智能视频监控系统目标跟踪与分类算法研究
|
摘要
随着视频监控需求的迅速增长、监控规模的日益扩大，人工监视已远远不能满足监控要求，视频监控系统的“智能化”变得越来越迫切。研究高实时性高准确度的智能视觉分析算法、多目视觉数据融合以及最优化问题是智能视频监控系统研究的关键。本文针对智能视频监控系统中的运动目标跟踪与分类问题——从运动目标分割、跟踪和分类，到基于多目视觉数据融合的目标连续跟踪、跟踪优化分配以及目标分类／跟踪互协作，进行了深入研究，并设计和实现了基于嵌入式CPU和DSP相互协作的智能摄像机原型系统。论文的主要研究内容概述如下：
1．基于区域分割的复杂背景建模算法研究
针对复杂监控场景，为了消除动态背景物、光照变化所产生的干扰以及无关的阴影区域，提出了基于区域分割的复杂背景建模算法。通过在色度和亮度空间对监控背景进行有效的区域分类，在变化小的稳定区域采用简单快速的自适应单高斯模型(Adaptive Single Gaussian Model)，在变化大的动态区域采用计算复杂而有效的非参数化模型(Nonparametric Model)。该算法采用通用合并方法(GAS)聚类填充动态区域中的小空隙，并在边界处向外适当扩充像素，以提高区域分割对动态环境的适应性。在动态区域非参数化背景建模的训练阶段，采用双阀值顺序算法方案(TTSAS)把所有的背景采样值聚类成几个高斯分布类，以加速新采样值的核密度计算；
2．基于模型动态切换的运动目标实时跟踪算法研究
针对拥挤的监控场景，为了实现遮挡状态下目标跟踪的稳定性，提出基于模型动态切换的运动目标实时跟踪算法。通过对目标遮挡状态的有效判定，对未遮挡的单运动目标采用基于区域跟踪的简单快速模型，对相互遮挡的复合运动目标采用基于窄基线SIFT特征匹配的跟踪模型。由于被跟踪目标在相邻图像帧之间尺度和外形变化很小以及基于目标位置预测出的运动范围有限，SIFT特征匹配模型实现了快速的窄基线小范围特征匹配，达到了遮挡状态下目标跟踪的稳定性；
3．基于多目视觉的目标连续跟踪及跟踪优化研究
针对广域监控场景，提出一种基于多目视觉的目标连续跟踪及跟踪优化方法。利用摄像机背景图像之间的SIFT特征匹配自动检测摄像机之间的重叠视域，并根据相匹配的SIFT关键点计算重叠视域之间单应性变换矩阵的系数，SIFT特征匹配和单应性变换使跟踪系统达到了稳定的连续跟踪。为了在目标跟踪过程中获得更好的跟踪效果，该方法通过基于多目视觉的跟踪优化算法对目标的跟踪优先级和目标在各个摄像机中的遮挡状态及其分割图像大小进行数据加权融合，优先分配高优先级目标给具有最佳权值的摄像机进行跟踪，并动态平衡各个摄像机的计算资源与跟踪负载。该方法不需要具备摄像机校正和场景建模条件，适用范围较广；
4．运动目标分类算法研究
针对交通监控场景特点，提出基于分区归一化加权特征的目标分类算法。通过提取简单有效的运动特征和外形特征，并对交通监控场景中不同交通方向的道路区域和不同的场景位置进行分区，以提高目标特征的可区分性。在分区后应用AdaBoost方法评估各个特征的相对重要性，赋给每个特征一个归一化权值，最后生成一个线形分类器。由于遮挡状态会严重影响目标分类算法的性能，通过基于重叠摄像机数据融合的目标分类与跟踪互协作改善了拥塞场景中目标分类算法的正确率。借助于重叠摄像机之间不同的视角方向，利用摄像机之间的视点对应和数据融合决定最优的分类与跟踪结果，提高了遮挡状态下运动目标分类的准确度和目标跟踪的稳定性。
在以上研究基础之上，本论文最后针对智能视频监控系统的核心功能单元——嵌入式智能摄像机系统，设计一种新型的实时嵌入式智能摄像机系统，该方案基于嵌入式CPU和DSP协作的硬件体系结构，实现智能视觉分析和网络交互模块并行处理的软件系统框架，提供了一个较好的智能摄像机原型设计实例。
With the rapid growth of video surveillance requirements and the extension ofsurveillance area day by day,manual monitoring can't meet the needs of surveillanceand the“intelligentization”of video surveillance systems gets more and more urgent.Study on highly real-time,precise and intelligent video analysis algorithms as well asmulti-camera data fusion and optimization problems are the key of intelligent videosurveillance systems.The relative techniques of object tracking and classification inintelligent video surveillance system are studied in the thesis,which includes motiondetection,object classification and tracking as well as the object continuous tracking,tracking optimization and object classification/tracking cooperation based onmulti-camera data fusion.The thesis implements an intelligent camera systemprototype based on the cooperation between embedded CPU and DSP.The maincontents are summarized as follows:
1.Background modeling algorithm based on region segmentation
Aiming at complex surveillance scenes,a background modeling algorithm basedon region segmentation is proposed.The surveillance background is effectivelyclassified in the chromaticity and lightness space.The adaptive single Gaussian modelis used in the stable region with gradual changes and the nonparametric model is usedin the dynamic region with jumping changes.A Generalized Agglomerative Scheme isused to merge the pixels in the Variable Region and fill the small interspaces.ATwo-Threshold Sequential Algorithmic Scheme is used to group the backgroundsamples of the Variable Region into distinct Gaussian distributions.The kernel densitycomputation complexity is largely reduced by arranging the computation order of thesegroups according to their proximity in mean value to the current pixel sample beingestimated;
2.Moving object tracking based on dynamically switching models
Aiming at congested surveillance scenes,a moving object tracking method basedon dynamically switching models is proposed.After effectively estimating theocclusion state of moving objects,a simple region-based tracking model is deployedfor non-occluded moving objects and a narrow-scale image matching model based onSIFT(Scale Invariant Feature Transform) features is deployed for occluded movingobjects.Because the tracked targets only have very small scale changes and limitedrange on target region position prediction between neighboring image frames,theimage matching model based on SIFT features can also implement rapid SIFT featuresmatching and robust target tracking in complex occlusion scenes;
3.Tracking target continuously and optimization based on multiple cameras
Aiming at wide area video surveillance scenes,a method to track targetcontinuously and optimization based on multiple cameras is proposed.The centralserver detects the overlapping area between the field of views (FOV) of the cameras byfeatures matching of the background images through Scale Invariant FeatureTransform(SIFT).Viewpoint correspondence between the overlapping cameras is thenestablished by using the ground plane homography transformation matrix throughSIFT keypoints matched between the background images.SIFT feature matching andhomography transformation achieve stable continuous target tracking.In order toeffectively track moving targets among multiple cameras,the method prioritizes thefusion process based on assigned priority,the occlusion state and image segmentationsize of the moving target by use of a tracking optimization algorithm based onmulti-camera data fusion is proposed.This optimization algorithm preferably allocatethe optimal camera to track moving targets with high priority.The algorithm alsodynamically balances the tracking load of each camera.The method doesn't needcamera calibration and environment modeling and its application area is very wide.
