摘要
智能车辆作为智能交通系统的关键技术和重要组成部分,被认为是解决各种交通问题的一个有效途径。智能车辆的研究涉及图像处理、模式识别、人工智能、自动控制、传感器技术等多个学科的理论与技术,集成了信息科学与人工智能技术的最新成果,具有重要的实用价值和学术理论价值。
智能车辆是一个集环境感知、规划决策、操作控制等功能于一体的智能体。在智能车辆诸多研究任务中,对环境信息的感知是所有工作的基础和核心,基于视觉的信息感知是车辆理解外部环境的核心技术,其成功与否直接决定未来智能车辆的生存空间。其中,对于障碍物目标的检测和跟踪又是最为重要和不可或缺的功能,是预防危险和安全行驶的前提条件。目前,高速公路等结构化道路环境中的目标检测技术已基本成熟,但复杂的城市交通环境下的目标检测技术尚不能满足实用化要求,成为智能车辆目标检测领域亟待解决的热点和难点问题。本论文围绕基于视觉导航的智能车辆在城区复杂交通环境中的目标检测、识别和跟踪技术进行了深入研究和探讨。主要研究内容概括如下:
(1)论文回顾了智能车辆的研究进展,介绍了当前国内外典型智能车辆系统概况,对智能车辆领域的主要研究内容和关键技术进行了探讨。在对各种信息感知手段进行综合比较的基础上,介绍了智能车辆目标检测技术的主要流派及其研究进展,并提出了当前目标检测技术的不足和本文研究方向。
(2)论文对机器视觉理论做了综述性介绍,分析了三种具有代表性的视觉理论框架模型,建立了一种针对具体应用改进的计算视觉模型,为算法设计提供指导。从候选目标检测、目标确认识别、目标跟踪定位这三个方面,重点分析了基于视觉的智能车辆目标检测技术的研究进展,提出了本文基于单目视觉的目标检测算法模型,不仅分析了单目视觉方法的可行性,而且阐明了本文算法的总体架构。
(3)论文详细论述了基于单目视觉的候选目标检测方法。对智能车辆候选目标检测中的常用视觉特征进行了分析,介绍了小波变换模极大值对奇异信号探测的理论原理。在此基础上,提出了一种基于小波模极大值和多特征融合的候选目标检测方法。实验表明,该算法能在无道路约束条件下直接从整个像平面中提取候选障碍物目标,有效克服复杂场景中目标特征易被背景或其它目标“淹没”的难题,满足城区环境下智能车辆目标检测的鲁棒性要求。
(4)论文详细论述了基于单目视觉的目标确认识别方法。对机器学习中的统计学习理论和支持向量机原理进行了介绍,对目前支持向量机的多类分类方法进行了归纳和分析,并介绍了集成学习的理论原理。在此基础上,提出了一种基于混合核函数和集成学习改进的二叉树支持向量机多类分类方法。该方法根据目标在场景中的出现概率和类间差异设计二叉树树型结构,采用混合核函数设计分类器分类函数,并采用AdaBoost与SVM相结合的方法对分类器参数进行自适应选取,有效提高了分类器的分类精度和泛化能力。实验表明,该方法可有效解决小样本条件下,城区场景中所需考虑的“车辆-行人-非机动车辆-背景”等多类分类问题。
(5)论文详细论述了基于视觉的目标跟踪定位方法。对Mean Shift算法的理论基础——基于核函数的无参数密度估计及其一般过程进行了介绍,并对算法收敛性条件做了简要分析。在此基础上,提出了一种基于Mean Shift的智能车辆目标跟踪算法。该方法以目标颜色空间为特征空间,采用颜色特征的统计直方图对目标模型进行描述,利用Bhattacharyya系数定义目标模型在相邻帧间的相似性度量,并基于Mean Shift迭代实现被跟踪目标的准确定位。该方法着力改进并解决了经典Mean Shift算法中的以下关键问题:基于Kalman滤波器改进机动目标跟踪初始点选取问题;提出一种分块匹配策略改进目标遮挡情况下的处理问题;提出一种基于匹配贡献度的选择性子模型更新机制,克服了实际跟踪过程中的模型偏移问题,保证算法在实际应用中对目标的长时间稳定跟踪。
最后,对全文的研究工作进行总结,并指出今后工作中进一步研究的方向。
Intelligent vehicle as the key technology and important part of Intelligent Traffic System (ITS) has been regarded as the effective way to resolve these traffic problems. The research of intelligent vehicle involve in image processing, pattern recognition, artificial intelligence, automatic control, sensing technology and so on. It has integrated the latest achievements of the information science and artificial intelligence. Thus, the research of intelligent vehicle has important values of practical and academic theory.
Intelligent vehicle is an intelligent agent which integrates the functions of environmental perception, planning decision and operation control. In the lots of research tasks of intelligent vehicle, the information perception of driving environment is the foundation and key of all works. Machine vision is the key technology of information perception, and its success or failure will directly decide the survive space of intelligent vehicle in the future. Furthermore, the object detection and tracking is the most important and indispensable function in information perception, and is also the precondition of preventing risk and safe driving for intelligent vehicle. At present, the object detection technical in highway traffic scenes has been maturely almost, but it can not meet the practical requirement in complex urban traffic scenes. Thus, it is urgent and hot problem to develope the research of object detection for intelligent vehicle in complex urban traffic scenes. This paper further discusses the vision-based object detection, recognition and tracking in complex urban traffic scenes for intelligent vehicle. Main study content has been summarized as follows:
Firstly, the research progress and typical systems of intelligent vehicle in domestic and international are reviewed, the main research contents and the key techniques of intelligent vehicle are also discussed. Based on the comparison of common information perception methods, the main technical schools of object detection in intelligent vehicle are discussed, and these research progresses are reviewed. Furthermore, the shortages of current research and the direction of future research are proposed in the paper.
