车辆集成式横向安全预警系统及其关键技术
|
摘要
车辆横向安全预警系统能够有效避免或降低行驶碰撞带来的人员伤亡和经济损失，对提高交通安全具有重大意义。针对传统预警系统存在的横向安全预警功能集成性不足和误警率漏警率较高的问题，本文提出一种车辆集成式横向安全预警系统结构，并开展车辆驾驶意图识别、符合驾驶员习惯的车道偏离预警算法和邻车道后侧向车辆识别等关键技术的研究，实现车道偏离预警和换道碰撞预警功能的集成，并对各项关键技术进行实验验证，以达到提高系统精度及系统对多种路况和不同驾驶员的适应性的目的。
论文首先研究车辆驾驶意图识别方法。通过对各种信息在大量不同驾驶员的车道保持和车道更换行为下的统计分析，确定了它们对于车辆驾驶意图的反映程度，从而提取出应用于意图识别的特征信息组，将其输入到支持向量机中，通过对支持向量机方法中内核、时窗及特征向量的研究选取，提出基于信息统计的车辆驾驶意图识别方法，有效提高了识别的准确率和实时性。
然后，研究适应驾驶员习惯的车道偏离预警方法。通过对传统预警方法存在误警和漏警原因的分析，提出一种驾驶员横向驾驶行为特性指标，并进一步得到了该特性的区域划分方法，在此基础上设计考虑驾驶员横向驾驶行为特性的分区域分指标的车道偏离预警算法，并提出一个综合误警率和漏警率的指标来分析预警效果和确定算法参数，有效提高了预警的准确性。
其次，研究基于邻车道后侧向车辆识别的换道碰撞预警方法。通过识别邻车道来规划车辆识别区域，选取了底部阴影、边缘和形状特征进行后向车辆识别，并提出一种基于多梯形区域的三阶累计量统计方法，在后向车辆识别方法识别失效时，实现对侧向车辆的稳定识别和跟踪，并设计预警策略，完成换道碰撞预警功能。
最后，为验证所提出方法的有效性和正确性，搭建相关实验平台，并进行了大量驾驶员的实车实验。使用采集到的实验数据完成了车辆集成式横向安全预警系统关键技术的验证，结果表明，本文设计的车辆集成式横向安全预警系统能够有效区分车辆驾驶意图，采用的预警算法符合驾驶员习惯，能降低误警率和漏警率，明显改善预警效果。
The vehicle lateral warning system can effectively decrease the crash accidents,make drivers easier and thus has a great significance for the traffic safety. Conventionalsystems should make some improvements in the performances due to the lack ofintegrated lateral warning functions and the high false and missed alarm rates. To solvethese problems, a scheme of vehicle integrated lateral warning system is proposed andthe key technologies are studied, which include the driver lateral operation intentionidentification method, the lane departure warning algorithm considering lateral drivingbehavior characteristics and the lane change collision warning algorithm based onrear/side vehicle detection. Thus the integration of lane departure and lane changecollision warning functions is realized and the key technologies of the integrated systemare verified to adapt to the variety of road conditions and driving styles.
Firstly the driver lateral operation intention identification method is studied. Alarge amount of driver experiment data is collected and analyzed to determine therelationship with driver intentions and thus the feature data set for recognition isselected. The Support Vector Machine method is applied and the accuracy and real timeperformances of driver intention identification are improved.
Then the lane departure warning algorithm considering driver lateral drivingbehavior characteristics is investigated. The cause for missed and false alarms isanalyzed and an index for lateral driving behavior characteristics is proposed. Based onthis cause, the lateral driving areas are divided and the lane departure warning algorithmdepending on area and index is determined. A warning efficiency index integrating falsealarm rate and missed alarm rate is designed to validate the warning efficiency.
Meanwhile the lane change collision warning algorithm based on rear/side vehicledetection is determined. The vehicle detection area is programmed through side lanerecognition and the rear vehicle recognition is done based on multi-feature fusion. Athree order cumulant statistics method is designed based on the multi-trapezoid areas,which can realize the robust side vehicle recognition and tracking where the rear vehiclerecognition method makes no effect. The disturbances are excluded and the real-timeperformance and accuracy are improved.
Finally field tests are carried out to validate the proposed methods. The test resultsshow that the proposed vehicle integrated lateral warning system can effectivelydistinguish the drivers lateral operation intentions and the warning algorithms are inaccordance with the driver characteristics, thus reducing false alarm rate and missedalarm rate and improving warning effects.
论文首先研究车辆驾驶意图识别方法。通过对各种信息在大量不同驾驶员的车道保持和车道更换行为下的统计分析，确定了它们对于车辆驾驶意图的反映程度，从而提取出应用于意图识别的特征信息组，将其输入到支持向量机中，通过对支持向量机方法中内核、时窗及特征向量的研究选取，提出基于信息统计的车辆驾驶意图识别方法，有效提高了识别的准确率和实时性。
然后，研究适应驾驶员习惯的车道偏离预警方法。通过对传统预警方法存在误警和漏警原因的分析，提出一种驾驶员横向驾驶行为特性指标，并进一步得到了该特性的区域划分方法，在此基础上设计考虑驾驶员横向驾驶行为特性的分区域分指标的车道偏离预警算法，并提出一个综合误警率和漏警率的指标来分析预警效果和确定算法参数，有效提高了预警的准确性。
其次，研究基于邻车道后侧向车辆识别的换道碰撞预警方法。通过识别邻车道来规划车辆识别区域，选取了底部阴影、边缘和形状特征进行后向车辆识别，并提出一种基于多梯形区域的三阶累计量统计方法，在后向车辆识别方法识别失效时，实现对侧向车辆的稳定识别和跟踪，并设计预警策略，完成换道碰撞预警功能。
最后，为验证所提出方法的有效性和正确性，搭建相关实验平台，并进行了大量驾驶员的实车实验。使用采集到的实验数据完成了车辆集成式横向安全预警系统关键技术的验证，结果表明，本文设计的车辆集成式横向安全预警系统能够有效区分车辆驾驶意图，采用的预警算法符合驾驶员习惯，能降低误警率和漏警率，明显改善预警效果。
The vehicle lateral warning system can effectively decrease the crash accidents,make drivers easier and thus has a great significance for the traffic safety. Conventionalsystems should make some improvements in the performances due to the lack ofintegrated lateral warning functions and the high false and missed alarm rates. To solvethese problems, a scheme of vehicle integrated lateral warning system is proposed andthe key technologies are studied, which include the driver lateral operation intentionidentification method, the lane departure warning algorithm considering lateral drivingbehavior characteristics and the lane change collision warning algorithm based onrear/side vehicle detection. Thus the integration of lane departure and lane changecollision warning functions is realized and the key technologies of the integrated systemare verified to adapt to the variety of road conditions and driving styles.
