智能视频监控中的运动目标检测和跟踪算法研究
|
摘要
智能视频监控就是利用计算机视觉和数字图像处理的方法,在不需要人为干预的情况下,对摄像机拍摄的图像序列进行自动分析,实现对动态场景中运动目标的检测、跟踪和识别,并在此基础上分析和判断目标的行为,给出对运动目标行为和动作的描述,自动发现一些可疑情况,实现系统对场景中的异常进行鉴别并自动报警,从而指导和规划人们的行动。
目前,智能视频监控方面的研究和应用都面临着很多难题,国内外的许多学者投身于该领域的研究,取得了大量的成果。本文在这些成果的基础上,对智能视频监控系统中的关键步骤——运动目标检测与跟踪进行了研究。主要的工作概括如下：
(1)针对运动目标检测和跟踪算法中的应用,改进了LBP (Local Binary Pattern)算子。LBP是一种强大的纹理描述算子,论文经过对LBP的二进制位串的01跳变情况进行统计,合并了出现概率较低的模式,使得LBP纹理的种类得到极大地削减,使后续使用LBP纹理的运动目标检测与跟踪算法在特征匹配时的速度得到提高。
(2)提出了一种结合改进的LBP纹理和色度信息的运动目标检测算法。运用LBP纹理和色度这两种特征对阴影都不敏感的特性,论文用LBP纹理和色度信息对背景进行描述,然后把该背景描述应用到高斯混合模型中,提出了一种新的运动目标检测方法,该方法能较好的抵御阴影及背景光照变化的影响；
(3)提出了一种结合光流法与三帧差分法的运动目标检测算法。由于计算光流的算法复杂,论文简化了光流的计算：选择图像中少数具有某些特征的像素点,只对这部分像素点计算光流信息,有效地减少了复杂度。但是,由于只选取了部分代表性像素,检测得到的运动目标区域不太完整,于是论文引入了三帧差分法作为简化光流法的补充,在不增加太多计算量的情况下,得到了相对完整的运动目标轮廓。
(4)提出了联合LBP纹理和色度信息的Camshift跟踪算法。由于传统的Camshift算法是基于色彩直方图的目标跟踪,当目标和背景颜色相近或干扰目标和被跟踪目标颜色相近时,或者运动目标存在阴影时,跟踪的正确性受到很大的影响。论文采用LBP纹理和色度信息相结合描述运动物体,两种特征都对阴影不敏感,能克服阴影对跟踪结果的影响。另外,对于纹理缺乏区域,LBP纹理性能不好,但是色度往往能取得较好效果；而对运动目标和背景颜色相同的区域,而LBP纹理往往又能取得一定的效果。
(5)提出了基于Kalman滤波器和Blob匹配法的目标跟踪算法。Blob匹配法利用目标的外形特征去匹配候选目标,该方法在运动物体数目较多时,每个Blob都要与其它的各物体相匹配,速度会变慢,且不适用于对非刚性物体的跟踪,同时在目标遮挡时也难于继续跟踪到目标。而Kalman滤波器可以根据目标先前的运动信息去预测下一帧中目标的位置,和Blob匹配法结合后,能在Blob搜索时只需在预测到的位置附近做Blob匹配,减少了计算量。
论文得到了云南省应用基础研究计划项目“智能视频坚控中的运动目标检测与跟踪技术研究”(编号：2011FB019)的支持。
Intelligent visual surveillance system can automatically analyze video sequences by the methods of computer vision and digital image processing without human intervention. The system can real-time detect, track and recognize moving objects in a scene. Furthermore, it can analyze and judge moving objects' behavior, give a description of the behaviors and actions, automatically discover some suspicious behaviors, identify irregular actions in the scene and alarm automatically in order to guide our actions and decisions.
At present, there are many problems in the research and application of intelligent visual surveillance. Both domestic and overseas scholars devote themselves to the research and get a large number of achievements. On the basis of these achievements, this thesis researches the technologies of moving objects detection and tracking, which are critical steps in the intelligent visual surveillance. The main work is summarized as follows:
(1) The LBP (Local Binary Pattern) operator is improved. LBP is a powerful mean of texture description. After counting the times of0jumping to1and1to0in a LBP's binary codes, the models, which have lower probability of occurrence, are combined. Therefore, the species of LBP texture are reduced, and the speed of feature matching is increased in moving objects detection and tracking algorithm based on the LBP texture.