Secondly, the machine vision theory and three representative vision theory models are discussed in the paper. A new application-based improved computing vision theory model is established and provides the guiding for the practical algorithm design. From the three views of candidate object detection, object recognition and object tracking, the research progress of vision-based object detection in intelligent vehicle is reviewed. A practical monocular vision-based object detection algorithm model is presented, in which the feasibility of monocular vision and the general algorithm architecture of the paper are discussed.
Thirdly, the monocular vision-based candidate object detection method is discussed detailedly in the paper. The common visual characters for candidate object detection in intelligent vehicle are discussed, and the theory principle of the singular signal detection based on Wavelet Transform Modulus Maxima (WTMM) is introduced. Furthermore, a novel WTMM-based candidate object detection method is presented in the paper.
Experiment shows that the method can directly detect the candidate objects from the whole image plane without road constraint, overcome the problem of the object character submerged by the background and other objects, and meet the robustness acquirements of intelligent vehicle in complex urban traffic scenes. Fourthly, the vision-based object recognition method is discussed detailedly in the paper. The statistical learning theory and the principle of Support Vector Machine (SVM) are introduced, the main SVM-based multi-class classification methods are analysed, and the ensemble learning theory is discussed. Furthermore, a multi-class classification method based on binary tree SVM (BT-SVM) improved by mixtures of kernels and ensemble learning is presented in the paper. In the proposed method, a decision-tree structure is designed based on the distributing probability and pattern diversity of common objects in urban traffic scenes. The classifier function is designed based on the mixtures of kernels. Moreover, the parameters of classifier function are adaptively selected based on AdaBoost. The proposed method effectively improves classification accuracy and generalization ability of the classifer. Experiment shows that the method can effectively resolve the multi-class classification problem including vehicle, pedestrian, non-motor vehicle, background, etc in urban traffic scenes, especially the small samples condition.
Fifthly, the vision-based object tracking method is discussed detailedly in the paper. The theory of no-parametric kernel density estimation based on Mean Shift algorithm is introduced, and the algorithm convergence condition is discussed briefly. Furthermore, a Mean Shift-based intelligent vehicle object tracking method is presented in the paper. In the proposed method, the object color space is used as feature space, the color feature statistical histogram is used to describe the target model, the Bhattacharyya coefficient between target model and target candidate model of adjacent frames is defined as the similarity metric, and the Mean Shift iterative algorithm is applied to locate the tracked object. The proposed method emphasizes to improve the following key problems of classical Mean Shift algorithm: 1) the Kalman-based motion prediction is introdced to improve the tracking initial point selection of maneuvering object; 2) a block matching strategy is presented to improve the processing for object occlusion in complex traffic scenes; 3) a selective submodel updating mechanism based on matching contribution degree is presented to overcome the model migration problem during tracking and guarantee the stability of long-time tracking in the practical application.
Finally, the conclusion of whole research work in the paper is given. Furthermore, the further work and research prospects are introduced.
引文
[1]廖传锦.以人为中心的汽车主动安全预警信息系统研究[D].重庆:重庆大学, 2005.
[2]王宏武,孙逢春,曹琦,刘淑艳.道路交通系统驾驶行为理论与方法[M].北京:科学出版社, 2001.
[3]徐春友,王荣本.世界智能车辆近况综述[J].汽车工程, 2001, 23(5): 289-295.
[4] J.S.Albus. Outline for a Theory of Intelligence [J]. IEEE Trans. on Systems, Man and Cybernetics, 1991, 21(3): 473-509.
[5]徐利民.智能交通系统发展及其战略思考[J].技术经济, 2003, (4): 15-16.
[6]张丰焰.现代智能交通系统及其发展趋势[J].交通科技, 2002, (1): 11-12.
[7]杨殿阁,李克强,郑四发,侯德藻,连小珉.智能交通系统中的汽车技术[J].汽车工程, 2003, 25(3): 223-226.
[8] S.Tsugawa. Vision-based Vehicles in Japan: Machine Vision Systems and Driving Control Systems [J]. IEEE Trans. on Industrial Electronics, 1994, 41(4): 398-405.
[9] F.P.Andresen, L.Davis, R.Eastman, et al. Visual Algorithms for Autonomous Navigation [C]. Proc. of IEEE International Conference on Robotics and Automation, 1985, 2: 856-861.
[10] C.Thorpe, M.H.Hebert, T.Kanade, et al. Vision and Navigation for the Carnegie-Mellon Navlab [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1988, 10(3): 362-373.
[11] S.Baten, M.Lutzeler, E.D.Dickmanns, et al. Techniques for Autonomous, Off-road Navigation [J]. IEEE Trans on Intelligent Systems and Their Applications, 1998, 13(6): 57-65.
[12] G.Brusaglino. Safe and Effective Mobility in Europe-the Contribution of the PROMETHEUS Programme [C]. Proc. of IEE Colloquium on Prometheus and Drive, 1992: 101-110.