Firstly the driver lateral operation intention identification method is studied. Alarge amount of driver experiment data is collected and analyzed to determine therelationship with driver intentions and thus the feature data set for recognition isselected. The Support Vector Machine method is applied and the accuracy and real timeperformances of driver intention identification are improved.
Then the lane departure warning algorithm considering driver lateral drivingbehavior characteristics is investigated. The cause for missed and false alarms isanalyzed and an index for lateral driving behavior characteristics is proposed. Based onthis cause, the lateral driving areas are divided and the lane departure warning algorithmdepending on area and index is determined. A warning efficiency index integrating falsealarm rate and missed alarm rate is designed to validate the warning efficiency.
Meanwhile the lane change collision warning algorithm based on rear/side vehicledetection is determined. The vehicle detection area is programmed through side lanerecognition and the rear vehicle recognition is done based on multi-feature fusion. Athree order cumulant statistics method is designed based on the multi-trapezoid areas,which can realize the robust side vehicle recognition and tracking where the rear vehiclerecognition method makes no effect. The disturbances are excluded and the real-timeperformance and accuracy are improved.
Finally field tests are carried out to validate the proposed methods. The test resultsshow that the proposed vehicle integrated lateral warning system can effectivelydistinguish the drivers lateral operation intentions and the warning algorithms are inaccordance with the driver characteristics, thus reducing false alarm rate and missedalarm rate and improving warning effects.
引文
[1]公安部交通管理局.中华人民共和国道路交通事故统计年报（2005年度）.江苏省无锡市:公安部交通管理科学研究所,2006.
[2]刘强,陆化普,张永波,等.我国道路交通事故特征分析与对策研究.中国安全科学学报,2006,16(6):123~128.
[3] Richard Bishop. A survey of intelligent vehicle applications worldwide. Proceedings of theIEEE Intelligent Vehicles Symposium. Dearborn:2000:25~30.
[4]2006年全国道路交通事故概况[J].道路交通管理,2007,02
[5] Reason J. Driving errors, driving violations and accident involvement. Ergonomics,1995,38(5):1036~1048.
[6]孙平,宋瑞,王海霞.我国道路交通事故成因分析及预防对策.安全与环境工程,2007,02(14):97~100.
[7]2004年全国道路交通事故情况[J].道路交通管理,2005,01
[8] Aufrere R, Gowdy J, Mertz C, et al. Perception for collision avoidance and autonomousdriving. Mechatronics,2003,13(10):1149~1161.
[9] Nobe S A, Wang Feiyue. An overview of recent developments in automated lateral andlongitudinal vehicle controls. In: IEEE International Conference on System, Man andCybernetics. Tucson,AZ: IEEE Press,2001, Vol.5.3447~3452.
[10] Tatsuya Yoshida, Hiroshi Kuroda, Takaomi Nishigaito. Adaptive driver-assistance systems.HITACHI REVIEW,2004,53(4).
[11] Aotani T, Yamaoka S, Tajima T. Research&development of driving safety support systems.Proceedings of the41st SICE Annual Conference. Osaka: SICE,2002(3):1792~1795.
[12] Sugimoto M, Aoyama K, Shimizu D, et al. Realization of head-on collision warning system atintersections-DSSS: driving safety support systems. Proceedings of the IEEE IntelligentVehicles Symposium. Dearborn:2000:731-735.
[13] Marchau V, Van der Heijden R, Molin E. Desirability of advanced driver assistance from roadsafety perspective: the case of ISA. Safety Science,2005,43(1):11-27.
[14] Kyongsu Yi, Jintai Chung. Nonlinear brake control for vehicle CW/CA Systems. IEEE/ASMETransactions on Mechatronics,2001,6(1):17-25.
[15] Ioannis Golias, Mstthew G. Karlaftis. An International Comparative Study of Self-reportDriver Behavior. Transportation Research Part F.2002:243~246.
[16] Pomerleau Dean,et al. Performance Specification Development for Roadway DepartureCollision Avoidance Systems,Proc. of4th World Congress on Intelligent TransportationSystems,Berlin, Germany, Oct.21-24,1997
[17] Pomerleau Dean,et al. Performance Specification Development for Roadway DepartureCollisionAvoidance Systems Final Report,1999
[18] Mei Chen, Todd Jochem, Dean Pomerleau. AURORA: AVision-Based Roadway DepartureWarning System,Carnegie Mellon University technical report,1997
[19] Iteris’Lane Departure Warning System Now Available on Mercedes Trucks in Europe. TheSource for Intelligent Vehicle News IV source,June2000
[20] Dagan Erez,et al. Forward Collision Warning with a Single Camera, IEEESymposium,Dearborn,MI,USA,October3-5,2000
[21] Jiang Gangyi, Chen Yanhua, Yu Mei, et al. Approach to lane departure detection. Proceedingsof5th International Conference on Signal Processing. Beijing, China: IEEE Press,2000:971-974.