(2) A moving objects detection method based on a combination of improved local binary pattern texture and hue is proposed. Because both LBP texture and hue are not sensitive to shadows, they are used to describe a background. Then, the background is applied to the Gaussian mixture model, and the method can better resist shadows and the changes of background illumination.
(3) A moving object detection algorithm based on a combination of optical flow and the three-frame difference is proposed. Because of the complexity of computing optical flow, the calculation of optical flow is simplified. A few pixels with certain characteristics are selected to compute optical flow information, which reduce the algorithm's complexity. However, because of selecting parts of representative pixels only, target area detected by the algorithm is not complete, so three-frame difference method is introduced as a supplement in order to get a relative complete target area without increasing too much computing complexity.
(4) A Camshift tracking algorithm based on LBP texture and hue is proposed. Traditional Camshift algorithm is based on the color histogram of moving objects. When an object and its corresponding background have similar color, an interferential object and the tracked object have similar color or moving objects have shadows, the tracking accuracy can be greatly affected. The LBP texture and hue are combined to describe moving objects in order to solve these troubles because two features are not sensitive to the shadow. In addition, in the region with similar color between moving objects and background, LBP texture can often achieve certain effects; and in the region of lacking texture, the LBP texture performance is not good, but color can often achieve better results.
(5) A moving object tracking algorithm based on Kalman filter and blob matching is proposed. Blob matching method matches the candidate target using the moving objects'shape characteristics. When there are a large number of moving objects, the method has slower speed because each blob must match with other objects. Meanwhile, the method does not apply to non-rigid object tracking, and it is difficult to continue to track objects if the objects'occlusion is existed. Kalman filter can predict the target's location in the next frame using the current frame's motion information. Before blob matching, Kalman filter is used, so the matching area can be limited in the predicted area by Kalman filter.
This thesis is supported by the application foundation project of Yunnan province "Research on moving objects detection and tracking methods in intelligent visual surveillance system"(No.2011FB019).
目前,智能视频监控方面的研究和应用都面临着很多难题,国内外的许多学者投身于该领域的研究,取得了大量的成果。本文在这些成果的基础上,对智能视频监控系统中的关键步骤——运动目标检测与跟踪进行了研究。主要的工作概括如下：
(1)针对运动目标检测和跟踪算法中的应用,改进了LBP (Local Binary Pattern)算子。LBP是一种强大的纹理描述算子,论文经过对LBP的二进制位串的01跳变情况进行统计,合并了出现概率较低的模式,使得LBP纹理的种类得到极大地削减,使后续使用LBP纹理的运动目标检测与跟踪算法在特征匹配时的速度得到提高。
(2)提出了一种结合改进的LBP纹理和色度信息的运动目标检测算法。运用LBP纹理和色度这两种特征对阴影都不敏感的特性,论文用LBP纹理和色度信息对背景进行描述,然后把该背景描述应用到高斯混合模型中,提出了一种新的运动目标检测方法,该方法能较好的抵御阴影及背景光照变化的影响；
(3)提出了一种结合光流法与三帧差分法的运动目标检测算法。由于计算光流的算法复杂,论文简化了光流的计算：选择图像中少数具有某些特征的像素点,只对这部分像素点计算光流信息,有效地减少了复杂度。但是,由于只选取了部分代表性像素,检测得到的运动目标区域不太完整,于是论文引入了三帧差分法作为简化光流法的补充,在不增加太多计算量的情况下,得到了相对完整的运动目标轮廓。
(4)提出了联合LBP纹理和色度信息的Camshift跟踪算法。由于传统的Camshift算法是基于色彩直方图的目标跟踪,当目标和背景颜色相近或干扰目标和被跟踪目标颜色相近时,或者运动目标存在阴影时,跟踪的正确性受到很大的影响。论文采用LBP纹理和色度信息相结合描述运动物体,两种特征都对阴影不敏感,能克服阴影对跟踪结果的影响。另外,对于纹理缺乏区域,LBP纹理性能不好,但是色度往往能取得较好效果；而对运动目标和背景颜色相同的区域,而LBP纹理往往又能取得一定的效果。
(5)提出了基于Kalman滤波器和Blob匹配法的目标跟踪算法。Blob匹配法利用目标的外形特征去匹配候选目标,该方法在运动物体数目较多时,每个Blob都要与其它的各物体相匹配,速度会变慢,且不适用于对非刚性物体的跟踪,同时在目标遮挡时也难于继续跟踪到目标。而Kalman滤波器可以根据目标先前的运动信息去预测下一帧中目标的位置,和Blob匹配法结合后,能在Blob搜索时只需在预测到的位置附近做Blob匹配,减少了计算量。
论文得到了云南省应用基础研究计划项目“智能视频坚控中的运动目标检测与跟踪技术研究”(编号：2011FB019)的支持。
Intelligent visual surveillance system can automatically analyze video sequences by the methods of computer vision and digital image processing without human intervention. The system can real-time detect, track and recognize moving objects in a scene. Furthermore, it can analyze and judge moving objects' behavior, give a description of the behaviors and actions, automatically discover some suspicious behaviors, identify irregular actions in the scene and alarm automatically in order to guide our actions and decisions.