4.Research on object classification algorithms
Aiming at traffic surveillance scenes,an object classification algorithm based onnormalized weight features of the partitions is proposed.The classification algorithmextracts effective motion-features and shape-features,and the discriminability of theobject features is improved by partitioning the surveillance secens according todifferent traffic road boundaries and scene locations.After the partition,AdaBoostmethod is utilized to evaluate the relative importance of each feature and assigns anormalized weight to each feature.Because the occluded state can reduce the accuracyof the classification algorithm,the classification accuracy in congested scenes isimproved by an improved object classification and tracking method based on multipleoverlapping cameras cooperation is proposed.The optimized classification andtracking results are determined by the viewpoint correspondence and data fusionamong the overlapping cameras.By use of the different view directions of theoverlapping cameras,object classification accuracy and tracking stabilization incomplex occlusion scenes are improved.
Based on the above research,a novel and high-powered intelligent camera systemis designed aiming at the kernel unit of intelligent video surveillance systems
embedded intelligent camera.The scheme is based on the cooperative hardwarearchitecture between embedded CPU and DSP,and implements parallel softwareframework of intelligent video analysis and network interaction module.The systemprovides a prototype design of intelligent camera.
1．基于区域分割的复杂背景建模算法研究
针对复杂监控场景，为了消除动态背景物、光照变化所产生的干扰以及无关的阴影区域，提出了基于区域分割的复杂背景建模算法。通过在色度和亮度空间对监控背景进行有效的区域分类，在变化小的稳定区域采用简单快速的自适应单高斯模型(Adaptive Single Gaussian Model)，在变化大的动态区域采用计算复杂而有效的非参数化模型(Nonparametric Model)。该算法采用通用合并方法(GAS)聚类填充动态区域中的小空隙，并在边界处向外适当扩充像素，以提高区域分割对动态环境的适应性。在动态区域非参数化背景建模的训练阶段，采用双阀值顺序算法方案(TTSAS)把所有的背景采样值聚类成几个高斯分布类，以加速新采样值的核密度计算；
2．基于模型动态切换的运动目标实时跟踪算法研究
针对拥挤的监控场景，为了实现遮挡状态下目标跟踪的稳定性，提出基于模型动态切换的运动目标实时跟踪算法。通过对目标遮挡状态的有效判定，对未遮挡的单运动目标采用基于区域跟踪的简单快速模型，对相互遮挡的复合运动目标采用基于窄基线SIFT特征匹配的跟踪模型。由于被跟踪目标在相邻图像帧之间尺度和外形变化很小以及基于目标位置预测出的运动范围有限，SIFT特征匹配模型实现了快速的窄基线小范围特征匹配，达到了遮挡状态下目标跟踪的稳定性；
3．基于多目视觉的目标连续跟踪及跟踪优化研究
针对广域监控场景，提出一种基于多目视觉的目标连续跟踪及跟踪优化方法。利用摄像机背景图像之间的SIFT特征匹配自动检测摄像机之间的重叠视域，并根据相匹配的SIFT关键点计算重叠视域之间单应性变换矩阵的系数，SIFT特征匹配和单应性变换使跟踪系统达到了稳定的连续跟踪。为了在目标跟踪过程中获得更好的跟踪效果，该方法通过基于多目视觉的跟踪优化算法对目标的跟踪优先级和目标在各个摄像机中的遮挡状态及其分割图像大小进行数据加权融合，优先分配高优先级目标给具有最佳权值的摄像机进行跟踪，并动态平衡各个摄像机的计算资源与跟踪负载。该方法不需要具备摄像机校正和场景建模条件，适用范围较广；
4．运动目标分类算法研究
针对交通监控场景特点，提出基于分区归一化加权特征的目标分类算法。通过提取简单有效的运动特征和外形特征，并对交通监控场景中不同交通方向的道路区域和不同的场景位置进行分区，以提高目标特征的可区分性。在分区后应用AdaBoost方法评估各个特征的相对重要性，赋给每个特征一个归一化权值，最后生成一个线形分类器。由于遮挡状态会严重影响目标分类算法的性能，通过基于重叠摄像机数据融合的目标分类与跟踪互协作改善了拥塞场景中目标分类算法的正确率。借助于重叠摄像机之间不同的视角方向，利用摄像机之间的视点对应和数据融合决定最优的分类与跟踪结果，提高了遮挡状态下运动目标分类的准确度和目标跟踪的稳定性。
在以上研究基础之上，本论文最后针对智能视频监控系统的核心功能单元——嵌入式智能摄像机系统，设计一种新型的实时嵌入式智能摄像机系统，该方案基于嵌入式CPU和DSP协作的硬件体系结构，实现智能视觉分析和网络交互模块并行处理的软件系统框架，提供了一个较好的智能摄像机原型设计实例。
With the rapid growth of video surveillance requirements and the extension ofsurveillance area day by day,manual monitoring can't meet the needs of surveillanceand the“intelligentization”of video surveillance systems gets more and more urgent.Study on highly real-time,precise and intelligent video analysis algorithms as well asmulti-camera data fusion and optimization problems are the key of intelligent videosurveillance systems.The relative techniques of object tracking and classification inintelligent video surveillance system are studied in the thesis,which includes motiondetection,object classification and tracking as well as the object continuous tracking,tracking optimization and object classification/tracking cooperation based onmulti-camera data fusion.The thesis implements an intelligent camera systemprototype based on the cooperation between embedded CPU and DSP.The maincontents are summarized as follows:
1.Background modeling algorithm based on region segmentation
Aiming at complex surveillance scenes,a background modeling algorithm basedon region segmentation is proposed.The surveillance background is effectivelyclassified in the chromaticity and lightness space.The adaptive single Gaussian modelis used in the stable region with gradual changes and the nonparametric model is usedin the dynamic region with jumping changes.A Generalized Agglomerative Scheme isused to merge the pixels in the Variable Region and fill the small interspaces.ATwo-Threshold Sequential Algorithmic Scheme is used to group the backgroundsamples of the Variable Region into distinct Gaussian distributions.The kernel densitycomputation complexity is largely reduced by arranging the computation order of thesegroups according to their proximity in mean value to the current pixel sample beingestimated;
2.Moving object tracking based on dynamically switching models
Aiming at congested surveillance scenes,a moving object tracking method basedon dynamically switching models is proposed.After effectively estimating theocclusion state of moving objects,a simple region-based tracking model is deployedfor non-occluded moving objects and a narrow-scale image matching model based onSIFT(Scale Invariant Feature Transform) features is deployed for occluded movingobjects.Because the tracked targets only have very small scale changes and limitedrange on target region position prediction between neighboring image frames,theimage matching model based on SIFT features can also implement rapid SIFT featuresmatching and robust target tracking in complex occlusion scenes;
3.Tracking target continuously and optimization based on multiple cameras
Aiming at wide area video surveillance scenes,a method to track targetcontinuously and optimization based on multiple cameras is proposed.The centralserver detects the overlapping area between the field of views (FOV) of the cameras byfeatures matching of the background images through Scale Invariant FeatureTransform(SIFT).Viewpoint correspondence between the overlapping cameras is thenestablished by using the ground plane homography transformation matrix throughSIFT keypoints matched between the background images.SIFT feature matching andhomography transformation achieve stable continuous target tracking.In order toeffectively track moving targets among multiple cameras,the method prioritizes thefusion process based on assigned priority,the occlusion state and image segmentationsize of the moving target by use of a tracking optimization algorithm based onmulti-camera data fusion is proposed.This optimization algorithm preferably allocatethe optimal camera to track moving targets with high priority.The algorithm alsodynamically balances the tracking load of each camera.The method doesn't needcamera calibration and environment modeling and its application area is very wide.