[22] Kunihito Sato et al, Development Of Steering Assist System(STAR) for the Lane DepartureWarning, IEEE International Conference on Intelligent Robots and Systems,1997
[23] Zheng Nanning, Tang Shuming, Cheng Hong, et al. Toward intelligent driver assistance andsafety warning system. IEEE Intelligent Systems,2004,19(2):8-11.
[24] Li Qing, Zheng Nanning, Cheng Hong. Springrobot: a prototype autonomous vehicle and itsalgorithms for lane detection. IEEE Transactions on Intelligent Transportation System,2004,5(4):300-308.
[25] Cheng Hong, Zheng Nanning, Ma Lin, et al. Vehicle active safety applications by fusingmultiple-sensor for the Springrobot system. Proceedings of IEEE International Conference onVehicular Electronics and Safety. Xi'an, Shaan'Xi, China: IEEE Press,2005:155-160.
[26]邢征北,郑南宁,刘铁,等.道路检测算法及其DSP实时实现.微电子学与计算机,2004,21(5):114-117.
[27]李青,郑南宁,马琳,等.基于主元神经网络的非结构化道路跟踪.机器人,2005,27(3):247-251.
[28]程洪,郑南宁,高振海,等.基于主元神经网络和K-均值的道路识别算法.西安交通大学学报,2003,37(8):812-815.
[29] Liu Tie, Zheng Nanning, Zhao Li, et al. Learning based symmetric feature selection forvehicle detection. Proceedings of IEEE Intelligent Vehicles Symposium. Las Vegas, NV, USA:IEEE Press,2005:124-129.
[30]李析,郑南宁,程洪.基于Kruppa方程的摄像机标定.西安交通大学学报，2003,37(8):820-823.
[31]李青,郑南宁,张雪涛.车载摄像机的一种简易标定方法.机器人,2003,25(7):626-630.
[32]王荣本,游峰,崔高健,等.基于计算机视觉高速智能车辆的道路识别.计算机工程与应用,2004(26):18-21.
[33]王荣本,余天洪,郭烈,等.车道标识线识别和跟踪方法研究.计算机工程与应用,2005(24):19-22.
[34] Li Bin, Wang Rongben, Guo Keyou. Vehicle detection based on distributed sensor decisionfusion. Proceedings of the IEEE5th International Conference on Intelligent TransportationSystems. Singapore: IEEE Press,2002:242-247.
[35] Li Bin, Wang Rongben, Chu Jiangwei. A new optimal controller for intelligent vehicleheadway distance. Proceedings of IEEE Intelligent Vehicle Symposium. Paris, France: IEEEPress,2002:387-392.
[36]余天洪.基于机器视觉的车道偏离预警系统研究：[博士学位论文].吉林：吉林大学交通学院,2006.12.
[37]王荣本,余天洪,郭烈,等.基于机器视觉的车道偏离预警系统研究综述,汽车工程,2005年(第27卷)第4期, P463~466
[38]孙振平,安向京,贺汉根. CITAVT-IV—视觉导航的自主车.机器人,2002,24(2):115-121.
[39]张朋飞,何克忠,欧阳正柱,等.多功能室外智能移动机器人实验平台—THMR-V.机器人,2002,24(2):97-101.
[40]高锋,李克强,王建强,等.车速控制系统自适应油门控制器设计.汽车工程,2005,27(4):418-422.
[41]周亮,宾洋,李克强,等.走-停巡航系统分层控制器设计.汽车工程,2005,27(3):319-322.
[42]马莹,李克强,高锋,等.改进的有限时间最优预瞄横向控制器设计.汽车工程,2006,28(5):433-438.
[43] Zhifeng LIU, Lei GUO, Jianqiang WANG and Keqiang LI. An Integrated System of DrivingEnvironment Recognition based on THASV-II. Journal of Mechanical Systems forTransportation and Logistics, Vol.1, No.3(2008), pp.252-263.
[44]刘志峰,王建强,李克强.具有鲁棒特性的车载雷达有效目标确定方法.清华大学学报(自然科学版),48(5),2008:875-878.
[45] Zhifeng LIU, Jianqiang WANG and Keqiang LI. A robust method to determine relevant targetvehicle using vehicular radar. IEEE International Conference on Vehicular Electronics andSafety, Beijing, China, Dec.13-15,2007.
[46] M. Ruder, W. Enkelmann, R. Gamitz. Highway Lane Change Assistant, Procs. IEEEIntelligent Vehicle Symposium, Versaille, France, June17-212002, pp.240-244
[47] Gideon P. Stein, Ofer Mano, Amnon Shashua. A Robust Method for Computing VehicleEgo-motion, Proceedings of the IEEE Intelligent Vehicles Symposium2000, Dearborn (MI),USA October3-5,2000
[48] Andreas Eidehall, Jochen Pohl, Fredrik Gustafsson. A new approach to lane guidance systems,Proceedings of the8th International IEEE Conference on Intelligent Transportation SystemsVienna,Austria, September13-16,2005
[49] Tim van Dijck, Geert A.J. van der Heijden. VisionSense-An advanced lateral collisionwarning system. In:2005IEEE Intelligent Vehicles Symposium Conference Proceedings,6-8June2005, Las Vegas, Nevada, USA.
[50]王荣本,游峰,崔高健,等.车辆安全换道分析.吉林大学学报:工学版,2005,35(2):179-182.