[13] M.Bertozzi, A.Broggi, A.Fascioli. Vision-based Intelligent Vehicles: State of the Art and Perspectives [J]. Robotics and Autonomous Systems, 2000, 32(1): 1-16.
[14] M.Bertozzi, A.Broggi. GOLD: a Parallel Real-time Stereo Vision System for Generic Obstacle and Lane Detection [J]. IEEE Trans. on Image Processing, 1998, 7(1): 62-81.
[15] S.E.Shladover, C.A.Desoer, J.K.Hedrick, et al. Automated Vehicle Control Developments in the PATH Program [J]. IEEE Trans. on Vehicular Technology, 1991, 40(1): 114-130.
[16] C.Thorpe, R.C.Coulter, M.Hebert, et al. Smart Cars: the CMU Navlab [C]. Proc. of World Med93, 1993: 26-36.
[17] C.M.Shoemaker, J.A.Bomstein. Overview of the Demo III UGV Program [C]. In Part of the SPIE Conference on Robotic and Semi-Robotic Ground Vehicle Technology, 1998: 202-211.
[18] H.Kamiya, Y.Fujita, T.Tsuruga, et al. Intelligent Technologies of Honda ASV [C]. Proc. of the1996 IEEE Intelligent Vehicle Symposium, 1996: 236-241.
[19] S.Tsugawa, T.Saito, A.Hosaka. Super Smart Vehicle System: AVCS Related Systems for the Future [C]. Proc. of the Intelligent Vehicles’92 Symposium, 1992: 132-137.
[20]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.
[21]张朋飞,何克忠,欧阳正柱,张军宇.多功能室外智能移动机器人实验平台——THMR-V [J].机器人, 2002, 24(2): 97-101.
[22]黄席樾,柴毅,周欣.汽车智能辅助操作系统中的障碍物检测[J].重庆大学学报, 2000, 23(4): 123-126.
[23]黄席樾,汪先矩,柴毅,周欣.基于道路几何模型的单目测距算法[J].重庆大学学报, 2000, 23(3): 70-73.
[24]周欣,黄席樾,黎昱.基于单目视觉的高速公路车道保持与距离测量[J].中国图象图形学报, 2003, 8(5): 590-595.
[25]周欣,黄席樾,樊友平,刘涛.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.
[26]周欣.高速公路单目视觉主动导航技术研究[D].重庆:重庆大学, 2003.
[27]沈志熙,黄席樾.基于数据回归建模的单目视觉测距算法[J].计算机工程与应用, 2007, 43(24): 15-18.
[28]沈志熙,黄席樾,权循宝,李晓伟.基于小波模极大值和SVM的智能车辆障碍物检测[J].四川大学学报(工程科学版), 2008, 40(6): 144-149.
[29]沈志熙,黄瀚敏,黄席樾,李敏.基于视觉的室外移动机器人障碍物检测方法[J].机器人, 2008. (已录用)
[30] Grand Challenge, URL: http://www.darpa.mil/grandchallenge/, 2006.
[31] ELROB, URL: http://www.elrob2006.org/, 2006.
[32] SAPRO, URL: http://www.sapro.com.au/smartdemo/smartdemo2005.htm/, 2006.
[33] Mobileye, URL: http://www.mobileye.com/, 2006.
[34] E.Dagan, O.Mano, G.P.Stein, A.Shashua. Forward collision warning with a single camera [C]. Proc. of the 2004 IEEE Intelligent Vehicles Symposium, 2004: 37-42.
[35]何克忠.智能移动机器人的一种体系结构[J].机器人, 1992, 14(3): 55-58.
[36] D.A.Forsyth. Computer Vision—A Modern Approach [M]. New Jersey: Pearson Education, Inc., 2003.
[37]席裕庚.一类动态不确定环境下机器人的滚动路径规划[J].自动化学报, 2002, 28(2): 161-175.
[38]李兵.基于视觉的智能车辆自主导航控制的研究[D].长春:吉林大学, 2001.
[39] A.Bensrhair, A.Bertozzi, A.Broggi, et al. Stereo Vision-based Feature Extraction for Vehicle Detection [C]. Proc. of the 2002 IEEE Intelligent Vehicles Symposium, 2002, 2: 465-470.
[40] R.Labayrade, D.Aubert. In-Vehicle Obstacles Detection and Characterization by Stereovision [C]. Proc. of Int. Workshop on In-Vehicle Cognitive Computer Vision Systems, 2003: 13-19.
[41] R.Labayrade, D.Aubert, J.P.Tarel. Real Time Obstacle Detection in Stereovision on Non Flat Road Geometry through“V-disparity”Representation [C]. Proc. of the 2002 IEEE Intelligent Vehicles Symposium, 2002, 2: 646-651.
[42] N.Srinivasa. Vision-based Vehicle Detection and Tracking Method for Forward Collision Warning in Automobiles [C]. Proc. of the IEEE Intelligent Vehicles Sym., 2002, 2: 626-631.
[43]李斌,王荣本,郭克友.基于机器视觉的智能车辆障碍物检测方法研究[J].公路交通科技, 2002, 19(4): 126-129.
[44]周欣,黄席樾.基于方向分形维的高速公路车辆边缘检测研究[J].信号处理, 2004, 20(3): 258-262.
[45] L.Andreone, P.C.Antonello, M.Bertozzi, et al. Vehicle detection and localization in infra-red images [C]. Proc. of the IEEE 5th International Conference on ITS, 2002: 141-146.