At present, there are many problems in the research and application of intelligent visual surveillance. Both domestic and overseas scholars devote themselves to the research and get a large number of achievements. On the basis of these achievements, this thesis researches the technologies of moving objects detection and tracking, which are critical steps in the intelligent visual surveillance. The main work is summarized as follows:
(1) The LBP (Local Binary Pattern) operator is improved. LBP is a powerful mean of texture description. After counting the times of0jumping to1and1to0in a LBP's binary codes, the models, which have lower probability of occurrence, are combined. Therefore, the species of LBP texture are reduced, and the speed of feature matching is increased in moving objects detection and tracking algorithm based on the LBP texture.
(2) A moving objects detection method based on a combination of improved local binary pattern texture and hue is proposed. Because both LBP texture and hue are not sensitive to shadows, they are used to describe a background. Then, the background is applied to the Gaussian mixture model, and the method can better resist shadows and the changes of background illumination.
(3) A moving object detection algorithm based on a combination of optical flow and the three-frame difference is proposed. Because of the complexity of computing optical flow, the calculation of optical flow is simplified. A few pixels with certain characteristics are selected to compute optical flow information, which reduce the algorithm's complexity. However, because of selecting parts of representative pixels only, target area detected by the algorithm is not complete, so three-frame difference method is introduced as a supplement in order to get a relative complete target area without increasing too much computing complexity.
(4) A Camshift tracking algorithm based on LBP texture and hue is proposed. Traditional Camshift algorithm is based on the color histogram of moving objects. When an object and its corresponding background have similar color, an interferential object and the tracked object have similar color or moving objects have shadows, the tracking accuracy can be greatly affected. The LBP texture and hue are combined to describe moving objects in order to solve these troubles because two features are not sensitive to the shadow. In addition, in the region with similar color between moving objects and background, LBP texture can often achieve certain effects; and in the region of lacking texture, the LBP texture performance is not good, but color can often achieve better results.
(5) A moving object tracking algorithm based on Kalman filter and blob matching is proposed. Blob matching method matches the candidate target using the moving objects'shape characteristics. When there are a large number of moving objects, the method has slower speed because each blob must match with other objects. Meanwhile, the method does not apply to non-rigid object tracking, and it is difficult to continue to track objects if the objects'occlusion is existed. Kalman filter can predict the target's location in the next frame using the current frame's motion information. Before blob matching, Kalman filter is used, so the matching area can be limited in the predicted area by Kalman filter.
This thesis is supported by the application foundation project of Yunnan province "Research on moving objects detection and tracking methods in intelligent visual surveillance system"(No.2011FB019).
引文
[Ahonen09]Timo Ahonen, Jiri Matas, Chu He, Matti Pietikainen. Rotation invariant image description with local binary pattern histogram fourier features[J]. Lecture Notes in Computer Science, Vol.5575,2009:61-70.
[Anderson85]Anderson C, Bert P, Vander W al. Change detection and tracking using pyramids transformation techniques[A]. In:Proceeding of SPIE Conference on Intelligent Robots and Computer Vision[C], Cambridge, MAR, 1985,579:72-78.
[Axis11]Axis Communications[Online]. http://www.axis.com/.2011-9-12.
[Barron94]Barron J L, Fleet D J, Beauchemin S. Performance of optical flow techniques[J]. International Journal of Computer Vision,1994,12 (1):42-77.