[51] Rasmussen, J., Information Processing and Human machine Interaction: An Approach toCognitive Engineering, New York: North-Holland,1986
[52] Michon, J. A.. A Critical View of Driver Behaviour Models:What Do We Know, What ShouldWe Do?, In: Evans, L.&Schwing, R. C., Human Behaviour and Traffic Safety. Plenum Press,New York,1985
[53] Boer, E. R., et al., Modeling Driver Behavior with Different Degrees of Automation: AHierarchical Decision Framework of Interacting Mental Models. In Proceedings of the XVIIthEuropeanAnnual Conference on Human Decision Making and Manual Control, Valenciennes,France, Dec.14~16,1998
[54] Alex Pentland, Andrew Liu, Modeling and Prediction of Human Behavior, NeuralComputation11,229–242(1999),1999Massachusetts Institute of Technology
[55] Nobuyuki Kuge, Tomohiro Yamamura, Osamu Shimoyama, Andrew Liu. A Driver BehaviorRecognition Method Based on a Driver Model Framework, Proceedings of the2000SocietyofAutomotive Engineers World Congress, Detroit, MI,2000.
[56] Oliver, N., Pentland, A. P. Graphical Models for Driver Behavior Recognition in SmartCar.Proceedings of the IEEE Intelligent Vehicles Symposium2000.
[57] Hiren Mansukhlal Mandalia. Pattern Recognition Techniques to Infer Driver Intentions,master thesis, Drexel University, Philadelphia, December2004
[58] Claudio Rosito Jung and Christian Roberto Kelber. A Lane Departure Warning System basedon a Linear-Parabolic Lane Model, IEEE Intelligent Vehicles Symposium, University ofParma, Parma, Italy June14-17,2004
[59] Pau-Lo Hsu, Hsu-Yuan Cheng, Bol-Yi Tsuei, Wen-Jing Huang. The Adaptive Lane-DepartureWarning System, SICE2002. Proceedings of the41st SICE Annual Conference, Volume:5,5-7Aug.2002:2867-2872vol.5
[60] Qing Li, et al. Springrobot: A Prototype Autonomous Vehicle and Its Algorithms for LaneDetection, IEEE Transactions on Intelligent Transportation Systems, Vol.5,NO.4,December2004
[61] H. Godhelp, P. Milgram, and G. Blaauw. The development of a time related measure todescribe driver strategy. Human Factor, vol.26,no.3, pp.257-268,1984.
[62] R. Risack, N. Mohler, W. Enkelmann. A Video-based Lane Keeping Asistant. Proceedingsof the IEEE Intelligent Vehicles Symposium2000,2000.10:356~361
[63] Said Mammar, Sibastien Glaser, Mariana Netto, Jean-Marc Blosseville, Time to LineCrossing and Vehicle Dynamics for Lane Departure Avoidance,2004IEEE IntelligentTransportation Systems Conference Washington, D.C., USA, October36,2004
[64] Chiu-Feng Lin, A. Galip Ulsoy, David J. LeBlanc, Vehicle Dynamics and ExternalDisturbance Estimation for Vehicle Path Prediction, IEEE transactions on control systemstechnology, vol.8, No.3, May2000
[65] Chen Mei, et al. AURORA: A Vision Based Roadway Departure Warning System, IEEEConference on Intelligent Robots and Systems Human Robot Interaction and CooperativeRobots,Vol11,August,1995
[66] Dagan Erez, et al. Forward Collision Warning with a Single Camera IEEE Symposium,Dearborn, MI, USA, October3-5,2000
[67] Kunihito Sato, et al. Development Of Steering Assist System(STAR) for the Lane DepartureWarning, IEEE International Conference on Intelligent Robots and Systems,1997
[68] Wu Mo, et al. On vision-based lane departure detection approach, IEEE2005
[69] Parag H. Batavia, Driver-Adaptive Lane Departure Warning Systems, PHD thesis, TheRobotics Institute Carnegie Mellon University, September20,1999
[70] Tom Pilutti, A. Galip Ulsoy. Fuzzy-Logic-Based Virtual Rumble Strip for Road DepartureWarning Systems, IEEE Transactions on Intelligent Transportation Systems, Vol.4, NO.1,March2003
[71] Miguel Gonzilez-Mendoza, Bruno James, Neil Hernandez-Gress, Andre Titli, Daniel Esttve.AComparison of Road Departure Warning Systems on Real Driving Conditions,2004IEEEIntelligent Transportation Systems Conference Washington, D.C., USA, October34,2004
[72] V. Graefe and W. Efenberger. A Novel Approach for the Detection of Vehicles on Freeways byReal-Time Vision. Proc. IEEE Intelligent Vehicles Symposium,1996.
[73] M. Betke, E. Haritglu and L. Davis. Real-time multiple vehicle detection and tracking from amoving vehicle. Machine Vision andApplications, vol.12, no.2, pp.69-83,2000
[74] PH Batavia, DA Pomerleau, CE Thorpe. Overtaking Vehicle Detection Using Implicit OpticalFlow. IEEE Conference on Intelligent Transportation,1997
[75] C. Knoeppel, A. S chanz, B.Michae1is. Robust Vehicle Detection at Large Distance UsingLow Resolution Cameras. Proc. IEEE Intelligent Vehicles Symposium, pp.276-272,2000
[76] Axel Techmer. Real-time Motion Analysis for Monitoring the Rear and Lateral Road. IEEEIntelligent Vehicles Symposium, pp.704-709,2004
[77] J. C. Reed. Side zone automotive radar. Proc.1997National Radar Conference, Syracuse, NY,May,1997, pp.186-190.