[46] C.C.Wang, C.Thorpe, A.Suppe. Ladar-based detection and tracking of moving objects from a ground vehicle at high speeds [C]. Proc. of IEEE Intelligent Vehicles Sym., 2003: 416-421.
[47]李斌.智能车辆前方车辆探测及安全车距控制方法的研究[D].长春:吉林大学, 2001.
[48] B.Steux, C.Laurgeau, et al. Fade: a vehicle detection and tracking system featuring monocular color vision and data fusion [C]. Proc. of IEEE Intelligent Vehicles Sym., 2002, 2: 632-639.
[49]贾云得.机器视觉[M].北京:科学出版社, 2000.
[50]章毓晋.图象工程(下册)——图象理解与计算机视觉[M].北京:清华大学出版社, 2000.
[51]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社, 1998.
[52] D. Marr[著],姚国正,刘磊,汪云九[译].视觉计算理论[M].北京:科学出版社, 1988.
[53]马颂德,张正友.计算机视觉——计算理论与算法基础[M].北京:科学出版社, 1998.
[54]高文,陈熙霖.计算机视觉——算法与系统原理[M].北京:清华大学出版社, 1999.
[55]陈熙霖.视觉计算——人类感知能力的延伸[J].测控技术, 2000, 29(5): 7-14.
[56] Milan Sonka, Vaclav Hlavac, Roger Boyle. Image Processing, Analysis, and Machine Vision [M]. Thomson Asia Pte Led, 2002.
[57] J.M.Jolion. Computer Vision Methodologies [J]. Image Understanding, 1994, 59(1): 53-71.
[58] M.Bart, T.H.Romeny. Computer Vision and Mathematica [J]. Computing and Visualization in Science, 2002, 5: 53-65.
[59]王天珍.视觉理论与模型研究的回顾与展望[J].武汉汽车工业大学学报, 1996, 18(6): 7-12.
[60]王天珍.计算机视觉研究进展[J].武汉汽车工业大学学报, 1998, 20(1): 23-27.
[61]王天珍.计算机视觉不需要重建[J].信息与控制, 1999, 28(1): 47-52.
[62]蒋加伏,叶吉祥.计算机视觉系统研究中存在的问题及解决思路[J].长沙交通学院学报, 1999, 15(1): 13-17.
[63]席学强,王润生.计算机视觉模型中的知识及其表示[J].计算机工程与应用, 2000, 11: 45-48.
[64] A.Giachetti, M.Campani, V.Torre. The Use of Optical Flow for Road Navigation [J]. IEEE Trans. on Robotics and Automation, 1998, 14(1): 34-48.
[65] B.Heisele, W.Ritter. Obstacle Detection based on Color Blob Flow [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Detroit, USA, 1995: 282-286.
[66] H.Mori, N.M.Charkari. Shadow and Rhythm as Sign Patterns of Obstacle Detection [C]. Proc. of the IEEE Industrial Electronics Symposium, Budapest, Hungary, 1993: 271-277.
[67] E.D.Dickmanns, R.Behringer, D.Dickmanns, et al. The Seeing Passenger Car‘VaMoRs-P’[C]. Proc. of the IEEE Intelligent Vehicles Symposium, 1994: 68-73.
[68] A.Kuehnle. Symmetry-based Recognition for Vehicle Rears [J]. Pattern Recognition Letters, 1991, 12: 249-258.
[69] T.Kalinke, C.Tzomakas, W.V.Seelen. A Texture-based Object Detection and an Adaptive Model-based Classification [C]. Proc. of the IEEE International Conference on Intelligent Vehicles, Stuttgart, Germany, 1998: 143-148.
[70] N.D.Mattews, P.E.An, D.Charnley, C.J.Harris. Vehicle Detection and Recognition in Greyscale Imagery [J]. Control Engineering Practice, 1996, 4(4): 473-479.
[71] U.Handmann, T.Kalinke, C.Tzomakas, et al. An Image Processing System for Driver Assistance [J]. Image and Vision Computing, 2000, 18(5): 367-376.
[72] D.Guo, T.Fraichard, M.Xie, et al. Color Modeling by Spherical Influence Field in Sensing Driving Environment [C]. Proc. of the IEEE Intelligent Vehicles Symposium, 2000: 249-254.
[73] M.Bertozzi, A.Broggi. S.Castelluccio. A Real-time Oriented System for Vehicle Detection [J]. Journal of Systems Architecture, 1997, 43(1-5): 317-325.
[74] R.Cucchiara, M.Piccardi. Vehicle Detection under Day and Night Illumination [C]. Proc. of the ICSC Intelligent Industrial Automation Symposium, Genoa, Italy, 1999: 789-794.
[75] M.Bertozzi, A.Broggi, A.Fascioli, et al. Stereo Vision-based Vehicle Detection [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Dearborn, USA, 2000: 39-44.
[76] T.K.ten Kate, M.B.van Leewen, S.E.Moro-Ellenberger, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Parma, Italy, 2004: 72-77.
[77] M.B.van Leeuwen, F.C.Groen. Vehicle Detection with a Mobile Camera: Spotting Midrange, Distant, and Passing Cars [J]. IEEE Robotics & Automation Magazine, 2005, 12(1): 37-43.
[78] C.Bregler. Learning and Recognizing Human Dynamics in Video Sequences [C]. Proc. of IEEE CS Conference on Computer Vision and Pattern Recognition, San Juan, 1997: 568-574.
