摘要
基于视频处理的交通事件识别是智能交通领域中较有前途的应用技术之一,可为城市交通管理与控制提供全面、实时的交通状态信息。目前基于视频处理的智能化交通事件识别系统仍处于发展阶段,在某些关键技术环节,特别是在运动目标交通行为分析以及交通事件识别模型构建等方面尚需进一步研究。
本文结合图像处理、模式识别、机器学习等理论与方法,围绕交通事件视频识别过程中的若干关键技术问题进行系统性的研究。首先针对背景模型的背景初始化、背景表达与更新进行深入探讨,实现了复杂场景下的自适应前景运动区域检测;同时给出了运动阴影去除的解决方案,提高了运动目标的检测精度。结合运动目标的形态特性与运动特性设计了基于多类支持向量机的分类算法,实现了混合交通运动目标的类别判断。提出了基于卡尔曼滤波的多特征匹配跟踪算法与基于历史运动信息补偿的遮挡处理方法,保证了复杂遮挡情况下的运动状态准确估计。综合考虑轨迹的空间特性、方向特性、类别特性,提出了运动模式的多层次学习方法,并由此构建了基于Bayes空间模式匹配以及基于起讫点方向模式匹配的异常行为检测方法。将运动目标的状态属性与交通场景中的上下文相关信息相结合,定义了简单事件、复杂事件等具体概念,为事件识别提供了通用的表达形式;在此基础上,构建了基于Bayes分类器与逻辑约束相结合的基本事件识别方法及基于隐马尔可夫模型的复杂事件识别方法。通过对实际场景中交通事件的识别验证了本文方法的有效性。
本文的研究成果深化了交通事件信息视频检测理论与方法,为运动目标的交通行为特性研究、智能化交通事件信息采集提供了有效的技术手段,具有重要的理论意义与实用价值。
In recent years, video detection technology is applied more and more in the field of intelligent transportation. Traffic event recognition based on video is one of the most promising applications in it. Traffic event automatic recognition technology could provide basic information for urban intelligent transportation management and control, and play an important role in easing traffic jams, reducing traffic accidents and ensuring travel safety. Currently, research of intelligent traffic event recognition system based on video processing is still at the exploratory stage that many key technical issues remain to be resolved. In this paper, key techniques of the process of video-based traffic event recognition are studied systematically, including moving object detection, object recognition and tracking, traffic behavior analysis and traffic event recognition.
Moving object detection is the basic component of video detection and surveillance, which provides essential resource for behavior analysis and event recognition. Background model is crucial to obtain the background image for detecting moving targets effectively. Generally, background model is consisting of three parts: background initialization, background representation and background update. Among them, background initialization is the premise of background representation and update, while background representation and updating is the basis to maintain and update background image in complicated scenes for a long time. A background initialization algorithm based on the stable interval sequence searching is used in the paper. All stable non-overlapping intervals in the temporal sequence of each pixel are detected to obtain probably backgrounds first, and then background set is constructed with the pixel value variable-constrained to realize background initialization. From experiments it can be seen that the algorithm proposed could overcome "pseudo-background" generated from the slow motion of large-scale targets, as well as the accurate initial background could extracted when foreground coverage is more than 50% in the training sequence. Based on background initialization, realtime background is represented by Gaussian Mixture Model whose parameters are solved by EM algorithm. In addition, for realizing long-term background maintenance, the object-level background update algorithm is presented with the consideration of foreground motion regions information detected. This algorithm can solve the problem that suspended foreground objects become one part of the background during background update process. Foreground motion regions detected are often including moving shadow which has a significant impact on feature representation, classification and tracking of moving targets. So object-level moving shadow detection model based on RGB color variable degree is utilized to eliminate moving shadow of multi-objects effectively. Tests through several video sequences obtained from realistic scenarios show that proposed methods have good robustness and self-adaptability. This part of research enriches theories and methods of video detection and surveillance, as well as lays the foundation for traffic event recognition based on video processing.