[78] O. Achler, M. Trivedi. Vehicle Wheel Detector using2D Filter Banks. IEEE IntelligentVehicles Symposium, Parma, Italy, June14-172004, pp.25-30
[79] Leanne Matuszyk, Alexander Zelinsky Lars Nilsson, Magnus Rilbe. Stereo Panoramic Visionfor Monitoring Vehicle Blind-spots.2004IEEE Intelligent Vehicles Symposium, University ofParma, Parma, Italy June14-17,2004
[80] Aaron Steinfeld, David Duggins, et al. Development of the Side Component of the TransitIntegrated Collision Warning System.2004IEEE Intelligent Transportation SystemsConference, Washington, D.C., USA, October36,2004
[81] Mark Tucker, Adam Heenan, Alastair Buchanan. Real Time Embedded Sensor Fusion forDriver Assistance. Proceedings of the8th International IEEE Conference on IntelligentTransportation Systems, Vienna,Austria, September13-16,2005
[82] Greg Welch and Gary Bishop, An Introduction to the Kalman Filter, Department of ComputerScience University of North Carolina,2006.
[83] Venhovens P J T, Naab K. Vehicle dynamics estimation using Kalman filters. Vehicle SystemDynamics,1999,32(2):171-184.
[84] Eom T D, Lee J J. Hierarchical object recognition algorithm based on Kalman filter foradaptive cruise control system using scanning laser. Proceedings of the IEEE49th VehicularTechnology Conference. Houston, TX, USA: IEEE Press,1999:2343-2347.
[85]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.电子测量与仪器学报,2000,14(2):15-20.
[86] Amditis A, Polychronopoulos A, Karaseitanidis I, et al. Multiple sensor collision avoidancesystem for automotive applications using an IMM approach for obstacle tracking. Proceedingsof the Fifth International Conference on Information Fusion. Annapolis, Maryland, USA:IEEE Press,2002:812-817.
[87]皮燕妮,史忠科,黄金.智能车中基于单目视觉的前车检测和跟踪.计算机应用,2005,25(1):220-223.
[88] Vapnik V. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag,1982
[89] V apnik V. The Nature of Statistical Learning Theory, NY: Springer-Verlag,1995
[90] Vapnik V, Levin E, Le Cun Y. Measuring the VC-dimension of a learning machine. NeuralComputation,1994,6:851～876.
[91] Boser B, Guyon I, Vapnik V. At raining algorithm for optimal margin classifiers, FifthAnnual Workshop on Computational Learning Theory. Pittsburgh: ACM Press,1992
[92] Boser B, Guyon I, Vapnik V. At raining algorithm for optimal margin classifiers, FifthAnnual Workshop on Computational Learning Theory. Pittsburgh: ACM Press,1992
[93] Cortes C, Vapnik V. Support vector networks. Machine Learning,1995,20:273～297
[94] Schoblkopf B, Burges C, Vapnik V. Extracting support data for a given task. In: Fayyad U M,U thurusamy R(eds.). Proc. of First Int l. Conf. on Knowledge Discovery&Data Mining,AAA I Press,1995,262～267
[95] Vapnik V, Golowich S, Smola A. Support vector method for function approximation,regression estimation, and signal processing. In: Mozer M, Jordan M, Petsche T (eds). NeuralInformation Processing Systems, MIT Press,1997,9
[96]张朋飞.室外高速移动机器人视觉导航技术的研究[博士学位论文].北京:清华大学，2002.
[97]张贤达.时间序列分析—高阶统计量方法.北京:清华大学出版社,1996,1—20.
[98] Farook Sattar, Goran Solomonsson, Nonparametric Waveform Estimation Using Filter Bank[J]. IEEE transactions on signal processing,1996,44(2):240—247.
[99]姬中华,黄土涛,孟雅俊等,谐波恢复的时间平均三阶累积量方法及其工程应用.振动与冲击,2006,25(1):10—13.
[100] Farook Sattar, Goran Solomonsson, On Detection Using Filter Banks and Higer OrderStatistics[J]. IEEE transactions on aerospace and electronic system,2000,36(4):1179—1189.
[101]王华民,陈霞等.基于高阶累积量的齿轮故障诊断研究.机械强度,2004,26(3):247—249.
[102]姜宏.高阶循环统计量在移动通信系统定位参数估计中的应用[博士学位论文],吉林：吉林大学,2005.
[103]陈冬梅.高阶循环统计量在多径情况下DOA估计中的应用[硕士学位论文],吉林：吉林大学,2002.
[104]郭磊.基于机器视觉的智能汽车行驶环境感知系统[博士学位论文].北京:清华大学,2007.
[2]刘强,陆化普,张永波,等.我国道路交通事故特征分析与对策研究.中国安全科学学报,2006,16(6):123~128.
[3] Richard Bishop. A survey of intelligent vehicle applications worldwide. Proceedings of theIEEE Intelligent Vehicles Symposium. Dearborn:2000:25~30.
[4]2006年全国道路交通事故概况[J].道路交通管理,2007,02
[5] Reason J. Driving errors, driving violations and accident involvement. Ergonomics,1995,38(5):1036~1048.
[6]孙平,宋瑞,王海霞.我国道路交通事故成因分析及预防对策.安全与环境工程,2007,02(14):97~100.
[7]2004年全国道路交通事故情况[J].道路交通管理,2005,01
[8] Aufrere R, Gowdy J, Mertz C, et al. Perception for collision avoidance and autonomousdriving. Mechatronics,2003,13(10):1149~1161.
[9] Nobe S A, Wang Feiyue. An overview of recent developments in automated lateral andlongitudinal vehicle controls. In: IEEE International Conference on System, Man andCybernetics. Tucson,AZ: IEEE Press,2001, Vol.5.3447~3452.
[10] Tatsuya Yoshida, Hiroshi Kuroda, Takaomi Nishigaito. Adaptive driver-assistance systems.HITACHI REVIEW,2004,53(4).
[11] Aotani T, Yamaoka S, Tajima T. Research&development of driving safety support systems.Proceedings of the41st SICE Annual Conference. Osaka: SICE,2002(3):1792~1795.