4.Research on object classification algorithms
Aiming at traffic surveillance scenes,an object classification algorithm based onnormalized weight features of the partitions is proposed.The classification algorithmextracts effective motion-features and shape-features,and the discriminability of theobject features is improved by partitioning the surveillance secens according todifferent traffic road boundaries and scene locations.After the partition,AdaBoostmethod is utilized to evaluate the relative importance of each feature and assigns anormalized weight to each feature.Because the occluded state can reduce the accuracyof the classification algorithm,the classification accuracy in congested scenes isimproved by an improved object classification and tracking method based on multipleoverlapping cameras cooperation is proposed.The optimized classification andtracking results are determined by the viewpoint correspondence and data fusionamong the overlapping cameras.By use of the different view directions of theoverlapping cameras,object classification accuracy and tracking stabilization incomplex occlusion scenes are improved.
Based on the above research,a novel and high-powered intelligent camera systemis designed aiming at the kernel unit of intelligent video surveillance systems
embedded intelligent camera.The scheme is based on the cooperative hardwarearchitecture between embedded CPU and DSP,and implements parallel softwareframework of intelligent video analysis and network interaction module.The systemprovides a prototype design of intelligent camera.
引文
无编改内容
[14] HU Weiming, TAN Tieniu, WANG Liang, et al. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transaction on Systems, Man, and Cybernetics-Part C:Applications and Reviews, 2004,34(3):334-352.
[15] S. J. Mc, S. Jabri, Z. Duric, A. Rosenfeld and H. Wechsler. Tracking Groups of People[J]. Computer Vision and Image Understanding, 2000,80:42-56.
[16] A. Elgammal, D. Harwood and L. Davis. Non-parametric Model for Background[C]. In Proceedings of the 6th European Conference on Computer Vision-Part II, London, UK, 2000.
[17] S. Theodoridis and K. Koutroumbas. Pattern Recognition, New York: Academic, 2006.
[18] M. Tsuchiya and H. Fujiyoshi. Evaluating Feature Importance for Object Classification in Visual Surveillance[C]. In Proceedings of the 18th IEEE International Conference on Pattern Recognition, 2006:978-981.
[19] Lowe David. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[20] Criminisi A, Reid I, Zisserman A. A plane measuring device[J]. Image and Vision Computing, 1999, 17(8): 625-634.
[21] Terrance E.Boult, et al. A Decande of Networked Intelligent Video Surveillance[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[22] 中国安防杂志(AS CHINA),第2006年4期.
[23] M. Valera and S. Velastin. Intelligent distributed surveillance systems: a review[j]. In Proceedings of IEEE on Vision, Image and Signal Processing, 2005, 152(2): 192-204.
[24] Rita Cucchiara. Multimedia surveillance systems[C]. In Proceedings of the third ACM international workshop on Video surveillance & sensor networks, Singapore, 2005.
[25] A Amer, C Regazzoni. Introduction to the special issue on video object processing for surveillance applications[J]. Real-Time Imaging, 2005.
[26] N. Friedman and S. Russell. Image segmentation in video sequences: a probabilistic approach[C]. In Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence, 1997:1-3.
[27] Nguyen, N.T., Venkatesh, S., West, G, and Bui, H.H.. Multiple camera coordination in a surveillance system[J]. Acta Automatica Sinica, 2003,29(3):408-421.
[28] Jaynes, C. Multi-view calibration from planar motion for video surveillance[C]. The 2nd IEEE International Workshop on Visual Surveillance, Colorado, 1999:59-67.
[29] Y.L.Tian and A.Hampapur. Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance[C]. In Proceedings of IEEE Computer Society Workshop on Motion and Video Computing, 2005.
[30] Shotton J,Blake A,Cipolla R. Contour-Based Learning for Object Detectio[C]. In Proceedings of the Tenth IEEE International Conference on Computer Vision, 2005, 1:503 -510.
[31] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland. Pfinder: Real-Time Tracking of the Human Body[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19:780-785.
[32] C. Stauffer and W. E. L. Grimson. Adaptive background mixture models for real-time tracking[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, 1999:246-252.
[33] A. Elgammal, R. Duraiswami, D. Harwood and L. Davis. Background and Foreground Modeling Using Nonparametric Kernel Density for Visual Surveillance[J]. In Proceedings of IEEE, 2002, 90(7)1151 -1163.
[34] P.KaewTraKulPong and R.Bowden. An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection[C]. In Proceedings of European Workshop on Advanced Video-based Surveillance Systems, Kingston, UK, 2001.
[35] S. M. Bhandarkar and X. Luo. Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, 2005.
[36] Y. Sheikh and M. Shah. Bayesian Object Detection in Dynamic Scenes[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, 2005.
[37] X. Luo, S. M. Bhandarkar, W. Hua and H. Gu. Nonparametric Background Modeling Using the CONDENSATION Algorithm[C]. In Proceedings of IEEE Conference on Video and Signal Based Surveillance, Washington, DC, USA ,2006.
[38] A. J. Lipton, H. Fujiyoshi, and R. S. Patil. Moving target classification and tracking from real-time video[C]. In Proceedings of IEEE Workshop Applications of Computer Vision, 1998:8-14.
[39] D. Meyer, J. Denzler, and H. Niemann. Model based extraction of articulated objects in image sequences for gait analysis[C]. In Proceedings of IEEE International Conference on Image Processing, 1998:78-81.
[40] D. Meyer, J. Psl, and H. Niemann. Gait classification with HMM's for trajectories of body parts extracted by mixture densities[C]. In Proceedings of British Machine Vision Conference, 1998:459-468.
[41] J. Barron, D. Fleet, and S. Beauchemin. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12(l):42-77.
[42] Y. Kuno, T. Watanabe, Y. Shimosakoda, and S. Nakagawa. Automated detection of human for visual surveillance system[C], In Proceedings of International Conference on Pattern Recognition, 1996:865-869.
[43] I. Haritaoglu, D. Harwood, and L. S. Davis. W~4: Real-time surveillance of people and their activities[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:809-830.
[44] Ehud Rivlin, Michael Rudzsky, Roman Goldenberg, et al. A real-time system for classification of moving objects[C]. In Proceedings of the 16th International Conference on Pattern Recognition-ICPR'02, Quebec, 2002:30688-30691.
[45] Viola, P., Jones, M., Snow, D.. Detecting Pedestrians Using Patterns of Motion and Appearance. Mitsubishi Electric Research Lab Technical Report. TR-2003-90(2003).
[46] R. Cutler and L. S. Davis. Robust real-time periodic motion detection, analysis, and applications[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:781-796.
[47] A. J. Lipton. Local application of optic flow to analyze rigid versus nonrigid motion[C]. In Proceedings of International Conference on Computer Vision Workshop Frame-Rate Vision, Corfu, Greece, 1999.
[48] O. Javed and M. Shah. Tracking and Object Classification for Automated Surveillance[C]. In Proceedings of the Seventh European Conference on Computer Vision, 2002, Part Ⅳ:343-357.
[49] C. Stauffer. Automatic hierarchical classification using time-base co-occurrences[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1999, 2:335-339.
[50] SC, Kamath C. Robust techniques for background subtraction in urban traffic video[C]. In Proceedings of SPIE Electronic Imaging:Visual Communications and Image Processing, San Jose, California, USA, 2004, 1:881-892.
[51] Robert T., Collins, et al. A system for video Surveillance and Monitoring. Technical Report CMU-RI-TR-00-12, Carnegie Mellon University 2000.
[52] R.-E. Fan, P.-H. Chen, and C.-J. Lin. Working set selection using second order information for training SVM[J]. Journal of Machine Learning Research 6, 2005.
[53] Julier S, Fleet D, El-Maraghi T. A new extension of the Kalman filter to nonlinear system[C]. In Proceedings of SPIE, 1997:182-193.