Moving objects’categories and spatio-temporal motion information could be obtained from object classification and tracking. In the aspect of the moving object recognition and classification, two basic issues are focused on: feature selection and representation, as well as classification model choice and learning. In order to provide information of target types of mixed traffic, a simple effective feature representation algorithm based on‘centro-bias’moment is proposed. Centro-bias moments feature has the invariability of rotation, translation and scale, which can overcome the influence of the moving status and dynamic environment. Meantime, object velocity is extracted as the motion feature. Combination of these two representation feature, multi-class support vector machine (SVM) is used to construct optimal hyperplanes for classifying moving object into vehicles, bikes and pedestrians. Experimental results show that the classification accuracy rate can reach 89.4%. In the aspect of motion tracking of multi-class objects in mixed traffic, multi-feature matching method based on Kalman filter is developed, which is combined with motion feature, shape feature and color feature. Additionly, to solve the problem of temporary trajectory missing caused by occlusion in the process of tracking, occlusion handling method based on historical motion information compensation is proposed. The method ensures an accurate estimate of the state of motion in the complex environment. The proposed methods are validated under different traffic scenes. Results show that the proposed tracking method is robust and adaptive, and has a good real-time property that the processing speed is below 0.02 seconds / frame. This part of research provides effective technical means to obtain object feature information for behavior analysis and event recognition.
Traffic objects motion pattern and abnormal behavior can be obtained by trajectory distribution learning. In order to solve limitations that most exist methods of behavior pattern recognition rely on spatial characteristics, multi-level trajectory pattern learning algorithm is presented considering spatial characteristic, orientation characteristic and type characteristic. First, improved Hausdorff distance measure approach is utilized to construct spatial similarity matrix of a collection of traces and spectral clustering is used to realizing spatial pattern learning. Secondly, distribution of trace begin-points and end-points are fitted by GMM model. Orientation pattern can be learn From this. Thirdly, trace type pattern is obtained by hierarchical clustering algorithm with object categories. Multi-level trajectory pattern learning algorithm proposed is tested with realistic scenarios videos and good performances are showed in the experimental results. Abnormal behavior detection algorithms based on spatial pattern matching and orientation pattern matching are proposed respectively. Traffic behaviors of lane-changing and reverse-driving are detected effectively through these algorithms. This part of research provides technical support to study behavior characteristics of traffic targets.
Traffic event recognition not only depends on reasoning and analysis of object behavior, but also is closely related with context information. If there is a lack of context information, the meaning and content of event can’t be described accurately. Hence, traffic event representation and recognition method based on context is developed and the concept of context information in traffic event is defined. Context is divided into spatial context, temporal context, object context and special parameter context according to the event content. And then, event unit is constructed with object’s property and one context information. Based on this, a common semantics representation form is realized involving basic event and complex event. For traffic event recognition, basic event recognition method based on Bayes classifier combined with logical restriction and complex event recognition method based on HMM model are developed. Events of pedestrian illegal crossing and temporary parking are recognized effectively through our approaches. This part of research provides a theoretical guidance and reference for traffic event recognition system.
In summary, the achievement of our research results deepens the theories and approaches of traffic event information video detection, and provides some guidance and reference meaning for the follow-up studies. On the other hand, the research has an important application value that it provides effective technical support for traffic behavioral characteristics research and intelligent traffic event information collection.
引文
[1].汤淑明,王坤峰,李元涛.基于视频的交通事件自动检测技术综述[J].公路交通科技, 2006. Vol. 23(08): pp. 116-121.
[2]. A. RAZAVI, A survey of automatic incident detection systems[R]. Victoria,BC,Canada, Prepared for Province of British Columbia Ministry of Transportation and Highways. 1995.
[3].姜桂艳,温慧敏,杨兆升.高速公路交通事件自动检测系统与算法设计[J].交通运输工程学报, 2001. Vol. 1(01): pp. 77-81.