[12] Sugimoto M, Aoyama K, Shimizu D, et al. Realization of head-on collision warning system atintersections-DSSS: driving safety support systems. Proceedings of the IEEE IntelligentVehicles Symposium. Dearborn:2000:731-735.
[13] Marchau V, Van der Heijden R, Molin E. Desirability of advanced driver assistance from roadsafety perspective: the case of ISA. Safety Science,2005,43(1):11-27.
[14] Kyongsu Yi, Jintai Chung. Nonlinear brake control for vehicle CW/CA Systems. IEEE/ASMETransactions on Mechatronics,2001,6(1):17-25.
[15] Ioannis Golias, Mstthew G. Karlaftis. An International Comparative Study of Self-reportDriver Behavior. Transportation Research Part F.2002:243~246.
[16] Pomerleau Dean,et al. Performance Specification Development for Roadway DepartureCollision Avoidance Systems,Proc. of4th World Congress on Intelligent TransportationSystems,Berlin, Germany, Oct.21-24,1997
[17] Pomerleau Dean,et al. Performance Specification Development for Roadway DepartureCollisionAvoidance Systems Final Report,1999
[18] Mei Chen, Todd Jochem, Dean Pomerleau. AURORA: AVision-Based Roadway DepartureWarning System,Carnegie Mellon University technical report,1997
[19] Iteris’Lane Departure Warning System Now Available on Mercedes Trucks in Europe. TheSource for Intelligent Vehicle News IV source,June2000
[20] Dagan Erez,et al. Forward Collision Warning with a Single Camera, IEEESymposium,Dearborn,MI,USA,October3-5,2000
[21] Jiang Gangyi, Chen Yanhua, Yu Mei, et al. Approach to lane departure detection. Proceedingsof5th International Conference on Signal Processing. Beijing, China: IEEE Press,2000:971-974.
[22] Kunihito Sato et al, Development Of Steering Assist System(STAR) for the Lane DepartureWarning, IEEE International Conference on Intelligent Robots and Systems,1997
[23] Zheng Nanning, Tang Shuming, Cheng Hong, et al. Toward intelligent driver assistance andsafety warning system. IEEE Intelligent Systems,2004,19(2):8-11.
[24] Li Qing, Zheng Nanning, Cheng Hong. Springrobot: a prototype autonomous vehicle and itsalgorithms for lane detection. IEEE Transactions on Intelligent Transportation System,2004,5(4):300-308.
[25] Cheng Hong, Zheng Nanning, Ma Lin, et al. Vehicle active safety applications by fusingmultiple-sensor for the Springrobot system. Proceedings of IEEE International Conference onVehicular Electronics and Safety. Xi'an, Shaan'Xi, China: IEEE Press,2005:155-160.
[26]邢征北,郑南宁,刘铁,等.道路检测算法及其DSP实时实现.微电子学与计算机,2004,21(5):114-117.
[27]李青,郑南宁,马琳,等.基于主元神经网络的非结构化道路跟踪.机器人,2005,27(3):247-251.
[28]程洪,郑南宁,高振海,等.基于主元神经网络和K-均值的道路识别算法.西安交通大学学报,2003,37(8):812-815.
[29] Liu Tie, Zheng Nanning, Zhao Li, et al. Learning based symmetric feature selection forvehicle detection. Proceedings of IEEE Intelligent Vehicles Symposium. Las Vegas, NV, USA:IEEE Press,2005:124-129.
[30]李析,郑南宁,程洪.基于Kruppa方程的摄像机标定.西安交通大学学报，2003,37(8):820-823.
[31]李青,郑南宁,张雪涛.车载摄像机的一种简易标定方法.机器人,2003,25(7):626-630.
[32]王荣本,游峰,崔高健,等.基于计算机视觉高速智能车辆的道路识别.计算机工程与应用,2004(26):18-21.
[33]王荣本,余天洪,郭烈,等.车道标识线识别和跟踪方法研究.计算机工程与应用,2005(24):19-22.
[34] Li Bin, Wang Rongben, Guo Keyou. Vehicle detection based on distributed sensor decisionfusion. Proceedings of the IEEE5th International Conference on Intelligent TransportationSystems. Singapore: IEEE Press,2002:242-247.
[35] Li Bin, Wang Rongben, Chu Jiangwei. A new optimal controller for intelligent vehicleheadway distance. Proceedings of IEEE Intelligent Vehicle Symposium. Paris, France: IEEEPress,2002:387-392.
[36]余天洪.基于机器视觉的车道偏离预警系统研究：[博士学位论文].吉林：吉林大学交通学院,2006.12.
[37]王荣本,余天洪,郭烈,等.基于机器视觉的车道偏离预警系统研究综述,汽车工程,2005年(第27卷)第4期, P463~466
[38]孙振平,安向京,贺汉根. CITAVT-IV—视觉导航的自主车.机器人,2002,24(2):115-121.
[39]张朋飞,何克忠,欧阳正柱,等.多功能室外智能移动机器人实验平台—THMR-V.机器人,2002,24(2):97-101.
[40]高锋,李克强,王建强,等.车速控制系统自适应油门控制器设计.汽车工程,2005,27(4):418-422.
[41]周亮,宾洋,李克强,等.走-停巡航系统分层控制器设计.汽车工程,2005,27(3):319-322.
[42]马莹,李克强,高锋,等.改进的有限时间最优预瞄横向控制器设计.汽车工程,2006,28(5):433-438.
[43] Zhifeng LIU, Lei GUO, Jianqiang WANG and Keqiang LI. An Integrated System of DrivingEnvironment Recognition based on THASV-II. Journal of Mechanical Systems forTransportation and Logistics, Vol.1, No.3(2008), pp.252-263.
[44]刘志峰,王建强,李克强.具有鲁棒特性的车载雷达有效目标确定方法.清华大学学报(自然科学版),48(5),2008:875-878.