[79] A.Iketani, Y.Kuno, N.Shimada, et al. Real-time Surveillance System Detecting Persons in Complex Scenes [C]. Proc. of Int. Conf. on Image Analysis and Processing, 1999: 1112-1115.
[80] R.Polana, R.Nelson. Detection and Recognition of Periodic, Nonrigid Motion [J]. International Journal of Computer Vision, 1997, 23(3): 261-282.
[81] S.McKenna, S.Gong. Non-intrusive Person Authentication for Access Control by Visual Tracking and Face Recognition [C]. Proc. of Audio and Video based Biometric Person Authentication, Crans-Montana, Switzerland: Springer-Verlag, 1997: 177-184.
[82] L.Zhao, C.E.Thorpe. Stereo and Neural Network based Pedestrian Detection [J]. IEEE Trans. on ITS, 2000, 1(3): 148-154.
[83] D.Beymer, K.Konolige. Real-time tracking of multiple people using continuous detection [D]. Artificial Intelligence Center, SRI International Report, 1998.
[84] A.Mohan, C.Papageorgiou, et al. Example-based object detection in images by components [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001, 23(4): 349-361.
[85] D.M.Gavrila. Pedestrian Detection from a Moving Vehicle [C]. Proc. of the IEEE European Conference on Computer Vision, Dublin, Ireland, 2000: 37-49.
[86] A.Broggi, M.Bertozzi, A.Fascioli, M.Sechi. Shape-based Pedestrian Detection [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Dearborn, USA, 2000: 215-220.
[87] C.Curio, J.Edelbrunner, T.Kalinke, et al. Walking Pedestrian Recognition [J]. IEEE Trans. on ITS, 2000, 1(3): 155-163.
[88] P.Parodi, G.Piccioli. A Feature-based Recognition Scheme for Traffic Scenes [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Detroit, USA, 1995: 229-234.
[89] T.Ito, K.Yamada, K.Nishioka. Understanding Driving Situations using a Network Model [C]. Proc. of the IEEE Intelligent Vehicles Symposium, Detroit, USA, 1995: 48-53.
[90] U.Regensburger, V.Graefe. Visual Recognition of Obstacles on Roads [C]. Proc. of IEEE Int. Conf. on Intelligent Robots and Systems, Munich, Germany, 1994: 980-987.
[91] A.Bensrhair, M.Bertozzi, A.Broggi, et al. A Cooperative Approach to Vision-based Vehicle Detection [C]. Proc. of the IEEE Int. Conf. on ITS, Oakland, USA, 2001: 207-212.
[92] J.W.Wu, X.Zhang. A PCA Classifier and its Application in Vehicle Detection [C]. Proc. of the IEEE International Joint Conference on Neural Networks, Washington, USA, 2001: 600-604.
[93] C.Goerick, N.Detlev, M.Werner. Artificial Neural Networks in Realtime Car Detection andTracking Applications [J]. Pattern Recognition Letters, 1996, 17: 335-343.
[94] H.Schneiderman, T.Kanade. A Statistical Method for 3D Object Detection Applied to Faces and Cars [C]. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, Island, 2000: 746-751.
[95] M.Weber, M.Welling, P.Perona. Unsupervised Learning of Models for Recognition [C]. Proc. of European Conference on Computer Vision, London, UK: Springer-Verlag, 2000: 18-32.
[96] Z.H.Sun, G.Bebis, R.Miller. On-road Vehicle Detection using Evolutionary Gabor Filter Optimization [J]. IEEE Trans. on ITS, 2005, 6(2): 125-137.
[97] A.Khammari, F.Nashashibi, Y.Abramson, et al. Vehicle detection combining gradient analysis and AdaBoost classification [C]. Proc. of the IEEE Conf. on ITS, Vienna, 2005: 1084-1089.
[98] R.Cutler, L.S.Davis. Robust Real-time Periodic Motion Detection, Analysis, and Applications [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(8): 781-796.
[99] C.Wohler, U.Kressel, J.K.Anlaur. Pedestrian recognition by classification of image sequences global approaches vs. local spatio-temporal processing [C]. Proc. of the IEEE Int. Conf. on Pattern Recognition, Barcelona, Spain, 2000: 540-544.
[100] S.K.Weng, C.M.Kuo, S.K.Tu. Video Object Tracking using Adaptive Kalman Filter [J]. Journal of Visual Communication and Image Representation, 2006, 17(6): 1190-1208.
[101] Y.Q.Chen, Y.Rui, T.S.Huang. Multicue HMM-UKF for Real-time Contour Tracking [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(9): 1525-1529.
[102] K.Nummiaro, E.K.Meier, L.V.Gool. An Adaptive Color-based Particle Filter [J]. Image and Vision Computing, 2003, 21(1): 99-110.
[103] K.Nummiaro, E.K.Meier, L.V.Gool. Object Tracking with an Adaptive Color-based Particle Filter [C]. Proc. of the 24th DAGM Pattern Recognition Symposium, Lecture Notes in Computer Science, 2002, 2449: 353-360.
[104] H.Moravec. Towards Automatic Visual Obstacle Avoidance [C]. Proc. of the 5th International Joint Conference on Artificial Intelligence, 1997: 584-590.
[105] R.Polana, R.Nelson. Low Level Recognition of Human Motion [C]. Proc. of the 1994 IEEE Workshop on Motion of Non-Rigid and Articulated Objects, Texas, USA, 1994: 77-82.