[4]. P. G. Michalopoulos. Vehicle detection through video image processing: The AUTOSCOPE system[J]. IEEE Transactions on Vehicular Technology, 1991. Vol. 40(1): pp. 21-29.
[5]. http://www.gaodewei.com.
[6]. http://www.citilog.com/.
[7]. http://www-sop.inria.fr/orion/ADVISOR/.
[8]. http://www.research.ibm.com/peoplevision/index.html.
[9]. L. Wang, W. M. Hu, T. N. Tan. Recent developments in human motion analysis[J]. Pattern Recognition, 2003. Vol. 36(3): pp. 585-601.
[10].王亮,胡卫明,谭铁牛.基于步态的身份识别[J].计算机学报, 2003. Vol. 26(3): pp. 353-360.
[11].徐成华,王蕴红,谭铁牛.三维人脸建模与应用[J].中国图象图形学报, 2004. Vol. 9(8): pp. 893-903.
[12]. B. Steven, Airborne Video Surveillance[R]. Florida, HARRIS CORP MELBOURNE FL GOVERNMENT COMMUNICATIONS DIV. Feb. 2002.
[13]. I. Haritaoglu, D. Harwood, L. S. Davis. W4 who? when? where? what? a real time system for detecing and tracking people[C]. in Proceedings of IEEE International Conference on Face and Gesture Recognition. 1998, Vol. : pp. 222-227.
[14]. R. Collins, A. Lipton, T. Kanade, et al., A System for Video Surveillance and Monitoring: VSAM Final Report[R]. Technical report CMU-RI-TR-00-12, Carnegie Mellon University. 2000.
[15]. M.Suchendra, Bhandarkar, X. Luo. Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring[C]. in Computer Society Conference on Computer Vision and Pattern Recognition. 2005, Vol. : pp. 55-56.
[16]. Batavia, Parag, Pomerleau, et al., Detecting Overtaking Vehicles With Implicit Optical Flow[R], CMU RI Technical Report, CMU-RI-TR-97-28. 1997.
[17]. S. Mckenna. Tracking Groups of People[J]. Computer Vision and Image Understanding, 2000. Vol. 80(1): pp. 42-56.
[18]. B. Shoushtarian, H. E. Bez. A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking[J]. Pattern Recognition Letters, 2005. Vol. 26: pp. 5-26.
[19]. C. R. Wren, A. J. Azarbayejani, T. J. Darrell, et al. Pfinder: real-time tracking of the human body[C]. in Proceedings of SPIE - The International Society for Optical Engineering. 1996, Vol. 2615: pp. 89-98.
[20]. C. Stauffer, W. E. L. Grimson. Adaptive background mixture models for real-time tracking[C]. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999, Vol. 2: pp. 246-252.
[21]. M.Harville, G. Gordon, J. Woodfill. Foreground Segmentation Using Adaptive Mixture Models in Color and Depth[C]. in IEEE Workshop on Detection and Recognition of Events in Video. 2001, Vol. : pp. 3-11.
[22]. I.Haritaoglu, D. Harwood, L. S. Davis. W4: Real-Time Surveillance of People and Their Activities[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000. Vol. 22(8): pp. 809-830.
[23]. B.Gloyer. Video-based Freeway Monitoring System Using Recursive Vehicle Tracking[C]. in Proc. of IS&T-SPIE Symposium on Electronic Imaging: Image and Video Processing. 1995, Vol. : pp. 173-180.
[24]. L. Warren, Y. Yee-Hong. Stationary background generation: An alternative to the difference of two images[J]. Pattern Recognition, 1990. Vol. 23(12): pp. 1351~1359.
[25]. H.Z.Wang, D.Suter. A novel robust statistical method for background initialization and visual surveillance[J]. Computer Vision, 2006. Vol. Pt I: pp. 328-337.