[45] Zhifeng LIU, Jianqiang WANG and Keqiang LI. A robust method to determine relevant targetvehicle using vehicular radar. IEEE International Conference on Vehicular Electronics andSafety, Beijing, China, Dec.13-15,2007.
[46] M. Ruder, W. Enkelmann, R. Gamitz. Highway Lane Change Assistant, Procs. IEEEIntelligent Vehicle Symposium, Versaille, France, June17-212002, pp.240-244
[47] Gideon P. Stein, Ofer Mano, Amnon Shashua. A Robust Method for Computing VehicleEgo-motion, Proceedings of the IEEE Intelligent Vehicles Symposium2000, Dearborn (MI),USA October3-5,2000
[48] Andreas Eidehall, Jochen Pohl, Fredrik Gustafsson. A new approach to lane guidance systems,Proceedings of the8th International IEEE Conference on Intelligent Transportation SystemsVienna,Austria, September13-16,2005
[49] Tim van Dijck, Geert A.J. van der Heijden. VisionSense-An advanced lateral collisionwarning system. In:2005IEEE Intelligent Vehicles Symposium Conference Proceedings,6-8June2005, Las Vegas, Nevada, USA.
[50]王荣本,游峰,崔高健,等.车辆安全换道分析.吉林大学学报:工学版,2005,35(2):179-182.
[51] Rasmussen, J., Information Processing and Human machine Interaction: An Approach toCognitive Engineering, New York: North-Holland,1986
[52] Michon, J. A.. A Critical View of Driver Behaviour Models:What Do We Know, What ShouldWe Do?, In: Evans, L.&Schwing, R. C., Human Behaviour and Traffic Safety. Plenum Press,New York,1985
[53] Boer, E. R., et al., Modeling Driver Behavior with Different Degrees of Automation: AHierarchical Decision Framework of Interacting Mental Models. In Proceedings of the XVIIthEuropeanAnnual Conference on Human Decision Making and Manual Control, Valenciennes,France, Dec.14~16,1998
[54] Alex Pentland, Andrew Liu, Modeling and Prediction of Human Behavior, NeuralComputation11,229–242(1999),1999Massachusetts Institute of Technology
[55] Nobuyuki Kuge, Tomohiro Yamamura, Osamu Shimoyama, Andrew Liu. A Driver BehaviorRecognition Method Based on a Driver Model Framework, Proceedings of the2000SocietyofAutomotive Engineers World Congress, Detroit, MI,2000.
[56] Oliver, N., Pentland, A. P. Graphical Models for Driver Behavior Recognition in SmartCar.Proceedings of the IEEE Intelligent Vehicles Symposium2000.
[57] Hiren Mansukhlal Mandalia. Pattern Recognition Techniques to Infer Driver Intentions,master thesis, Drexel University, Philadelphia, December2004
[58] Claudio Rosito Jung and Christian Roberto Kelber. A Lane Departure Warning System basedon a Linear-Parabolic Lane Model, IEEE Intelligent Vehicles Symposium, University ofParma, Parma, Italy June14-17,2004
[59] Pau-Lo Hsu, Hsu-Yuan Cheng, Bol-Yi Tsuei, Wen-Jing Huang. The Adaptive Lane-DepartureWarning System, SICE2002. Proceedings of the41st SICE Annual Conference, Volume:5,5-7Aug.2002:2867-2872vol.5
[60] Qing Li, et al. Springrobot: A Prototype Autonomous Vehicle and Its Algorithms for LaneDetection, IEEE Transactions on Intelligent Transportation Systems, Vol.5,NO.4,December2004
[61] H. Godhelp, P. Milgram, and G. Blaauw. The development of a time related measure todescribe driver strategy. Human Factor, vol.26,no.3, pp.257-268,1984.
[62] R. Risack, N. Mohler, W. Enkelmann. A Video-based Lane Keeping Asistant. Proceedingsof the IEEE Intelligent Vehicles Symposium2000,2000.10:356~361
[63] Said Mammar, Sibastien Glaser, Mariana Netto, Jean-Marc Blosseville, Time to LineCrossing and Vehicle Dynamics for Lane Departure Avoidance,2004IEEE IntelligentTransportation Systems Conference Washington, D.C., USA, October36,2004
[64] Chiu-Feng Lin, A. Galip Ulsoy, David J. LeBlanc, Vehicle Dynamics and ExternalDisturbance Estimation for Vehicle Path Prediction, IEEE transactions on control systemstechnology, vol.8, No.3, May2000
[65] Chen Mei, et al. AURORA: A Vision Based Roadway Departure Warning System, IEEEConference on Intelligent Robots and Systems Human Robot Interaction and CooperativeRobots,Vol11,August,1995
[66] Dagan Erez, et al. Forward Collision Warning with a Single Camera IEEE Symposium,Dearborn, MI, USA, October3-5,2000
[67] Kunihito Sato, et al. Development Of Steering Assist System(STAR) for the Lane DepartureWarning, IEEE International Conference on Intelligent Robots and Systems,1997
[68] Wu Mo, et al. On vision-based lane departure detection approach, IEEE2005
[69] Parag H. Batavia, Driver-Adaptive Lane Departure Warning Systems, PHD thesis, TheRobotics Institute Carnegie Mellon University, September20,1999
[70] Tom Pilutti, A. Galip Ulsoy. Fuzzy-Logic-Based Virtual Rumble Strip for Road DepartureWarning Systems, IEEE Transactions on Intelligent Transportation Systems, Vol.4, NO.1,March2003
[71] Miguel Gonzilez-Mendoza, Bruno James, Neil Hernandez-Gress, Andre Titli, Daniel Esttve.AComparison of Road Departure Warning Systems on Real Driving Conditions,2004IEEEIntelligent Transportation Systems Conference Washington, D.C., USA, October34,2004
[72] V. Graefe and W. Efenberger. A Novel Approach for the Detection of Vehicles on Freeways byReal-Time Vision. Proc. IEEE Intelligent Vehicles Symposium,1996.