[Bascle95]Bascle B, Deriche R. Region tracking through image sequences[A]. In Proceeding of IEEE International Conference of Computer Vision,1995: 302-307.
[Bradski08]Gary Bradski, Adrian Kaehler. Learning OpenCV-Computer Vision with the OpenCV Library [Online]. Free online edition, http://safari.oreilly.com.2011-9-12.
[Cedras95]Cedras C, Shah M. Motion-Based recognition:A survey[J]. Image and Vision Computing,1995,13(2):129-155.
[Collins00]R Collins, A Lipton, T Kanade et al. A System for Video Surveillance and Monitoring[Online]. Tech.report CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University,2000. http://www.ri.cmu.edu/publication_view.html?pub_id=3325.2011-9-12.
[Comaniciu03]Comaniciu Dorin, Ramesh Visvanathan, Meer Peter. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[Cvrr00]Computer Vision and Robotics Research Laboratory Test bed Data [Online]. Available:http://cvrr.ucsd.edu/aton/shadow/.2011-9-12.
[Detec11]Detec Company [Online], http://www.detec.no/.2011-9-12.
[Fejes97]Fejes S, Davis L S. Detection of Independent Motion Using Directional Motion Estimation[R]. University of Maryland, Technical Report: CAR-TR-866, CS3815,1997.
[Gennery82]Gennery D. Tracking known three-dimensional objects[A]. In Proceeding of International Conference on Artifical Intelligence[C].1982: 13-17.
[Ghosa94]GHOSAL Sugata. Robust optical flow estimation[J]. Image Processing, 1994,2(12):780-784.
[Ghosa97]GHOSAL Sugata. A moment-based unified approach to image feature detection[J]. Image Processing,1997,6 (6):781-793.
[Haritaoglu00]I. Haritaoglu, D. Harwood, L. S. Davis. W4:Real-time surveillance of people and their activities[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[Harris88]C. Harris and M. Stephens. A combined corner and edge detector[A]. In Proceedings of the 4th Alvey Vision Conference[C].1988:147-151.
[Hou06]HOU Zhi-Qiang, HAN Chong-Zhao. A Survey of Visual Tracking [J]. ACTA Automatica Sinica,2006,32(4):603-617.
[Hu04]Weiming Hu, Tieniu Tan, Liang Wang, Steve Maybank. A survey on visual suveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man and Cybernetics,2004,34(3):334-352.
[Huang10]HUANG Xin-juan, ZHOU Jie-min, LIU Bo-yang. Moving objects detection approach based on adaptive mixture Gaussian background model [J]. Journal of Computer Applications,2010,30(1):71-74.
[Huston08]Huston Stephen J. and Krapp Holger G., Visuomotor Transformation in the Fly Gaze Stabilization System[J]. Plos Biology,2008,6 (7):1468-1478.
[Ivs11]第三届全国智能视觉监控学术会议[Online]. http://ivs2011.csp.escience.cn/dct/page/65540.2011-9-12.
[Jain96]Jain A. K., Zhong Y. Lakshmanan. Object matching using deformable templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996,18(3):267-278.
[Jeon97]J. G. Jeon,K. T. Park. Multi-target tracking system using texture[A]. In Proeeedings of the SPIE Internatlonal Soeiety for optieal Engineering [C],1997,3024:229-236.
[Jong03]Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system[J]. Pattern Recognition Letters, 2003,24 (1-3):113-128.
[Jung98]Jung S. K., Wohn K. Y. A model based 3-D tracking of rigid objects from a sequence of multiple perspective views[J]. Pattern Recognition Letters,1998, 19(5-6):499-512.
[Kakadiaris00Kakadiaris L., Metaxas D. Model-based estimation of 3D human motion[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000,22(12):1453-1459.
[Kalman60]R. E. Kalman. A new approach to linear filtering and prediction problems[J]. Transactions of the ASME, Journal of Basic Engineering. 82(Series D):35-45.1960.
[Kass88]Kass M, Witkin A, Terzopoulos D. Snakes:Active contour models[J]. International Journal of Computer Vision,1988,1(4):321-331.
[Koller93]Koller D, Daniilidis K, Nagel H. Model-based object tracking in monocular image dequences of road traffic scene[J]. International Journal of Computer Vision,1993,10(3):257-281.
[Kwak08]KWAK N. Feature extraction for classification problems and its application to face recognition[J]. Pattern Recognition,2008, 41(5):1701-1717.