[26]. D.Gutchess, M.Trajkovic, E.Cohen-Solal. A background model initialization algorithm for video surveillance[C]. in Proc.of the 8th IEEE Int'l Conf.on Computer Vision. 2001, Vol. : pp. 733-740.
[27]. A. Colombari, A. Fusiello, V. Murino. Background Initialization in Cluttered Sequences[J]. Computer Vision and Pattern Recognition Workshop, 2006. Vol. 17(22): pp. 197-197.
[28]. M. Cristani, M. Bicego, V. Murino. Multi-level background initialization using Hidden Markov Models[C]. in First ACM SIGMM international workshop on Video surveillance. 2003, Vol. : pp. 11-20.
[29]. C. Ridder, O. Munkelt, a. H. Kirchner. Adaptive background estimation and foreground detection using kalman filtering[C]. in Proc International Conference on recent Advances in Mechatronics. 1995, Vol. : pp. 193-199.
[30]. F.Kahl, R.Hartley, V.Hilsenstein. Novelty detection in image sequences with dynamic background[C]. in Statistical Methods in Video Processing. 2004, Vol. 3247: pp. 117-128.
[31]. K. Toyama, J. Krumm, B. Brumitt, et al. Wallflower: Principles and practice of background maintenance[C]. in Proceedings of the IEEE International Conferenceon Computer Vision. 1999, Vol. 1: pp. 255-261.
[32]. L. Li, I. Y.-H. Gu, M. K. H. Leung, et al. Adaptive background subtraction based on feedback from fuzzy classification[J]. Optical Engineering, 2004. Vol. 43(10): pp. 2381-2394.
[33]. D.Koller, J.Weber, T.Huang. Toward robust automatic traffic scene analysis in real-time[C]. in Proc. hit. Conf. Patten Recognition. 1994, Vol. : pp. 126-131.
[34]. R.Rad, M.Jamzad. Real time classification and tracking of multiple vehicles in highways[J]. Pattern Recognition Letters, 2005. Vol. 26: pp. 1597–1607.
[35]. A.Lipton, H.Fujiyoshi, R.Patil. Moving target classification and tracking from real-time video[C]. in IEEE Workshop on Application of Computer Vision. 1998, Vol. 8-14.
[36]. D. Makris, T. Ellis. Learning semantic scene models from observing activity in visual surveillance[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2005. Vol. 35(3): pp. 397-408.
[37]. O.Javed , M.Shah. Tracking and Object Classification for Automated Surveillance[C]. in Proc of ECCV. 2002, Vol. 5: pp. 343-357.
[38]. R.Cutler, L.Davis. Robust Real-time periodic motion detection analysis and application[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000. Vol. 22(8): pp. 781-796.
[39]. O. Chomat, J. L. Crowley. Recognizing motion using local appearance[C]. in Proceedings of the Sixth International Symposium on Intelligent Robotic Systems. 1998, Vol. : pp. 271-279.
[40]. D.Toth, T.Aach. Detection and Recognition of Moving Objects Using Statistical Motion Detection and Fourier Descriptors[C]. in International Conference on Image Analysis and Processing. 2003, Vol. 430-435.
[41]. E. Rivlin, M. Rudzsky, R. Goldenberg, et al. A real-time system for classification of moving objects[C]. in Proceedings - International Conference on Pattern Recognition. 2002, Vol. 16: pp. 688-691.
[42]. Y.Bogomolov, G.Dror, S.Lapchev. Classification of Moving Targets Based on Motion and Appearance[C]. in British Machine Vision Conference. 2003, Vol. : pp. 429-438.
[43]. D. Koller, K. Daniilidis, H. H. Nagel. Model-based object tracking in monocular image sequences of road traffic scenes[J]. International Journal of Computer Vision, 1993. Vol. 10(3): pp. 257–281.