[54] Li P, Zhang T, Ma B. Unscented Kalman filter for visual curve tracking. Image and Vision Computing, 2004, 22(2):157-164.
[55] Chen Y, Rui Y. Real-time speaker tracking using particle filter sensor fusion[J]. In Proceedings of the IEEE, 2004, 92(3):485-494.
[56] Wu Y ,Huang T. Robust visual tracking by integrating multiple cues based on co-inference learning[J]. International Journal of Computer Vision, 2004, 58(1):55-71.
[57] Perez P, Vermask J, Blake A. Data fusion for visual tracking with particles[J]. In Proceedings of the IEEE, 2004, 92(3):495-513.
[58] Zhou S K, Chellappa R, Moghaddan B. Visual tracking and recognition using appearance-adaptive models in particle filters[J]. IEEE Transactions on Image Processing, 2004, 13(11):1491-1506.
[59] Hue C, Cader J, Perez P. Tracking multiple objects with particle filtering[J]. IEEE Transactions on Aerospace and Electronic Systems, 2002, 38(3):791-812.
[60] Spengler M, Schiele B. Towards robust multi-cue integration for visual tracking[J]. Machine Vision and Applications, 2003, 14(l):50-58.
[61] Merwe R,Doucet A,Freitas N,Wan E. The unscented particle filter, technical report CUED/F-INFENG/TR380, Engineering Department, Cambridge University, August, 2000.
[62] Rabiner L. A tutorial on hidden Markov models and selected applications in speech recognition[J]. In Proceedings of the IEEE, 1989,77(2):257-285.
[63] Isard M,Blake A. CONDENSATION-Conditional density propagation for visual tracking[J]. International Journal of Computer Vision, 1998, 29(1):52-81.
[64] K. Karmann and A. Brandt. Moving object recognition using an adaptive background memory[C]. In Proceedings of Time-Varying Image Processing and Moving Object Recognition,, 1990,2.
[65] M. Kilger. A shadow handler in a video-based real-time traffic monitoring system. [C] In Proceedings of IEEE Workshop Applications of Computer Vision, Palm Springs, CA, 1992:11-18.
[66] JPL. Traffic surveillance and detection technology development. Sensor Development Final Report, Jet Propulsion Laboratory Publication no.97-10, 1997.
[67] J. Malik, S. Russell, J. Weber, T. Huang, et. al. A machine vision based surveillance system for Californaia roads. Univ. of California, PATH project MOU-83 Final Report, November, 1994.
[68] I. A. Karaulova, P. M. Hall, and A. D. Marshall. A hierarchical model of dynamics for tracking people with a single video camera[C]. In Proceedings of British Machine Vision Conference, 2000:262-352.
[69] S. Ju, M. Black, and Y. Yaccob. Cardboard people: a parameterized model of articulated image motion[C]. In Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, 1996:38-44.
[70] S. A. Niyogi and E. H. Adelson. Analyzing and recognizing walking figures in XYT[C]. In Proceeings of IEEE Conference on Computer Vision and Pattern Recognition, 1994:469-474.
[71] K. Rohr. Toward model-based recognition of human movements in image sequences[J]. CVGIP: Image Understanding, 1994,59(1):94-115.
[72] S. Wachter and H.-H. Nagel. Tracking persons in monocular image sequences[J]. Computer Vision and Image Understanding, 1999, 74(3): 174-192.
[73] W. F. Gardner and D. T. Lawton. Interactive model-based vehicle tracking[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996, 18:1115-1121.
[74] T. N. Tan, G D. Sullivan, and K. D. Baker. Model-based localization and recognition of road vehides[J]. International Journal of Computer Vision, 1998, 29(l):22-25.
[75] D. Koller, K. Daniilidis, and H.-H. Nagel. Model-based object tracking in monocular image sequences of road traffic scenes[J]. International Journal of Computer Vision, 1993, 10(3):257-281.
[76] H. Kollnig and H.-H. Nagel. 3D pose estimation by directly matching polyhedral models to gray value gradient[J]. International Journal of Computer Vision, 1997,23(3):283-302.
[77] M. Haag and H.-H. Nagel. Combination of edge element and optical flow estimates for 3D-model-based vehicle tracking in traffic image sequences[J]. International Journal of Computer Vision, 1999,35(3):295-319.
[78] H. Yang, J. G Lou, H. Z. Sun, W. M. Hu, and T. N. Tan. Efficient and robust vehicle localization[C]. In Proceedings of ??IEEE International Conference on Image Processing, 2001:355-358.
[79] J. G Lou, H. Yang, W. M. Hu, and T. N. Tan. Visual vehicle tracking using an improved EKF[C]. In Proceedings of Asian Conference on Computer Vision, 2002:296-301.
[80] A. Baumberg and D. C. Hogg. Learning deformable models for tracking the human body[C]. In Proceedings of Motion-Based Recognition, Kluwer, 1996:39-60.
[81] A. Mohan, C. Papageorgiou, and T. Poggio. Example-based object detection in images by components[J]. IEEE Transaction on Pattern Recognition and Machine Intelligence, 2001, 23:349-361.
[82] A. Galata, N. Johnson, and D. Hogg. Learning variable-length Markov models of behavior[J]. Computer Vision and Image Understanding, 2001, 81(3):398-413.
[83] Y. Wu and T. S. Huang. A co-inference approach to robust visual tracking[C]. In Proceedings of International Conference on Computer Vision, 2001, II: 26-33.
[84] N. Paragios and R. Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000,12:266-280.
[85] N. Peterfreund. Robust tracking of position and velocity with Kalman snakes[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:564-569.
[86] M. Isard and A. Blake. Contour tracking by stochastic propagation of conditional density[C]. In Proceedings of European Conference on Computer Vision, 1996:343-356.
[87] R. Polana and R. Nelson. Low level recognition of human motion[C]. In Proceedings of IEEE Workshop Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994:77-82.
[88] Segen J, Pingali S. A camera-based system for tracking people in real time[C]. In Proceedings of International Conference on Pattern Recognition, 1996:63-67.
[89] D.-S. Jang and H.-I. Choi. Active models for tracking moving objects[J]. Pattern Recognition, 2000,33(7): 135-1146.
[90] Kaneko, T. and Hori, O. Feature selection for reliable tracking using template matching[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2003:796-802.
[91] P. Mitra, C. A. Murthy, and S. K. Pal, Unsupervised feature selection using feature similarity[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(3):301-312.
[92] Xu, M., Lowey, L., and Orwell, J.. Architecture and algorithms for tracking football players with multiple cameras[C]. In Proceedings of IEEE Workshop on Intelligent Distributed Surveillance Systems, London, 2004: 51-56.
[93] Paulidis, 1., and Morellas, V.. Two examples of indoor and outdoor surveillance systems[C]. In Proceedings of Video-based Surveillance Systems, Boston, 2002:39-51.
[94] Micheloni, C, Foresti, GL., and Snidaro, L.. A co-operative multicamera system for video-surveillance of parking lots[C]. Intelligent Distributed Surveillance Systems Symp. by the IEEE, London, 2003:21-24.
[95] Yuan, X., Sun, Z., Varol, Y., and Bebis, G A distributed visual surveillance system[C]. IEEE Conference on Advanced Video and Signal based Surveillance, Florida, 2003:199-205.
[96] Qureshi and D. Terzopoulos. Towards intelligent camera networks: A virtual vision approach[C]. In Proceedings of The Second Joint IEEE International Workshop on Visual Surveillanceand Performance Evaluation of Tracking and Surveillance, Beijing, 2005.