[Lee05]LEE S, DANIELS K. Gaussian kernel width generator for support vector clustering[A]. In Proceedings of the International Conference on Bioinformatics and its Applications[C]. IEEE,2005:151-162.
[Li09]LI Guang-lun, SHU Wei-qun. Real-time Detection for Moving Object in Video Monitor System [J]. Computer Engineering,2009,35(17):217-222.
[Lipton98]A. J. Lipton, H. Fujiyoshi, R. S. Patil. Moving target classification and tracking from real-time video [A]. In Proceeding of IEEE Workshop Applications of Computer Vision[C],1998:8-14.
[Liu09]LIU Guang-yu, LIU Guo-dong. Method for moving objection detection based on mixture Guassian models[J]. Computer Engineering and Applications,2009,45(24):180-182.
[Lucas81]B. D. Lucas, T. Kanade. An iterative image registration technique with an application in stereo vision[A]. In Proceeding of 7th International Joint Conference on Artificial Intelligence[C], Vancouver,1981:674-679.
[Meyer94]Meyer F, Bouthemy P. Region-based tracking using affine motion models in long image sequences[J]. CVGIP:Image understanding,1994,60(2): 119-140.
[Mitiche87]Mitiche A, Wang Y F, Aggarwal. Experiments in computing optical flow with gradient-based multi-constraint method[J]. Pattern Recognition, 1987,20(2):173-179.
[Nguyen04]Nguyen H.T, Smeulders A.W.M. Fast occluded object Tracking by a Robust Appearance Filter[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1099-1104.
[Nickels02]Nickels K, Hutchinson S. Estimating uncertainty in SSD-based feature tracking[J]. Image and Vision Computing,2002,20(1):47-58.
[Nummiaro03] Nummiaro Katja, Koller-meier Esther, Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [A]. In Proceeding of 24th DAGM Symposium on Pattern Recognition[C]. London, UK Springer-Verlag,2003:591-599.
[Objectvideo11] ObjectVideo Company[Online]. http://www.objectvideo.com/. 2011-9-12.
[Ojala02]Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7): 971-987.
[Paragios00]Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (3):266-280.
[PETS00]Performance Evaluation of Tracking and Surveillance 2000 (PETS2000) [Online]. Available:http://ftp.pets.rdg.ac.uk/pub/PETS2000/.2011-9-12.
[PETS01]The Second IEEE International Workshop on Performance Evaluation of Tracking and Surveillance(PETS2001) [Online]. Available: http://www.cvg.cs.rdg.ac.Uk/PETS2001/.2011-9-12.
[Ping03]Ping Lai Lo, B Sun J,Velastin S A. Fusing Visual and Audio Information in Distributed Intelligent Surveillance System for Public Transport Systems[J], Acta Automatica Sinica,2003,29(3):393-407.
[Power02]Power PW, Schoonees JA. Understanding background mixture models for foregrounds segmentation [A]. In Proceedings of Image and Vision Computing[C], New Zealand Auckland,2002:267-271.
[Ristic04]Ristic B, Arulampalam S, Gordon N. Beyond the Kalman Filter: Particle Filters for Tracking Applications[M]. Boston, London: Artech House, 2004.
[Shi94]Jianbo Shi, Carlo tomasi. Good features to track[A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR94) [C], Seattle, June,1994.
[Stauffer99]C. Stauffer, W. Grimson. Adaptive background mixture models for real time tracking[J]. Computer Vision and Pattern Recognition, 1999:252-258.
[Sun09]SUN Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control,2009, 38(1):11-16.
[Teng05]TENG Chin-Hung, LAI Shang-Hong. Accurate optical flow computation under non-uniform brightness variations [J].Computer Vision and Image Understanding,2005, (11):315-346.
[Till]Texas Instrument视频优化硬件与领先视频软件的完美结合必将满足不断壮大的IP视频监控市场需[Online]. http://focus.ti.com.cn/cn/pr/docs/preldetail.tsp?prelld=cnsc00277.2011-9-12
[Tissainayagam05]Tissainayagam P, Suter D. Obkect tracking in image sequences using point feature[J]. Pattern Recognition,2005,38(1):105-113.
[Wang02]WANG Liang, HU Wei-ming, TAN Tie-niu. A Survey of Visual Analysis of Human Motion [J]. Chinese Journal of Computers,2002,25(3):225-237.