[106] W.Daniel, L.Robert. Tracking and Recognition People in color using the Earth Mover’s Distance [C]. Proc. of the IEEE International Workshop on Haptic Virtual Environments and Their Applications, Ottawa, Canada, 2002: 91-96.
[107]郑江滨.视频监视方法研究[D].西安:西北工业大学, 2002.
[108] B.Bascle, P.Bouthemy, et al. Tracking Complex Primitives in an Image Sequence [C]. Proc. of the 12th International Conference on Pattern Recognition, Jerusalem, Israel, 1994: 426-431.
[109] Baumberg, D.Hogg. An Adaptive Eigen-shape Model [C]. Proc. of the 6th British Vision Conference, 1995: 87-96.
[110] K.Kamijo, T.Tanigawa. Stock price pattern recognition-A recurrent neural network approach [C]. Proc. of the IEEE International Conference of Neural Networks, 1990: 215-221.
[111]邵文坤,黄爱民,韦庆.目标跟踪方法综述[J].影像技术, 2006: 17-20.
[112] Kass, M.Witkinm, A.Terzopoulos, D.Snakes. Active contour models [J]. International Journal on Computer Vision, 1998, 1(4): 321-331.
[113] S.Menet, et al. B-snakes: Implementation and Application to Stereo [C]. Proc. of the DARPA Image Understanding Workshop, Pittsburgh, Pennsylvania, 1990: 720-726.
[114] G.D.Hager, M.Dewan, C.V.Stewart. Multiple Kernel Tracking with SSD [C]. Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition, 2004: 790-797.
[115] P.H.Li, F.Chaumette, O.Tahri. A Shape Tracking Algorithm for Visual Serving [C]. Proc. of the IEEE International Conference on Robotics and Automation, 2005: 2858-2863.
[116] D.Comaniciu, V.Ramesh. Mean Shift and Optimal Prediction for Efficient Object Tracking [C]. Proc. of the IEEE Int. Conf. on Image Processing, Vaneconver, Canada, 2000, 3: 70-73.
[117] D.Comaniciu, V.Ramesh, P.Meer. Real-Time Tracking of Non-rigid Objects using Mean Shift [C]. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, 2000: 142-149.
[118] D.Comaniciu, P.Meer. Mean Shift: a robust approach toward Feature Space Analysis [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.
[119] D.Comaniciu, V.Ramesh, P.Meer. Kernel-based Object Tracking [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
[120]宋新,沈振康,王平,王鲁平. Mean Shift在目标跟踪中的应用[J].系统工程与电子技术, 2007, 29(9): 1405-1409.
[121] Z.H.Sun, G.Bebis, R.Miller. Monocular Precrash Vehicle Detection: Features and Classifiers [J]. IEEE Trans. on Image Processing, 2006, 15(7): 2019-2034.
[122]胡斌,何克忠.计算机视觉在室外移动机器人中的应用[J].自动化学报, 2006, 32(5): 774-784.
[123]贾慧星,章毓晋.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学报, 2007, 33(1): 84-90.
[124] N.Matthews, P.An, D.Chamley, C.Harris. Vehicle Detection and Recognition in Grey Scale Imagery [J]. Control Engineering Practice, 1996, 4(4): 473-479.
[125] N.Srinivasa. A Vision-based Vehicle Detection and Tracking Method for Forward Collision Warning [C]. Proc. of the IEEE Intelligent Vehicle Symposium, 2002: 626-631.
[126] Z.H.Sun, R.Miller, G.Bebis, D.DiMea. A Real-time Precrash Vehicle Detection System [J].Proc. of the IEEE Int. Workshop on Application of Computer Vision, 2002, 12: 171-176.
[127] C.Tzomakas, W.Seelen. Vehicle Detection in Traffic Scenes Using Shadows [D]. Tech. Rep. 98-06, Institute for Neuroinformatik: Ruht universitat, 1998.
[128] U.Handmann, T.Kalinke. Fusion of texture and contour based methods for object recognition [C]. Proc. of the IEEE Conference on Intelligent Transportation System, 1997: 876-881.
[129] W.von Seelen, C.Curio, J.Gayko, et al. Scene analysis and organization of behavior in driver assistance systems [C]. Proc. of the IEEE Image Processing Symposium, 2000, 3: 524-527.
[130] J.Badenas, M.Bober, F.Pla. Motion and Intensity based Segmentation and Its Application to Traffic Monitoring [C]. Proc. of the International Conference on Image Analysis and Processings ICIAP’97, Florence, Italy: IAPR, 1997: 502-509.
[131]彭玉华著.小波变换与工程应用[M].北京:科学出版社, 1999.
[132]杨福生著.小波变换的工程分析与应用[M].北京:科学出版社, 1999.
[133] S.Mallat, S.Zhang. Characterization of Signal from Multiscale Edge [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1992, 14(7): 681-693.
[134] S.Mallat. Multi-Frequency Channel Decomposition of Images and Wavelet Model [J]. IEEE Trans. on Acoustics, Speech, and Signal Processing, 1989, 37(12): 2091-2110.
[135] G.P.Nason, B.W.Silverman. The Stationary Wavelet Transform and some statistical Applications [J]. Lecture Notes in Statistics, 1995, 103: 281-299.
[136] M.J.Shensa. The Discrete Wavelet Transform Wedding the A trous and Mallat Algorithms [J]. IEEE Trans. on Signal Processing, 1992, 40(10): 2462-2482.