[97] 马华东,陶丹.多媒体传感器网络及其研究进展.软件学报,2006, 17(9):2013-2028.
[98] Q. Cai and J. K. Aggarwal. Tracking human motion using multiple cameras[C]. In Proceedings of International Conference on Pattern Recognition, Vienna, Austria, 1996: 68-72.
[99] J. Krumm, S. Harris, B. Meyers, B. Brumitt, M. Hale, and S. Shafer. Multi-camera multi-person tracking for EasyLiving[C]. In Proceedings of IEEE International Workshop Visual Surveillance, Dublin, Ireland, July 2000:3-10.
[100] O. Javed, S. Khan, Z. Rasheed, and M. Shah. Camera handoff: tracking in multiple uncalibrated stationary cameras[C]. In Proceedings of IEEE Workshop Human Motion (HUMO'00), Austin, TX, 2000:113-118.
[101] Q. Cai and J. K. Aggarwal. Tracking human motion in structured environments using a distributed-camera system[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999,21(11):1241-1247.
[102] Snidaro L, Niu R, Varshney P K, et al. Automatic camera selection and fusion for outdoor surveillance under changing weather conditions[C]. In Proceedings of IEEE Conference on Advanced Video and Signal Based Surveillance, 2003:364-369.
[103] Nummiaro K, Koller-meier E, Svoboda T, et al. Color-based object tracking in multi-Camera environments[C]. In Proceedings of the 25th Pattern Recognition Symposium, 2003:591-599.
[104] Lim S N, Davis L S, Elgammal A. A scalable image-based multi-camera visual surveillance system[C]. In proceedings of IEEE Conference on Advanced Video and Signal Based Surveillance, 2003:205-212.
[105] Henriksson D, Olsson T. Maximizing the use of computer resources in multi-camera feedback control[C]. In Proceedings of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2004:360-367.
[106] Nguyen N T, Venkatesh S, West G, et al. Multiple camera coordination in a surveillance system[J]. Acta Automatica Sinica, 2003,29(3):408-422.
[107] A. Utsumi, H. Mori, J. Ohya, and M. Yachida. Multiple-view-based tracking of multiple humans[C]. In Proceedings of International Conference on Pattern Recognition, 1998:197-601.
[108] S. L. Dockstader and A. M. Tekalp. Multiple camera tracking of interacting and occluded human motion[C]. In Proceedings of IEEE, 2001, 89:1441-1455.
[109] H. Tsutsui, J. Miura, and Y. Shirai. Optical flow-based person tracking by multiple cameras[C]. In Proceedings of IEEE Conference on Multisensor Fusion and Integration in Intelligent Systems, 2001:91-96.
[110] A. Mittal and L. S. Davis. M2 tracker: a multi-view approach to segmenting and tracking people in a cluttered scene[C]. In Proceedings of European Conference on Computer Vision, 2002, 1:18-36.
[1ll] Dainis A, Juberts M. Accurate remote measurement of robot trajectory motion[C]. In Proceedings of International Conference on Robotics and Automation. 1985:92-99.
[112] Ganapathy S. Decomposition of transformation matrices for robot vision[C]. In Proceedings of Internationa] Conference on Robotics and Automation, 1984:130-139
[113] Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation[J]. IEEE Transaction on PAMI, 1992, 14(10):965-980.
[114] Wei G, Ma S. Complete two-plane camera calibration and experimental comparisons[C]. In Proceedings of ICC V'93:43 9-446.
[115] Maybank S J, Faugeras O D. A theory of self-calibration of a moving camera[J]. International Journal of Computer Vision, 1992,8(2): 123-151.
[116] Faugeras O D, Maybank S. Motion from point matches:multiplicity of solutions[J]. International Journal of Computer Vision, 1990,4:225-246.
[117] Ma S. A self-calibration technique for active vision system[J]. IEEE Transaction on Robotics and Automation, 1996, 12:114-120.
[118] Hartley RI. A Linear method for reconstruction from lines and points[C]. In Proceedings of ICCV 95:882-887.
[119] I. Pavlidis, V. Morellas, P. Tsiamyrtzis, et. al. Urban surveillance system: from the laboratory to the commercial world[C]. In Proceedings of IEEE, 2001, 89: 1478-1497.
[120] 袁野.基于嵌入式技术的网络视频监控系统.《通讯世界》, 2002, 8(4) :62-63.
[121] Jacky Mallett. The Role of Groups in Smart Camera Networks. PhD thesis, MIT, 2005.
[122] W.Wolf, B.Ozer,T.lv, "Smart cameras as Embedded System", Computer, 2002:48-53.
[123] Bramberger, M. Doblander, A. Maier, A. Rinner, B. Schwabach, H. Graz. Distributed embedded smart cameras for surveillance applications[J]. Computer, 2005, 39:68-75.
[124] Stephan Hengstler, Hamid Aghajan. A Smart Camera Mote Architecture for Distributed Intelligent Surveillance[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[125] Richard Kleihorst, Ben Schueler, Alexander Danilin, et. al. Smart camera mote with high performance vision system[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[126] Erik Ljung, Erik Simmons, Alexander Danilin, et. al. 802.15.4 Powered Distributed Wireless Smart Cameras Network[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[127] Freund Y,Schapire R E. A Decision-theoretic Generalization of Online Learning and an Application to Boosting[J]. Journal of Computer and System Sciences, 1997,55(1):119.
[128] L. M. Brown. View independent vehicle/person classification[C]. In Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks, 2004:114-123. [129] Valiant L GA Theory of Learnable[J]. Communication of ACM, 1984,27:1134. [130] Schapire R E.The Strength of Weak Learnability[J]. Machine Learning, 1990, 5:197. [131] Koenderink JJ. The structure of images[J]. Biological Cybernetics, 1984, 50: 363-396.
[132] Lindeberg T. Scale-space theory:A basic tool for analysing structures at different scales[J]. Journal of Applied Statistics, 1994, 21(2):224-270.
[133] Collins R, Fujiyoshi A, Kanade T. Algorithms for cooperative multisensor surveillance[C]. In Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[134] Kanade T, Collins R, Lipton A, et al. Advances in cooperative multi-sensor video surveillance[C]. In Proceedings of DARPA Image Understanding Workshop, 1998, 1:3-24.
[135] CHANG Ting-hsun., GONG Shao-gang. Tracking multiple people with a multi-camera system[C]. In Proceedings of IEEE Workshop on Multi-Object Tracking, 2001:19.
[136] Utsumi A, Ohya J. Multiple-camera-based human tracking using non-synchronous observations[C]. In Proceedings of 4th Asian Conference on Computer Vision, Taipei, 2000: 1034-1039.
[137] Kelly P, Katkere A, Kuramura D, et al. An architecture for multiple perspective interactive video[C]. In Proceedings of the third ACM international conference on Multimedia, New York, 1995:201-212.
[138] Black J, Ellis T. Multiple camera image tracking[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Kauai, 2001.
[139] Javed O, Rasheed Z, Alatas O, et al. Knight~m: a real-time surveillance system for multiple overlapping and non-overlapping cameras[C]. In Proceedings of the IEEE International conference on multimedia and expo. 2003.
[140] AMD Alchemy?Aul200?Data Book. Advanced Micro Devices, Inc. 2006. [141] ADSP-BF533 Blackfin Processor Hardware Reference. Analog Devices, Inc. 2003.
[142] K.Toyama, J. Krumm, B. Brumitt, and B. Meyers.Wall.ower. Principles and practice of background maintenance[C]. In Proceedings of IEEE International Conference on Computer Vision, 1999:255-261.