[73] M. Betke, E. Haritglu and L. Davis. Real-time multiple vehicle detection and tracking from amoving vehicle. Machine Vision andApplications, vol.12, no.2, pp.69-83,2000
[74] PH Batavia, DA Pomerleau, CE Thorpe. Overtaking Vehicle Detection Using Implicit OpticalFlow. IEEE Conference on Intelligent Transportation,1997
[75] C. Knoeppel, A. S chanz, B.Michae1is. Robust Vehicle Detection at Large Distance UsingLow Resolution Cameras. Proc. IEEE Intelligent Vehicles Symposium, pp.276-272,2000
[76] Axel Techmer. Real-time Motion Analysis for Monitoring the Rear and Lateral Road. IEEEIntelligent Vehicles Symposium, pp.704-709,2004
[77] J. C. Reed. Side zone automotive radar. Proc.1997National Radar Conference, Syracuse, NY,May,1997, pp.186-190.
[78] O. Achler, M. Trivedi. Vehicle Wheel Detector using2D Filter Banks. IEEE IntelligentVehicles Symposium, Parma, Italy, June14-172004, pp.25-30
[79] Leanne Matuszyk, Alexander Zelinsky Lars Nilsson, Magnus Rilbe. Stereo Panoramic Visionfor Monitoring Vehicle Blind-spots.2004IEEE Intelligent Vehicles Symposium, University ofParma, Parma, Italy June14-17,2004
[80] Aaron Steinfeld, David Duggins, et al. Development of the Side Component of the TransitIntegrated Collision Warning System.2004IEEE Intelligent Transportation SystemsConference, Washington, D.C., USA, October36,2004
[81] Mark Tucker, Adam Heenan, Alastair Buchanan. Real Time Embedded Sensor Fusion forDriver Assistance. Proceedings of the8th International IEEE Conference on IntelligentTransportation Systems, Vienna,Austria, September13-16,2005
[82] Greg Welch and Gary Bishop, An Introduction to the Kalman Filter, Department of ComputerScience University of North Carolina,2006.
[83] Venhovens P J T, Naab K. Vehicle dynamics estimation using Kalman filters. Vehicle SystemDynamics,1999,32(2):171-184.
[84] Eom T D, Lee J J. Hierarchical object recognition algorithm based on Kalman filter foradaptive cruise control system using scanning laser. Proceedings of the IEEE49th VehicularTechnology Conference. Houston, TX, USA: IEEE Press,1999:2343-2347.
[85]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.电子测量与仪器学报,2000,14(2):15-20.
[86] Amditis A, Polychronopoulos A, Karaseitanidis I, et al. Multiple sensor collision avoidancesystem for automotive applications using an IMM approach for obstacle tracking. Proceedingsof the Fifth International Conference on Information Fusion. Annapolis, Maryland, USA:IEEE Press,2002:812-817.
[87]皮燕妮,史忠科,黄金.智能车中基于单目视觉的前车检测和跟踪.计算机应用,2005,25(1):220-223.
[88] Vapnik V. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag,1982
[89] V apnik V. The Nature of Statistical Learning Theory, NY: Springer-Verlag,1995
[90] Vapnik V, Levin E, Le Cun Y. Measuring the VC-dimension of a learning machine. NeuralComputation,1994,6:851～876.
[91] Boser B, Guyon I, Vapnik V. At raining algorithm for optimal margin classifiers, FifthAnnual Workshop on Computational Learning Theory. Pittsburgh: ACM Press,1992
[92] Boser B, Guyon I, Vapnik V. At raining algorithm for optimal margin classifiers, FifthAnnual Workshop on Computational Learning Theory. Pittsburgh: ACM Press,1992
[93] Cortes C, Vapnik V. Support vector networks. Machine Learning,1995,20:273～297
[94] Schoblkopf B, Burges C, Vapnik V. Extracting support data for a given task. In: Fayyad U M,U thurusamy R(eds.). Proc. of First Int l. Conf. on Knowledge Discovery&Data Mining,AAA I Press,1995,262～267
[95] Vapnik V, Golowich S, Smola A. Support vector method for function approximation,regression estimation, and signal processing. In: Mozer M, Jordan M, Petsche T (eds). NeuralInformation Processing Systems, MIT Press,1997,9
[96]张朋飞.室外高速移动机器人视觉导航技术的研究[博士学位论文].北京:清华大学，2002.
[97]张贤达.时间序列分析—高阶统计量方法.北京:清华大学出版社,1996,1—20.
[98] Farook Sattar, Goran Solomonsson, Nonparametric Waveform Estimation Using Filter Bank[J]. IEEE transactions on signal processing,1996,44(2):240—247.
[99]姬中华,黄土涛,孟雅俊等,谐波恢复的时间平均三阶累积量方法及其工程应用.振动与冲击,2006,25(1):10—13.
[100] Farook Sattar, Goran Solomonsson, On Detection Using Filter Banks and Higer OrderStatistics[J]. IEEE transactions on aerospace and electronic system,2000,36(4):1179—1189.
[101]王华民,陈霞等.基于高阶累积量的齿轮故障诊断研究.机械强度,2004,26(3):247—249.
[102]姜宏.高阶循环统计量在移动通信系统定位参数估计中的应用[博士学位论文],吉林：吉林大学,2005.
[103]陈冬梅.高阶循环统计量在多径情况下DOA估计中的应用[硕士学位论文],吉林：吉林大学,2002.
[104]郭磊.基于机器视觉的智能汽车行驶环境感知系统[博士学位论文].北京:清华大学,2007.