[44]. B.Coifman, D.Beymer, J.Malik, et al. A real-time computer vision system for vehicle tracking and traffic surveillance[J]. Transport. Res.: Part C, 1998. Vol. 6(4): pp. 271–288.
[45]. N.Paragios, R.Deriche. Geodesic active regions: A new paradigm to deal with frame partition problems in computer vision[J]. Visual Commun. Image Represent., 2002. Vol. : pp. 249–268.
[46]. J.Kato, T. Watanabe, S.Joga. An HMM /MRF based stochastic framework for robust vehicle tracking[J]. IntelligentTransportation Systems, 2004. Vol. 5(3): pp. 142-154.
[47].岳昊,邵春福,赵熠.基于视频序列的行人多目标跟踪方法研究[J].交通运输系统工程与信息, 2007. Vol. 7(04): pp. 47-51.
[48]. W. Zhang, Q. M. J. Wu, X. Yang, et al. Multilevel framework to detect and handle vehicle occlusion[J]. IEEE Transactions on Intelligent Transportation Systems, 2008. Vol. 9(1): pp. 161-174.
[49]. V. J. D. Tsai. A comparative study on shadow compensation of color aerial images in invariant color models[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006. Vol. 44(6): pp. 1661-1671.
[50]. M.Khansari, H.R.Rabiee, M.Asadi. Occlusion Handling for Object Tracking in Crowded Video Scenes Based on the Undecimated Wavelet Features[C]. in IEEE/ACS International Conference on Computer Systems and Applications. 2007, Vol. : pp. 692-699.
[51]. D. Zhou, O. Bousquet, T. N. Lal, et al. Learning with local and global consistency [J]. Advances in Neural Information Processing Systems, 2004. Vol. 16: pp. 321-328.
[52]. T. Yang, S. Z. Li, Q. Pan, et al. Real-time multiple objects tracking with occlusion handling in dynamic scenes[C]. in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. 2005, Vol. I: pp. 970-975.
[53]. R.Cucchiara, C.Grana, G.Tardini, et al. Probabilistic people tracking for occlusion handling[C]. in Proceedings of the 17th International Conference on ICPR. 2004, Vol. 1: pp. 132-135.
[54].林培群,徐建闽.复杂交通场景中运动车辆的检测与轨迹跟踪[J].华南理工大学学报(自然科学版), 2008. Vol. 36(6): pp. 84-89.
[55]. W. Hu, D. Xie, T. Tan, et al. Learning activity patterns using fuzzy self-organizing neural network[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2004. Vol. 34(3): pp. 1618-1626.
[56]. D. Buzan, S. Sclaroff, G. Kollios. Extraction and clustering of motion trajectories in video[C]. in Proc. 17th Intl. Conf. on Pattern Recognition (ICPR). 2004, Vol. 2: pp. 521-524.
[57]. J. Lou, Q. Liu, T. Tan, et al. Semantic interpretation of object activities in a surveillance system[C]. in Proceedings - International Conference on Pattern Recognition. 2002, Vol. 16: pp. 777-780.
[58]. I. N. Junejo, O. Javed, M. Shah. Multi feature path modeling for video surveillance[C]. in Proc. 17th Intl. Conf. on Pattern Recognition (ICPR). 2004, Vol. 2: pp. 716-719.
[59].曲琳,周凡,陈耀武.基于Hausdorff距离的视觉监控轨迹分类算法[J].吉林大学学报(工学版), 2009. Vol. 39(06): pp. 1618-1629.
[60]. N. Johnson, D. Hogg. Learning the distribution of object trajectories for event recognition[J]. Image and Vision Computing, 1996. Vol. 14(8): pp. 609-615.
[61]. N. Sumpter, A. J. Bulpitt. Learning spatio-temporal patterns for predicting object behavior[J]. Image and Vision Computing, 2000. Vol. 18: pp. 697-704.
[62]. T. Kohonen. The self-organizing map[C]. in Proceedings of the IEEE. 1990, Vol. 78: pp. 1464-1480.