[143] E. Stringa, and C.S. Regazzoni. Real-time video-shot detection for scene surveillance appIication[J]. IEEE Transactions on Image Processing, 2000, 9(l):69-79.
[144] Porikli F. Real-time video object segmentation for MPEG-encoded video sequences[C]. In Proceedings of SPIE Conference on Real-Time Imaging VIII, 2004, 5297:195-203.
[145] Babu R V, Ramakrishnan K R, Srinivasan S H. Video object segmentation: a compressed domain approach[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(4):462-474.
[14] HU Weiming, TAN Tieniu, WANG Liang, et al. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transaction on Systems, Man, and Cybernetics-Part C:Applications and Reviews, 2004,34(3):334-352.
[15] S. J. Mc, S. Jabri, Z. Duric, A. Rosenfeld and H. Wechsler. Tracking Groups of People[J]. Computer Vision and Image Understanding, 2000,80:42-56.
[16] A. Elgammal, D. Harwood and L. Davis. Non-parametric Model for Background[C]. In Proceedings of the 6th European Conference on Computer Vision-Part II, London, UK, 2000.
[17] S. Theodoridis and K. Koutroumbas. Pattern Recognition, New York: Academic, 2006.
[18] M. Tsuchiya and H. Fujiyoshi. Evaluating Feature Importance for Object Classification in Visual Surveillance[C]. In Proceedings of the 18th IEEE International Conference on Pattern Recognition, 2006:978-981.
[19] Lowe David. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[20] Criminisi A, Reid I, Zisserman A. A plane measuring device[J]. Image and Vision Computing, 1999, 17(8): 625-634.
[21] Terrance E.Boult, et al. A Decande of Networked Intelligent Video Surveillance[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[22] 中国安防杂志(AS CHINA),第2006年4期.
[23] M. Valera and S. Velastin. Intelligent distributed surveillance systems: a review[j]. In Proceedings of IEEE on Vision, Image and Signal Processing, 2005, 152(2): 192-204.
[24] Rita Cucchiara. Multimedia surveillance systems[C]. In Proceedings of the third ACM international workshop on Video surveillance & sensor networks, Singapore, 2005.
[25] A Amer, C Regazzoni. Introduction to the special issue on video object processing for surveillance applications[J]. Real-Time Imaging, 2005.
[26] N. Friedman and S. Russell. Image segmentation in video sequences: a probabilistic approach[C]. In Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence, 1997:1-3.
[27] Nguyen, N.T., Venkatesh, S., West, G, and Bui, H.H.. Multiple camera coordination in a surveillance system[J]. Acta Automatica Sinica, 2003,29(3):408-421.
[28] Jaynes, C. Multi-view calibration from planar motion for video surveillance[C]. The 2nd IEEE International Workshop on Visual Surveillance, Colorado, 1999:59-67.
[29] Y.L.Tian and A.Hampapur. Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance[C]. In Proceedings of IEEE Computer Society Workshop on Motion and Video Computing, 2005.
[30] Shotton J,Blake A,Cipolla R. Contour-Based Learning for Object Detectio[C]. In Proceedings of the Tenth IEEE International Conference on Computer Vision, 2005, 1:503 -510.
[31] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland. Pfinder: Real-Time Tracking of the Human Body[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19:780-785.
[32] C. Stauffer and W. E. L. Grimson. Adaptive background mixture models for real-time tracking[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, 1999:246-252.
[33] A. Elgammal, R. Duraiswami, D. Harwood and L. Davis. Background and Foreground Modeling Using Nonparametric Kernel Density for Visual Surveillance[J]. In Proceedings of IEEE, 2002, 90(7)1151 -1163.
[34] P.KaewTraKulPong and R.Bowden. An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection[C]. In Proceedings of European Workshop on Advanced Video-based Surveillance Systems, Kingston, UK, 2001.
[35] S. M. Bhandarkar and X. Luo. Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, 2005.
[36] Y. Sheikh and M. Shah. Bayesian Object Detection in Dynamic Scenes[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, 2005.
[37] X. Luo, S. M. Bhandarkar, W. Hua and H. Gu. Nonparametric Background Modeling Using the CONDENSATION Algorithm[C]. In Proceedings of IEEE Conference on Video and Signal Based Surveillance, Washington, DC, USA ,2006.
[38] A. J. Lipton, H. Fujiyoshi, and R. S. Patil. Moving target classification and tracking from real-time video[C]. In Proceedings of IEEE Workshop Applications of Computer Vision, 1998:8-14.
[39] D. Meyer, J. Denzler, and H. Niemann. Model based extraction of articulated objects in image sequences for gait analysis[C]. In Proceedings of IEEE International Conference on Image Processing, 1998:78-81.
[40] D. Meyer, J. Psl, and H. Niemann. Gait classification with HMM's for trajectories of body parts extracted by mixture densities[C]. In Proceedings of British Machine Vision Conference, 1998:459-468.
[41] J. Barron, D. Fleet, and S. Beauchemin. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12(l):42-77.
[42] Y. Kuno, T. Watanabe, Y. Shimosakoda, and S. Nakagawa. Automated detection of human for visual surveillance system[C], In Proceedings of International Conference on Pattern Recognition, 1996:865-869.
[43] I. Haritaoglu, D. Harwood, and L. S. Davis. W~4: Real-time surveillance of people and their activities[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:809-830.
[44] Ehud Rivlin, Michael Rudzsky, Roman Goldenberg, et al. A real-time system for classification of moving objects[C]. In Proceedings of the 16th International Conference on Pattern Recognition-ICPR'02, Quebec, 2002:30688-30691.
[45] Viola, P., Jones, M., Snow, D.. Detecting Pedestrians Using Patterns of Motion and Appearance. Mitsubishi Electric Research Lab Technical Report. TR-2003-90(2003).
[46] R. Cutler and L. S. Davis. Robust real-time periodic motion detection, analysis, and applications[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:781-796.
[47] A. J. Lipton. Local application of optic flow to analyze rigid versus nonrigid motion[C]. In Proceedings of International Conference on Computer Vision Workshop Frame-Rate Vision, Corfu, Greece, 1999.
[48] O. Javed and M. Shah. Tracking and Object Classification for Automated Surveillance[C]. In Proceedings of the Seventh European Conference on Computer Vision, 2002, Part Ⅳ:343-357.
[49] C. Stauffer. Automatic hierarchical classification using time-base co-occurrences[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1999, 2:335-339.
[50] SC, Kamath C. Robust techniques for background subtraction in urban traffic video[C]. In Proceedings of SPIE Electronic Imaging:Visual Communications and Image Processing, San Jose, California, USA, 2004, 1:881-892.
[51] Robert T., Collins, et al. A system for video Surveillance and Monitoring. Technical Report CMU-RI-TR-00-12, Carnegie Mellon University 2000.
[52] R.-E. Fan, P.-H. Chen, and C.-J. Lin. Working set selection using second order information for training SVM[J]. Journal of Machine Learning Research 6, 2005.
[53] Julier S, Fleet D, El-Maraghi T. A new extension of the Kalman filter to nonlinear system[C]. In Proceedings of SPIE, 1997:182-193.
[54] Li P, Zhang T, Ma B. Unscented Kalman filter for visual curve tracking. Image and Vision Computing, 2004, 22(2):157-164.
[55] Chen Y, Rui Y. Real-time speaker tracking using particle filter sensor fusion[J]. In Proceedings of the IEEE, 2004, 92(3):485-494.
[56] Wu Y ,Huang T. Robust visual tracking by integrating multiple cues based on co-inference learning[J]. International Journal of Computer Vision, 2004, 58(1):55-71.
