操作系统中的障碍物检测[J]，重庆大学学报(自然科学版)，2000，23(4)：123-127．
[65] 周欣，黄席樾，樊友平．汽车智能辅助驾驶系统中的单目视觉导航技术[J]．机器人，2003，25(4)：289-295．
[66] 耿伯英，陆建峰，杨静宇．基于模糊主色调的彩色图像分割及道路检测[J]．南京理工大学学报，2000，24(4)：353-358．
[67] 王丰元，周一鸣，孙壮志．车辆引导路线检测的计算机视觉技术初探[J]．农业机械学报，1998，29(1)：1～5．
[68] 郁梅，蒋刚毅．采用快速路面重建的车道和障碍物检测新方法[J]．仪器仪表学报，2002，23(2)：144-149
[69] Lingxi Li, Fei-Yue Wang. the Automated Lane-Changing Model of Intelligent Vehicle Highway Systems[C]. the IEEE 5th International Conference on Intelligent Transportation Systems, 2002,216-218.
[70] Jian-Ping Liu; Han-Gen He; Yu-Fei Liu.The road segmentation for ALV navigation [C]. Intelligent Robots and Systems '94. 'Advanced Robotic Systems and the Real World', IROS '. Proceedings of the IEEE/RSJ/GI International Conference, 1994, (2): 974-979.
[71] Massimo Bertozzi, Alberto Broggi, Alessandra Fascioli. Stereo inverse perspective mapping: theory and applications[J],Image and Vision Computing, 1997, (16):585-590.
[72] 何斌，马天予，王运坚．Visual c++数字图像处理[M]．北京，人民邮电出版社，第二版，2002．
[73] Kate Gregory著，前导工作室译．Visual c++开发使用手册[M]．北京，机械工业出版社，1999．
[74] 陈坚．Visual C++．NET 编程基础专家教程[M]．西安，西安电子科技大学出版社，2002．
[75] 章毓晋．图象处理和分析[M]．北京，清华大学出版社，2000．
[76] 勒中鑫．数字图像信息处理[M]．北京 国防工业出版社 第一版 2003．1
[77] 杨宣禾，周维真．成像跟踪技术导论[M]．西安，西安电子科技大学出版社，1992
[78] 刘文萍，吴立德．图像分割中阈值选取方法比较研究[J]．模式识别与人工智能，1997，10(3)．271-277．
[79] Kreucher, C., Lakshmanan, S. LANA: a lane extraction algorithm that uses frequency domain features[C].Robotics and Automation, IEEE Transactions, 1999, 15(2) : 343-350.
[80] Coda A, Antonello P C, Peters B. Technical and Human Factor Aspects of Automatic Vehicle Control in Emergency Situations[C]. In: Proc of the 4~(th) World Congress on Intelligent Transport Systems, Berlin, 1997, 2096-2301.
[81] Franke U, Gavrila D, Gorzig S. Autonomous Driving Goes Downtown[J]. IEEE IntelligentSystems, 1998,13(6):40-48.
[82] Risack R, Klausmarm P, KrCGer W. Lane Recognition Embedded in a Real-Time Driver Assistance System[C]. Proc of IEEE Intelligent Vehicles Symposium, 1998,35-40.
[83] Aufrere, R., Chapuis, R., Chausse, F..A fast and robust vision based road following algorithm[C]. Intelligent Vehicles Symposium. Proceedings of the IEEE, 2000,192-197.
[84] Chapuis, R., Lancurit, J., Aufrere, R.. Accurate vision based road tracker[C]. Intelligent Vehicle Symposium, 2002. IEEE, 2002, (2): 666-671.
[85] Broggi A, BertE S. Vision-Based Road Detection in Automotive Systems: A Real-Time Expectation-Driven Approach[J]. Journal of Artificial Intelligent Research, 1995, 3(12): 325-348.
[86] Kuan D, Phipps G Hsuch A C. Autonomous Robotic Vehicle Road Following[C]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1988, 10(5): 648-658.