[137]许彬,郑链,王克勇,宋承天.基于信号奇异性分析的小目标检测方法[J].红外技术, 2005, 27(3): 245-249.
[138] S.Mallat, W.L.Hwang. Singularity detection and processing with wavelets [J]. IEEE Trans. on Information Theory, 1992, 14(7): 710-732.
[139] V.Vapnik. The Nature of Statistical Learning Theory [M]. New York: Springer-Verlag, 1995.
[140]边肇祺,张学工等著.模式识别[M].北京:清华大学出版社, 2000.
[141]张学工.关于统计学习理论与支持向量机[J].自动化学报, 2000, 26(1): 32-42.
[142] V.Vapnik. Statistical Learning Theory [M]. New York: J. Wiley, 1998.
[143] N.Cristianini, J.Shawe-Taylor[著],李国正,王猛,曾华军[译].支持向量机导论[M].北京:电子工业出版社, 2004.
[144]祝海龙.统计学习理论的工程应用[D].西安:西安交通大学, 2002.
[145] M.G.Genton. Classes of Kernels for Machine Learning: A Statistics Perspective [J]. Journal of Machine Learning Research, 2001, 2: 299-312.
[146] C.J.C.Burges. A Tutorial on Support Vector Machines for Pattern Recognition [J]. DataMining and Knowledge Discovery, 1998, 2(2): 121-167.
[147] J.Weston, C.Watkins. Support Vector Machines for Multi-class Pattern Recognition [C]. Proc. of the European Artificial Neural Networks Sympusium, Bruges, 1999: 219-224.
[148] D.Sebald, J.Buchlew. Support Vector Machines and Multiple Hypothesis Test Problem [J]. IEEE Trans. on Signal Processing, 2001, 49(11): 2865-2872.
[149] C.Hsu, C.J.Lin. A Comparison of Methods for Multi-class Support Vector Machines [J]. IEEE Trans. on Neural Networks, 2002, 13(2): 415-425.
[150] J.C.Platt, N.Cristianini, J.Shawe-Taylor. Large Margin DAGs for Multiclass Classification [C]. In: Advances in Neural Information Processing Systems, Cambridge, 2000: 547-553.
[151] F.Takahashi, S.Abe. Decision-Tree-Based Multiclass Support Vector Machines [C]. Proc. of the 9th Int. Conf. on Neural Information Processing, Singapore, 2002: 1418-1422.
[152] F.Schwenker. Hierarchical Support Vector Machines for Multi-class Pattern Recognition [C]. Proc. of the 4th International Conference on Knowledge-based Intelligent Engineering System & Allied Technologies, Chennai, 2000: 561-565.
[153] T.G.Dietterich. Machine Learning Research: Four Current Directions [J]. AI Magazine, 1997, 18(4): 97-136.
[154] T.G.Dietterich. Ensemble Methods in Machine Learning [J]. Lecture Notes in Computer Science, 2000, 1857: 1-15.
[155]周志华,陈世福.神经网络集成[J].计算机学报, 2002, 25(1): 1-8.
[156] G.Valentini, T.G.Dietterich. Bias-variance Analysis of Support Vector Machines for the Development of SVM-Based Ensemble Methods [J]. Journal of Machine Learning Research, 2004, 5: 725-775.
[157] D.Pavlov, J.Mao, B.Dom. Scaling-up Support Vector Machines Using Boosting Algorithm [C]. Proc. of the 15th IEEE CS Conf. on Pattern Recognition, Los Alamitos, 2000, 2: 2219-2222.
[158] H.C.Kim, S.Pang, H.M.Je, et al. Constructing Support Vector Machine Ensemble [J]. Pattern Recognition, 2003, 36(12): 2757-2767.
[159] L.G.Valiant. A Theory of the Learnable [J]. Communications of the ACM, l984, 27(11): 1134-l142.
[160] M.Kearns. The Computational Complexity of Machine Learning [M]. Cambridge: MIT Press, 1990.
[161] M.Kearns, L.G.Valiant. Cryptographic Limitations on Learning Boolean Formulae and Finite Automata [J]. Journal of the ACM, 1994, 41(1): 67-95.
[162] L.Breiman. Bagging Predictors [J]. Machine Learning, 1996, 24(2): 123-140.
[163] R.E.Schapire. The strength of weak learn ability [J]. Machine Learning, 1990, 5(2): 197-227.
[164] Y.Freund. Boosting a Weak Learning Algorithm by Majority [J]. Information and Computation, 1995, 121(2): 256-285.
[165] H.Drucker, R.E.Schapire, P.Simard. Boosting Performance in Neural Networks [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1993, 7(4): 705-719.
[166] Y.Freund, R.E.Schapire. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting [J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139.
[167] R.E.Schapire, Y.Singer. Improved Boosting Algorithms Using Confidence-Rated Predictions [J]. Machine Learning, 1999, 37(3): 297-336.
[168] Y.Freund, R.E.Sehapire. Experiments with a New Boosting Algorithm [C]. Proc. of the 13th International Conference on Machine Learning, San Francisco, CA, 1996: 148-156.
[169] R.E.Sehapire, Y.Freund, P.Bartlett, W.S.Lee. Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods [J]. The Annals of Statistics, l998, 26(5): l65l-l686.
[170] A.J.Grove, D.Schuurmans. Boosting in the Limit: Maximizing the Margin of Learned Ensembles [C]. Proc. of the 15th Int. Conf. on Artificial Intelligence, Menlo Park, CA, 1998: 692-699.