[57] Perez P, Vermask J, Blake A. Data fusion for visual tracking with particles[J]. In Proceedings of the IEEE, 2004, 92(3):495-513.
[58] Zhou S K, Chellappa R, Moghaddan B. Visual tracking and recognition using appearance-adaptive models in particle filters[J]. IEEE Transactions on Image Processing, 2004, 13(11):1491-1506.
[59] Hue C, Cader J, Perez P. Tracking multiple objects with particle filtering[J]. IEEE Transactions on Aerospace and Electronic Systems, 2002, 38(3):791-812.
[60] Spengler M, Schiele B. Towards robust multi-cue integration for visual tracking[J]. Machine Vision and Applications, 2003, 14(l):50-58.
[61] Merwe R,Doucet A,Freitas N,Wan E. The unscented particle filter, technical report CUED/F-INFENG/TR380, Engineering Department, Cambridge University, August, 2000.
[62] Rabiner L. A tutorial on hidden Markov models and selected applications in speech recognition[J]. In Proceedings of the IEEE, 1989,77(2):257-285.
[63] Isard M,Blake A. CONDENSATION-Conditional density propagation for visual tracking[J]. International Journal of Computer Vision, 1998, 29(1):52-81.
[64] K. Karmann and A. Brandt. Moving object recognition using an adaptive background memory[C]. In Proceedings of Time-Varying Image Processing and Moving Object Recognition,, 1990,2.
[65] M. Kilger. A shadow handler in a video-based real-time traffic monitoring system. [C] In Proceedings of IEEE Workshop Applications of Computer Vision, Palm Springs, CA, 1992:11-18.
[66] JPL. Traffic surveillance and detection technology development. Sensor Development Final Report, Jet Propulsion Laboratory Publication no.97-10, 1997.
[67] J. Malik, S. Russell, J. Weber, T. Huang, et. al. A machine vision based surveillance system for Californaia roads. Univ. of California, PATH project MOU-83 Final Report, November, 1994.
[68] I. A. Karaulova, P. M. Hall, and A. D. Marshall. A hierarchical model of dynamics for tracking people with a single video camera[C]. In Proceedings of British Machine Vision Conference, 2000:262-352.
[69] S. Ju, M. Black, and Y. Yaccob. Cardboard people: a parameterized model of articulated image motion[C]. In Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, 1996:38-44.
[70] S. A. Niyogi and E. H. Adelson. Analyzing and recognizing walking figures in XYT[C]. In Proceeings of IEEE Conference on Computer Vision and Pattern Recognition, 1994:469-474.
[71] K. Rohr. Toward model-based recognition of human movements in image sequences[J]. CVGIP: Image Understanding, 1994,59(1):94-115.
[72] S. Wachter and H.-H. Nagel. Tracking persons in monocular image sequences[J]. Computer Vision and Image Understanding, 1999, 74(3): 174-192.
[73] W. F. Gardner and D. T. Lawton. Interactive model-based vehicle tracking[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996, 18:1115-1121.
[74] T. N. Tan, G D. Sullivan, and K. D. Baker. Model-based localization and recognition of road vehides[J]. International Journal of Computer Vision, 1998, 29(l):22-25.
[75] D. Koller, K. Daniilidis, and H.-H. Nagel. Model-based object tracking in monocular image sequences of road traffic scenes[J]. International Journal of Computer Vision, 1993, 10(3):257-281.
[76] H. Kollnig and H.-H. Nagel. 3D pose estimation by directly matching polyhedral models to gray value gradient[J]. International Journal of Computer Vision, 1997,23(3):283-302.
[77] M. Haag and H.-H. Nagel. Combination of edge element and optical flow estimates for 3D-model-based vehicle tracking in traffic image sequences[J]. International Journal of Computer Vision, 1999,35(3):295-319.
[78] H. Yang, J. G Lou, H. Z. Sun, W. M. Hu, and T. N. Tan. Efficient and robust vehicle localization[C]. In Proceedings of ??IEEE International Conference on Image Processing, 2001:355-358.
[79] J. G Lou, H. Yang, W. M. Hu, and T. N. Tan. Visual vehicle tracking using an improved EKF[C]. In Proceedings of Asian Conference on Computer Vision, 2002:296-301.
[80] A. Baumberg and D. C. Hogg. Learning deformable models for tracking the human body[C]. In Proceedings of Motion-Based Recognition, Kluwer, 1996:39-60.
[81] A. Mohan, C. Papageorgiou, and T. Poggio. Example-based object detection in images by components[J]. IEEE Transaction on Pattern Recognition and Machine Intelligence, 2001, 23:349-361.
[82] A. Galata, N. Johnson, and D. Hogg. Learning variable-length Markov models of behavior[J]. Computer Vision and Image Understanding, 2001, 81(3):398-413.
[83] Y. Wu and T. S. Huang. A co-inference approach to robust visual tracking[C]. In Proceedings of International Conference on Computer Vision, 2001, II: 26-33.
[84] N. Paragios and R. Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000,12:266-280.
[85] N. Peterfreund. Robust tracking of position and velocity with Kalman snakes[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22:564-569.
[86] M. Isard and A. Blake. Contour tracking by stochastic propagation of conditional density[C]. In Proceedings of European Conference on Computer Vision, 1996:343-356.
[87] R. Polana and R. Nelson. Low level recognition of human motion[C]. In Proceedings of IEEE Workshop Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994:77-82.
[88] Segen J, Pingali S. A camera-based system for tracking people in real time[C]. In Proceedings of International Conference on Pattern Recognition, 1996:63-67.
[89] D.-S. Jang and H.-I. Choi. Active models for tracking moving objects[J]. Pattern Recognition, 2000,33(7): 135-1146.
[90] Kaneko, T. and Hori, O. Feature selection for reliable tracking using template matching[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2003:796-802.
[91] P. Mitra, C. A. Murthy, and S. K. Pal, Unsupervised feature selection using feature similarity[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(3):301-312.
[92] Xu, M., Lowey, L., and Orwell, J.. Architecture and algorithms for tracking football players with multiple cameras[C]. In Proceedings of IEEE Workshop on Intelligent Distributed Surveillance Systems, London, 2004: 51-56.
[93] Paulidis, 1., and Morellas, V.. Two examples of indoor and outdoor surveillance systems[C]. In Proceedings of Video-based Surveillance Systems, Boston, 2002:39-51.
[94] Micheloni, C, Foresti, GL., and Snidaro, L.. A co-operative multicamera system for video-surveillance of parking lots[C]. Intelligent Distributed Surveillance Systems Symp. by the IEEE, London, 2003:21-24.
[95] Yuan, X., Sun, Z., Varol, Y., and Bebis, G A distributed visual surveillance system[C]. IEEE Conference on Advanced Video and Signal based Surveillance, Florida, 2003:199-205.
[96] Qureshi and D. Terzopoulos. Towards intelligent camera networks: A virtual vision approach[C]. In Proceedings of The Second Joint IEEE International Workshop on Visual Surveillanceand Performance Evaluation of Tracking and Surveillance, Beijing, 2005.
[97] 马华东,陶丹.多媒体传感器网络及其研究进展.软件学报,2006, 17(9):2013-2028.
[98] Q. Cai and J. K. Aggarwal. Tracking human motion using multiple cameras[C]. In Proceedings of International Conference on Pattern Recognition, Vienna, Austria, 1996: 68-72.
[99] J. Krumm, S. Harris, B. Meyers, B. Brumitt, M. Hale, and S. Shafer. Multi-camera multi-person tracking for EasyLiving[C]. In Proceedings of IEEE International Workshop Visual Surveillance, Dublin, Ireland, July 2000:3-10.