[63]. S. Atev, O. Masoud, N. Papanikolopoulos. Learning traffic patterns at intersections by spectral clustering of motion trajectories[C]. in IEEE International Conference on Intelligent Robots and Systems. 2006, Vol. : pp. 4851-4856.
[64]. F. I. Bashir, A. A. Khokhar, D. Schonfeld. Object trajectory-based activity classification and recognition using hidden Markov models[J]. IEEE Transactions on Image Processing, 2007. Vol. 16(7): pp. 1912-1919.
[65]. W. Hu, X. Xiao, Z. Fu, et al. A system for learning statistical motion patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006. Vol. 28(9): pp. 1450-1464.
[66]. W. Hu, D. Xie, Z. Fu, et al. Semantic-based surveillance video retrieval[J]. IEEE Transactions on Image Processing, 2007. Vol. 16(4): pp. 1168-1181.
[67]. D. Biliotti, G. Antonini, J. P. Thiran. Multi-layer hierarchical clustering of pedestrian trajectories for automatic counting of people in video sequences[C]. in Proceedings - IEEE Workshop on Motion and Video Computing. 2007, Vol. : pp. 50-57.
[68]. S. Kamijo, Y. Matsushita, K. Ikeuchi, et al. Traffic Monitoring and Accident Detection at Intersections[J]. IEEE Transactions on Intelligent Transportation Systems, 2000. Vol. 1(2): pp. 108-118.
[69]. D. Thirde, M. Borg, J. Ferryman, et al. A real-time scene understanding system for airport apron monitoring[C]. in Proceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06. 2006, Vol. 2006: pp. 26.
[70]. Zhang, K. Huang, T. Tan, et al. Trajectory series analysis based event rule induction for visual surveillance[C]. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007, Vol. 2007: pp.
[71]. A. Amer, E. Dubois, A. Mitiche. Rule-based real-time detection of context-independent events in video shots[J]. Real-Time Imaging, 2005. Vol. 11(3): pp. 244-256.
[72]. Y. Ivanov, C. Stauffer, A. Bobick, et al. Video surveillance of interactions[C]. in in Proc. 2nd Int. Workshop Visual Surveillance. 1999, Vol. : pp. 82-89.
[73]. A.F. Bobick, A. P. Pentland, T. Poggio, VSAM at the MIT Media Laboratory and CBCL: Learning and Understanding Action in Video Imagery PI Report 1998[R]. Proc. DARPA Image Understanding Workshop. 1998, pp. 85-91.
[74]. P. Kumar, S. Ranganath, H. Weimin, et al. Framework for real-time behaviorinterpretation from traffic video[J]. IEEE Transactions on Intelligent Transportation Systems, 2005. Vol. 6(1): pp. 43-53.
[75]. G. Medioni, I. Cohen, F. Bremond, et al. Event detection and analysis from video streams[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001. Vol. 23(8): pp. 873-889.
[76].曲昭伟.混合交通视频检测算法研究[D].长春:吉林大学博士论文, 2009.
[77].李志慧,张长海,曲昭伟, et al.交通流视频检测中背景初始化算法[J].吉林大学学报(工学版), 2008. Vol. 38 (01): pp. 148-151.
[78]. R. O.Duda, P. E.Hart, D. G.Stork著.李宏东,姚天翔等译.模式分类(第二版)[M],北京:机械工业出版社. 2005.
[79]. A. P. Dempster, N. M. L, D. B. Rubin. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society, 1997. Vol. 39(1): pp. 1-38.
[80].李志慧,张长海,曲昭伟, et al.交通流视频检测中背景模型与阴影检测算法[J].吉林大学学报(工学版), 2006. Vol. 36(06): pp. 993-997.
[81]. E. Salvador, A. Cavallaro, T. Ebrahimi. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004. Vol. 95(2): pp. 238-259.