[Wang09]WANG Huan, Wang Jiang-tao, REN Ming-wu, YANG Jing-yu. A New Robust Objects Tracking Algorithm by Fusing Multi-features[J]. Journal of Image and Graphics,2009,14(3):489-498.
[Watcher99]Watcher S, Nagel H H. Tracking persons in monocular image sequences[J]. Computer Vision and Image Understanding,1999,74(3): 174-192.
[Xu04]Xu L Q,Landabaso J L,Lei B. Segmentation and track-ing of multiple moving objects for intelligent video analysis [J].BT Technology Journal,2004, 22(3):140-150.
[Yu00]Yu Z, Jain A K, Dubuisson-Jolly M. Object tracking using deformable teplates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(5):544-549.
[Zhang06a]ZHANG Juan, MAO Xiao-bo, CHEN Tie-jun. Survey of moving object tracking algorithm[J]. Application Research of Computers,2006, 26(12):4407-4410.
[Zhang06b]ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object tracking algorithm based on CamShift [J]. Computer Engineering and Design,2006,27(11):108-110.
[Zhang08]ZHANG Hai-qing, LI Hou-qiang. Object Tracking Through Multiple Cues [J]. Journal of Image and Graphics,2008,13(11):2187-2196.
[Zhou 04]Zhou S K,Chellappa R,Moghaddan B. Visual tracking and recognition using appearance-adaptive medels in Particle filters[J]. IEEE Transactions on Image Proeessing,2004,13(11):1491-1506.
[Zhu00]Zhu Z, Xu G, Yang B, et al. VISATRAM: A real-time vision system for automatic traffic monitoring[J]. Image and Vision Computing,2000,18(10): 781-794.
[博睿视11]北京博睿视科技有限责任公司[Online].http://www.bravevideo.com/. 2011-9-12.
[昌娅01]昌娅,胡卫明,谭铁牛.交通视觉监控系统中的三维车辆线框模型可视化算法[A].中国工程图学学会会议集[C],中国工程图学学会,2001.
[代科学06]代科学,李国辉,涂丹等.监控视频运动目标检测减背景技术的研究现状和展望[J].中国图象图形学报,2006,vol.11(7)：919-927.
[冯蓓蓓09]冯蓓蓓.运动目标检测系统的设计与实现[D].大连理工大学硕士论文,2009.
[冈萨雷斯04]冈萨雷斯.数字图像处理[M].电子工业出版社,2004.
[郝菲09]郝菲.智能监控系统中运动目标检测跟踪的研究[D].北京交通大学硕士论文,2009.
[宏电11]深圳市宏电技术股份有限公司[Online]. http://www.hongdian.com. 2011-9-12.
[侯志强06]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,vo132(4)：603-617.
[胡学友11]胡学友,陶亮,倪敏生.基于混合粒子滤波的目标跟踪[J].计算机应用.2011,31(6)：1602-1604+1608.
[华亿11]苏州华亿安防科技有限公司[Online], http://www.cnivs.com/. 2011-9-12.
[黄超群10]黄超群.基于混合高斯模型和Kalman滤波器的运动目标检测与跟踪[D].云南大学硕士学位论文,2010.
[贾桂敏08]贾桂敏.基于物体局部信息的跟踪算法研究[D].天津大学硕士论文,2008.
[乐应英10]乐应英.智能视频监控系统中目标检测与跟踪关键技术研究[D].云南大学硕士学位论文,2010.
[雷雨权04]雷雨权.多媒体电视监控与报警系统[M].北京：国防工业出版社2004.1.
[李爽07]李爽.运动目标识别和跟踪的智能化视频监控系统研究[D].辽宁工学院硕士学位论文,2007.
[刘光宇09]刘光宇,刘国栋.基于混合高斯模型的运动目标检测方法[J].计算机工程与应用,2009,vo1.45(24)：180-182.
[刘瑞祯07]刘瑞祯,于仕琪OpenCV教程-基础篇[M].北京：北京航空航天大学出版社,2007.
[刘雪07]刘雪.研究运动目标检测与跟踪技术[D].山东大学硕士学位论文,2007.
[刘一山07]刘一山.智能监控系统中运动目标检测与跟踪技术的研究[D].西安科技大学硕士学位论文,2007.