[171] L.K.Hansen, P.Salamon. Neural Network Ensembles [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1990, 12(10): 993-1001.
[172] A.Krogh, J.Vedelsby. Neural Network Ensembles, Cross Validation, and Active Learning [C]. In: Advances in Neural Information Processing Systems, Cambridge, MA: MIT Press, 1995: 231-238.
[173] K.Tumer, J.Ghosh. Error Correlation and Error Reduction in Ensemble Classifiers [J]. Connection Science, 1996, 8(3-4): 385-404.
[174] S.M.Azimi, S.Zckavat. Cloud Classification using Support Vector Machines [C]. Proc. of the IEEE Geosciences and Remote Sensing Sym., Honolulu, 2000: 669-671.
[175] G.F.Smits, E.M.Jordaan. Improved SVM Regression using Mixtures of Kernels [C]. Proc. of the 2002 International Joint Conference on Neural Networks, Hawaii, 2002: 2785-2790.
[176] B.Scholkopf, S.Mika, C.J.C.Burges, et al. Input Space versus Feature Space in Kernel-based Methods [J]. IEEE Trans. on Neural Networks, 1999, 10: 1000-1017.
[177] Tan Ying, Wang Jun. A Support Vector Machine with a Hybrid Kernel and Minimal Vapnik-Chervonenkis Dimension [J]. IEEE Trans. on Knowledge and Data Engineering, 2004, 14(4): 385-395.
[178] L.I.Kuncheva, C.J.Whitaker. Measures of Diversity in Classifier Ensembles and their Relationship with the Ensemble Accuracy [J]. Machine Learning, 2003, 51(2): 181-207.
[179] P.Melville, R.J.Mooney. Creating Diversity in Ensembles using Artificial Data [J].Information Fusion, 2005, 6(1): 99-111.
[180]胡金海,谢寿生,杨帆,等.基于支持向量机的组合分类方法及应用[J].推进技术, 2007, 28(6): 669-673.
[181] Y.F.Zhu, L.F.Tian, Z.Y.Mao, et al. Mixtures of Kernels for SVM Modeling [J]. Lecture Notes in Computer Science, 2005, 36(10): 601-607.
[182] R.C.Gonzalez, R.E.Woods著.阮秋琦,阮宇智等译.数字图像处理(第二版) [M].北京:电子工业出版社, 2004.
[183]李桂芝,安成万,杨国胜,等.基于场景识别的移动机器人定位方法研究[J].机器人, 2005, 27(2): 123-127.
[184] C.C.Chang, C.J.Lin. LIBSVM: A Library for Support Vector Machines [EB/OL]. URL: http://www.csie.ntu.edu.tw/ ~cjlin/libsvm, 2004.
[185] D.Opitz, R.Maclin. Popular Ensemble Methods: An Empirical Study [J]. Journal of Artificial Intelligence Research, 1999, 11: 169-198.
[186] K.Fukunaga, L.D.Hosteller. The Estimation of the Gradient of a Density Function, with Application in Pattern Recognition [J]. IEEE Trans. on Information Theory, 1975, 21: 32-40.
[187] Y.Z.Cheng. Mean Shift, Mode Seeking, and Clustering [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.
[188]付永会,张凤超,张宪民.一种改进的基于颜色直方图的实时目标跟踪算法[J].数据采集与处理, 2001, 16(3): 309-314.
[189] C.J.Yang, R.Duraiswami, L.Davis. Similarity Measure for Nonparametric Kernel Density based Object Tracking [C]. Proc. of the 18th Annual Conference on Neural Information Processing Systems, Victoria, British Columbia, Canada: NIPS, 2004.
[190] R.T.Collins. Mean-shift Blob Tracking through Scale Space [C]. Proc. of the IEEE CS Conference on Computer Vision and Pattern Recognition, 2003: 234-240.
[191]李乡儒,吴福朝,胡占义.均值漂移算法的收敛性[J].软件学报, 2005, 16(3): 365-374.
[192] T.Kailath. The Divergence and Bhattacharyya Distance Measures in Signal Selection [J]. IEEE Trans. on Communication Technology, 1967, 15: 52-60.
[193] F.Porikli, O.Tuzel, P.Meer. Covariance tracking using model update based on Lie Algebra [C]. Proc. of the IEEE CS Conf. on Computer Vision and Pattern Recognition, 2006, 1: 728-735.
[194] R.T.Collins, Y.X.Liu, M.Leordeanu. Online Selection of Discriminative Tracking Features [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643.
[195]王永忠,梁彦,赵春晖,潘泉.基于多特征融合自适应融合的核跟踪方法[J].自动化学报, 2008, 34(4): 393-399.
[196] H.T.Nguyen, M.Worring, R.Van.Boomagaard. Occlusion Robust Adaptive Template Tracking[C]. Proc. of IEEE Int. Conf. on Computer Vision, Vancouver, British Columbia, Canada, New York: Printing House, 2001, I: 678-683.
[197] N.S.Peng, Yang Jie, Liu Zhi. Mean Shift Blob Tracking with Kernel Histogram Filtering and Hypothesis Testing [J]. Pattern Recognition Letters, 2005, 26: 605-614.
[198] R.V.Babu, P.Patrick, B.Patrick. Robust Tracking with Motion Estimation and Local Kernel-based Color Modeling [J]. Image and Vision Computing, 2007, 25(8): 1205-1216.