[82]. E. Salvador, A. Cavallaro, T. Ebrahimi. Shadow identification and classification using invariant color models[C]. in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing. 2001, Vol. 3: pp. 1545-1548.
[83]. A. Prati, R. Cucchiara, I. Mikic, et al. Analysis and detection of shadows in video streams: A comparative evaluation[C]. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001, Vol. 2: pp. 571-576.
[84]. A. Prati, I. Mikic, M. M. Trivedi, et al. Detecting moving shadows: Algorithms and evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. Vol. 25(7): pp. 918-923.
[85]. A. J. Joshi, S. Atev, O. Masoud, et al. Moving shadow detection with low- And mid-level reasoning[C]. in Proceedings - IEEE International Conference on Robotics and Automation. 2007, Vol. : pp. 4827-4832.
[86]. A. J. Joshi, N. Papanikolopoulos. Learning of moving cast shadows for dynamic environments[C]. in Proceedings - IEEE International Conference on Robotics and Automation. 2008, Vol. : pp. 987-992.
[87]. R. Cucchiara, C. Grana, M. Piccardi, et al. Statistic and knowledge-based moving object detection in traffic scenes[C]. in IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. 2000, Vol. 27-32.
[88]. M. Kampel, H. Wildenauer, P. Blauensteiner, et al. Improved motion segmentation based on shadow detection[J]. Electronic Letters on Computer Vision and Image Analysis, 2007. Vol. 6(3): pp. 1-12.
[89]. Y. Wang. Real-time moving vehicle detection with cast shadow removal in video based on conditional random field[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009. Vol. 19(3): pp. 437-441.
[90]. Z. Liu, K. Huang, T. Tan, et al. Cast shadow removal combining local and global features[C]. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007, Vol. : pp. 1-8.
[91]. J.-B. Huang, C.-S. Chen. Moving cast shadow detection using Physics-based features[C]. in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2009, Vol. : pp. 2310-2317.
[92]. N. Martel-Brisson, A. Zaeearin. Moving cast shadow detection from a Gaussian mixture shadow model[C]. in Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005, Vol. II: pp. 643-648.
[93]. N. Martel-Brisson, A. Zaccarin. Learning and removing cast shadows through a multidistribution approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007. Vol. 29(7): pp. 1133-1146.
[94].张宏林. Visual C++数字图像模式识别技术及工程实践[M].北京,人民邮电出版社. 2003.
[95].韩东峰.图像分类识别中特征及模型的若干问题研究[D].长春:吉林大学博士论文, 2008.
[96]. H. Y. Hu, D. H. Wang, Z. H. Li, et al. Research on Recognition Algorithm of Moving Object[C]. in Transportation Research Board 87th Annual Meeting. 2008, Vol. 08-1437: pp. (DVD).
[97].郑南宁.计算机视觉与模式识别[M],北京:国防工业出版社. 1998.
[98].胡宏宇.混合交通中运动目标特征表达与分类算法研究[D].长春:吉林大学硕士论文, 2007.
[99]. V.Vapnik. The nature of statistical learning theory[M], New York:Springer-Verlag. 1995.
[100]. N.Cristianini, J.S.Taylor.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. 2005.
[101]. A.R.Webb著.王萍,杨培龙,罗颖昕译.统计模式识别(第二版)[M],北京:电子工业出版社. 2004.
[102]. C. W. Hsu, C. J. Lin. A Comparison of Methods for Multiclass Support Vector Machines[J]. IEEE Transactions on Neural Networks, 2002. Vol. 13(2): pp. 415-425.
[103].张晓龙,江川.计算机工程与应用[J].基于AUC的SVM多类分类方法的研究, 2007. Vol. 43(14): pp. 166-169.