[楼建光02]楼建光,柳崎峰,胡卫明,谭铁牛.交通视觉监控中的摄像机参数求解[J].计算机学报,2002,(11)：1269-1273.
[楼建光03]楼建光,柳崎峰,谭铁牛,胡卫明.基于三维模型的交通场景视觉监控(英文)[J].自动化学报,2003,(3)：434-449
[卢璇10]卢璇,雷航,郝宗波.联合多特征的自动CamShift跟踪算法[J].计算机应用,2010,30(3)：650-652.
[孟凤07]孟凤.视频监控系统中运动目标检测与跟踪算法的研究[D].燕山大学硕士学位论文,2007.
[谭铁牛09a]谭铁牛,黄凯奇,王莹.基于轮廓的异常行为识别方法[Z].CN101464952,2009.
[谭铁牛09b]谭铁牛,黄凯奇,张兆翔,李敏.一种基于运动目标表象和运动信息的摄像机自标定方法[Z].CN101488222,2009.
[田原01]田原,谭铁牛,孙洪赞,胡卫明.一种能处理部分遮挡的鲁棒性实时跟踪方法[A].中国工程图学学会会议集[C],中国工程图学学会,2001.
[田原02]田原,谭铁牛,孙洪赞.一种具有良好鲁棒性的实时跟踪方法[J].自动化学报,2002,(5)：851-853.
[王亮02]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,(3)：225-237.
[王绍钰08]王绍钰.基于粒子滤波器的运动目标跟踪方法研究[D].中南大学硕士论文,2008.
[王新余04]王新余,张桂林.基于光流的运动目标实时检测方法研究[J].计算机工程与应用,2004(1)：43-46.
[工耀南03]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京：高等教育出版社,2003.
[文灏07]文灏,陈红涛.基于减背景与对称差分的运动目标检测[J].微计算机信息,2007,23(9-1)：99-101.
[徐慧04]徐慧VisuaIC++数字图像实用工程案例精选[M].北京：人民邮电出版社,2004.
[徐剑09]徐剑,丁晓青,王生进等.一种融合局部纹理和颜色信息的背景减除方法[J].自动化学报,2009,vo1.35(9)：1145-1150.
[张海清07]张海清.计算机智能视频监控系统的目标运动检测和跟踪研究[D].中国科学技术大学,2007.
[章毓晋00]章毓晋.图像理解与计算机视觉[M].北京：清华大学出版社,2000
[赵俊07]赵俊.智能视频监控系统关键技术研究[D].西安电子科技大学硕士论文,2007.
[智安邦11]北京智安邦科技有限公司.安防智能视频监控系统[Online]. http://www.zanb.com.cn/.2011-9-12.
[周西汉05]周西汉,刘勃,周荷琴.一种基于对称差分和背景消减的运动检测方法[J].计算机仿真,2005,22(4)：117-119.
[Anderson85]Anderson C, Bert P, Vander W al. Change detection and tracking using pyramids transformation techniques[A]. In:Proceeding of SPIE Conference on Intelligent Robots and Computer Vision[C], Cambridge, MAR, 1985,579:72-78.
[Axis11]Axis Communications[Online]. http://www.axis.com/.2011-9-12.
[Barron94]Barron J L, Fleet D J, Beauchemin S. Performance of optical flow techniques[J]. International Journal of Computer Vision,1994,12 (1):42-77.
[Bascle95]Bascle B, Deriche R. Region tracking through image sequences[A]. In Proceeding of IEEE International Conference of Computer Vision,1995: 302-307.
[Bradski08]Gary Bradski, Adrian Kaehler. Learning OpenCV-Computer Vision with the OpenCV Library [Online]. Free online edition, http://safari.oreilly.com.2011-9-12.
[Cedras95]Cedras C, Shah M. Motion-Based recognition:A survey[J]. Image and Vision Computing,1995,13(2):129-155.
[Collins00]R Collins, A Lipton, T Kanade et al. A System for Video Surveillance and Monitoring[Online]. Tech.report CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University,2000. http://www.ri.cmu.edu/publication_view.html?pub_id=3325.2011-9-12.
[Comaniciu03]Comaniciu Dorin, Ramesh Visvanathan, Meer Peter. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[Cvrr00]Computer Vision and Robotics Research Laboratory Test bed Data [Online]. Available:http://cvrr.ucsd.edu/aton/shadow/.2011-9-12.