[100] O. Javed, S. Khan, Z. Rasheed, and M. Shah. Camera handoff: tracking in multiple uncalibrated stationary cameras[C]. In Proceedings of IEEE Workshop Human Motion (HUMO'00), Austin, TX, 2000:113-118.
[101] Q. Cai and J. K. Aggarwal. Tracking human motion in structured environments using a distributed-camera system[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999,21(11):1241-1247.
[102] Snidaro L, Niu R, Varshney P K, et al. Automatic camera selection and fusion for outdoor surveillance under changing weather conditions[C]. In Proceedings of IEEE Conference on Advanced Video and Signal Based Surveillance, 2003:364-369.
[103] Nummiaro K, Koller-meier E, Svoboda T, et al. Color-based object tracking in multi-Camera environments[C]. In Proceedings of the 25th Pattern Recognition Symposium, 2003:591-599.
[104] Lim S N, Davis L S, Elgammal A. A scalable image-based multi-camera visual surveillance system[C]. In proceedings of IEEE Conference on Advanced Video and Signal Based Surveillance, 2003:205-212.
[105] Henriksson D, Olsson T. Maximizing the use of computer resources in multi-camera feedback control[C]. In Proceedings of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2004:360-367.
[106] Nguyen N T, Venkatesh S, West G, et al. Multiple camera coordination in a surveillance system[J]. Acta Automatica Sinica, 2003,29(3):408-422.
[107] A. Utsumi, H. Mori, J. Ohya, and M. Yachida. Multiple-view-based tracking of multiple humans[C]. In Proceedings of International Conference on Pattern Recognition, 1998:197-601.
[108] S. L. Dockstader and A. M. Tekalp. Multiple camera tracking of interacting and occluded human motion[C]. In Proceedings of IEEE, 2001, 89:1441-1455.
[109] H. Tsutsui, J. Miura, and Y. Shirai. Optical flow-based person tracking by multiple cameras[C]. In Proceedings of IEEE Conference on Multisensor Fusion and Integration in Intelligent Systems, 2001:91-96.
[110] A. Mittal and L. S. Davis. M2 tracker: a multi-view approach to segmenting and tracking people in a cluttered scene[C]. In Proceedings of European Conference on Computer Vision, 2002, 1:18-36.
[1ll] Dainis A, Juberts M. Accurate remote measurement of robot trajectory motion[C]. In Proceedings of International Conference on Robotics and Automation. 1985:92-99.
[112] Ganapathy S. Decomposition of transformation matrices for robot vision[C]. In Proceedings of Internationa] Conference on Robotics and Automation, 1984:130-139
[113] Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation[J]. IEEE Transaction on PAMI, 1992, 14(10):965-980.
[114] Wei G, Ma S. Complete two-plane camera calibration and experimental comparisons[C]. In Proceedings of ICC V'93:43 9-446.
[115] Maybank S J, Faugeras O D. A theory of self-calibration of a moving camera[J]. International Journal of Computer Vision, 1992,8(2): 123-151.
[116] Faugeras O D, Maybank S. Motion from point matches:multiplicity of solutions[J]. International Journal of Computer Vision, 1990,4:225-246.
[117] Ma S. A self-calibration technique for active vision system[J]. IEEE Transaction on Robotics and Automation, 1996, 12:114-120.
[118] Hartley RI. A Linear method for reconstruction from lines and points[C]. In Proceedings of ICCV 95:882-887.
[119] I. Pavlidis, V. Morellas, P. Tsiamyrtzis, et. al. Urban surveillance system: from the laboratory to the commercial world[C]. In Proceedings of IEEE, 2001, 89: 1478-1497.
[120] 袁野.基于嵌入式技术的网络视频监控系统.《通讯世界》, 2002, 8(4) :62-63.
[121] Jacky Mallett. The Role of Groups in Smart Camera Networks. PhD thesis, MIT, 2005.
[122] W.Wolf, B.Ozer,T.lv, "Smart cameras as Embedded System", Computer, 2002:48-53.
[123] Bramberger, M. Doblander, A. Maier, A. Rinner, B. Schwabach, H. Graz. Distributed embedded smart cameras for surveillance applications[J]. Computer, 2005, 39:68-75.
[124] Stephan Hengstler, Hamid Aghajan. A Smart Camera Mote Architecture for Distributed Intelligent Surveillance[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[125] Richard Kleihorst, Ben Schueler, Alexander Danilin, et. al. Smart camera mote with high performance vision system[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[126] Erik Ljung, Erik Simmons, Alexander Danilin, et. al. 802.15.4 Powered Distributed Wireless Smart Cameras Network[C]. In Proceedings of Workshop on Distributed Smart Cameras, Boulder, USA, 2006.
[127] Freund Y,Schapire R E. A Decision-theoretic Generalization of Online Learning and an Application to Boosting[J]. Journal of Computer and System Sciences, 1997,55(1):119.
[128] L. M. Brown. View independent vehicle/person classification[C]. In Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks, 2004:114-123. [129] Valiant L GA Theory of Learnable[J]. Communication of ACM, 1984,27:1134. [130] Schapire R E.The Strength of Weak Learnability[J]. Machine Learning, 1990, 5:197. [131] Koenderink JJ. The structure of images[J]. Biological Cybernetics, 1984, 50: 363-396.
[132] Lindeberg T. Scale-space theory:A basic tool for analysing structures at different scales[J]. Journal of Applied Statistics, 1994, 21(2):224-270.
[133] Collins R, Fujiyoshi A, Kanade T. Algorithms for cooperative multisensor surveillance[C]. In Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[134] Kanade T, Collins R, Lipton A, et al. Advances in cooperative multi-sensor video surveillance[C]. In Proceedings of DARPA Image Understanding Workshop, 1998, 1:3-24.
[135] CHANG Ting-hsun., GONG Shao-gang. Tracking multiple people with a multi-camera system[C]. In Proceedings of IEEE Workshop on Multi-Object Tracking, 2001:19.
[136] Utsumi A, Ohya J. Multiple-camera-based human tracking using non-synchronous observations[C]. In Proceedings of 4th Asian Conference on Computer Vision, Taipei, 2000: 1034-1039.
[137] Kelly P, Katkere A, Kuramura D, et al. An architecture for multiple perspective interactive video[C]. In Proceedings of the third ACM international conference on Multimedia, New York, 1995:201-212.
[138] Black J, Ellis T. Multiple camera image tracking[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Kauai, 2001.
[139] Javed O, Rasheed Z, Alatas O, et al. Knight~m: a real-time surveillance system for multiple overlapping and non-overlapping cameras[C]. In Proceedings of the IEEE International conference on multimedia and expo. 2003.
[140] AMD Alchemy?Aul200?Data Book. Advanced Micro Devices, Inc. 2006. [141] ADSP-BF533 Blackfin Processor Hardware Reference. Analog Devices, Inc. 2003.
[142] K.Toyama, J. Krumm, B. Brumitt, and B. Meyers.Wall.ower. Principles and practice of background maintenance[C]. In Proceedings of IEEE International Conference on Computer Vision, 1999:255-261.
[143] E. Stringa, and C.S. Regazzoni. Real-time video-shot detection for scene surveillance appIication[J]. IEEE Transactions on Image Processing, 2000, 9(l):69-79.
[144] Porikli F. Real-time video object segmentation for MPEG-encoded video sequences[C]. In Proceedings of SPIE Conference on Real-Time Imaging VIII, 2004, 5297:195-203.
[145] Babu R V, Ramakrishnan K R, Srinivasan S H. Video object segmentation: a compressed domain approach[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(4):462-474.