[104]. R. E.Kalman. A New Approach to Linear Filtering and Prediction Problems[J]. Transactions of the ASME - Journal of Basic Engineering 1960. Vol. 82: pp. 35-45
[105]. R. E.Kalman, R. S.Bucy. New Results in Linear Filtering and Prediction Theory[J]. Transactions of the ASME - Journal of Basic Engineering, 1961. Vol. 83: pp.95-107.
[106].常好丽,史忠科.基于单目视觉的运动行人检测与跟踪方法[J].交通运输工程学报, 2006. Vol. 6(2): pp. 55-59.
[107]. P. Remagnino, S. A. Velastin, G. L. Foresti, et al. Novel concepts and challenges for the next generation of video surveillance systems[J]. Machine Vision and Applications, 2007. Vol. 18(3-4): pp. 135-137.
[108]. Z. Zhang, K. Huang, T. Tan. Comparison of similarity measures for trajectory clustering in outdoor surveillance scenes[C]. in Proceedings - International Conference on Pattern Recognition. 2006, Vol. 3: pp. 1135-1138.
[109]. B. T. Morris, M. M. Trivedi. Learning and classification of trajectories in dynamic scenes: A general framework for live video analysis[C]. in Proceedings - IEEE 5th International Conference on Advanced Video and Signal Based Surveillance, (AVSS 2008). 2008, Vol. 154-161.
[110]. Z. Fu, W. Hu, T. Tan. Similarity based vehicle trajectory clustering and anomaly detection[C]. in Proceedings - International Conference on Image Processing, ICIP. 2005, Vol. 2: pp. 602-605.
[111].袁和金,张艳宁,周涛, et al.基于归一化编辑距离和谱聚类的轨迹模式学习方法[J].计算机辅助设计与图形学学报, 2008. Vol. 06: pp. 753-758.
[112]. F. I. Bashir, A. A. Khokhar, D. Schonfeld. Segmented trajectory based indexing and retrieval of video data[C]. in IEEE International Conference on Image Processing. 2003, Vol. 2: pp. 623-626.
[113]. E. J. Keogh, M. J. Pazzani. Scaling up dynamic time warping for datamining applications[C]. in Proceeding of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2000, Vol. 285-289.
[114]. M. Vlachos, G. Kollios, D. Gunopulos. Discovering similar multidimensional trajectories[C]. in Proceedings - International Conference on Data Engineering. 2002, Vol. 673-684.
[115]. M. P. Dubuisson, A. K. Jain. A Modified Hausdorff distance for Object Matching[C]. in Proc. of ICPR. 1994, Vol.
[116].高琰,谷士文,唐琎, et al.机器学习中谱聚类方法的研究[J].计算机科学, 2007(02): pp. 201-203.
[117]. F. Chung. Spectral Graph Theory[M], American Mathematical Society. 1997.
[118]. M. Fiedler. Algebraic connectivity of graphs[J]. Math.J., 1973(23): pp. 298-305.
[119]. J. Shi, J. Malik. Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. Vol. 22(8): pp. 888-905.
[120].蔡晓妍,戴冠中,杨黎斌.谱聚类算法综述[J].计算机科学, 2008(07): pp. 14-18.
[121].胡宏宇,李志慧,曲昭伟, et al.基于上下文的交通事件表达与识别[J].吉林大学学报(工学版), 2009,. Vol. 39(S2): pp. 158-162.
[122].孙瑜,李志平.上下文在人工智能中的应用[J].计算机工程, 2004. Vol. 30(3):pp. 141-142.
[123]. T. Strat. Employing Contextual Information in Computer Vision[C]. in Proc. DARPA Image Understanding Workshop. 1993, Vol. 1993: pp. 217-229.
[124]. H. H. Nagel. From Image Sequences Towards Conceptual Descriptions[J]. Image and Vision Computing, 1988. Vol. 6(2): pp. 59-74.
[125]. F. Bre?mond, M. Thonnat., Issues of Representing Context Illustrated by Video-Surveillance Applications[R]. Int'l J. Human-Computer Studies. 1998.