[Detec11]Detec Company [Online], http://www.detec.no/.2011-9-12.
[Fejes97]Fejes S, Davis L S. Detection of Independent Motion Using Directional Motion Estimation[R]. University of Maryland, Technical Report: CAR-TR-866, CS3815,1997.
[Gennery82]Gennery D. Tracking known three-dimensional objects[A]. In Proceeding of International Conference on Artifical Intelligence[C].1982: 13-17.
[Ghosa94]GHOSAL Sugata. Robust optical flow estimation[J]. Image Processing, 1994,2(12):780-784.
[Ghosa97]GHOSAL Sugata. A moment-based unified approach to image feature detection[J]. Image Processing,1997,6 (6):781-793.
[Haritaoglu00]I. Haritaoglu, D. Harwood, L. S. Davis. W4:Real-time surveillance of people and their activities[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[Harris88]C. Harris and M. Stephens. A combined corner and edge detector[A]. In Proceedings of the 4th Alvey Vision Conference[C].1988:147-151.
[Hou06]HOU Zhi-Qiang, HAN Chong-Zhao. A Survey of Visual Tracking [J]. ACTA Automatica Sinica,2006,32(4):603-617.
[Hu04]Weiming Hu, Tieniu Tan, Liang Wang, Steve Maybank. A survey on visual suveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man and Cybernetics,2004,34(3):334-352.
[Huang10]HUANG Xin-juan, ZHOU Jie-min, LIU Bo-yang. Moving objects detection approach based on adaptive mixture Gaussian background model [J]. Journal of Computer Applications,2010,30(1):71-74.
[Huston08]Huston Stephen J. and Krapp Holger G., Visuomotor Transformation in the Fly Gaze Stabilization System[J]. Plos Biology,2008,6 (7):1468-1478.
[Ivs11]第三届全国智能视觉监控学术会议[Online]. http://ivs2011.csp.escience.cn/dct/page/65540.2011-9-12.
[Jain96]Jain A. K., Zhong Y. Lakshmanan. Object matching using deformable templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996,18(3):267-278.
[Jeon97]J. G. Jeon,K. T. Park. Multi-target tracking system using texture[A]. In Proeeedings of the SPIE Internatlonal Soeiety for optieal Engineering [C],1997,3024:229-236.
[Jong03]Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system[J]. Pattern Recognition Letters, 2003,24 (1-3):113-128.
[Jung98]Jung S. K., Wohn K. Y. A model based 3-D tracking of rigid objects from a sequence of multiple perspective views[J]. Pattern Recognition Letters,1998, 19(5-6):499-512.
[Kakadiaris00Kakadiaris L., Metaxas D. Model-based estimation of 3D human motion[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000,22(12):1453-1459.
[Kalman60]R. E. Kalman. A new approach to linear filtering and prediction problems[J]. Transactions of the ASME, Journal of Basic Engineering. 82(Series D):35-45.1960.
[Kass88]Kass M, Witkin A, Terzopoulos D. Snakes:Active contour models[J]. International Journal of Computer Vision,1988,1(4):321-331.
[Koller93]Koller D, Daniilidis K, Nagel H. Model-based object tracking in monocular image dequences of road traffic scene[J]. International Journal of Computer Vision,1993,10(3):257-281.
[Kwak08]KWAK N. Feature extraction for classification problems and its application to face recognition[J]. Pattern Recognition,2008, 41(5):1701-1717.
[Lee05]LEE S, DANIELS K. Gaussian kernel width generator for support vector clustering[A]. In Proceedings of the International Conference on Bioinformatics and its Applications[C]. IEEE,2005:151-162.
[Li09]LI Guang-lun, SHU Wei-qun. Real-time Detection for Moving Object in Video Monitor System [J]. Computer Engineering,2009,35(17):217-222.
[Lipton98]A. J. Lipton, H. Fujiyoshi, R. S. Patil. Moving target classification and tracking from real-time video [A]. In Proceeding of IEEE Workshop Applications of Computer Vision[C],1998:8-14.
[Liu09]LIU Guang-yu, LIU Guo-dong. Method for moving objection detection based on mixture Guassian models[J]. Computer Engineering and Applications,2009,45(24):180-182.
[Lucas81]B. D. Lucas, T. Kanade. An iterative image registration technique with an application in stereo vision[A]. In Proceeding of 7th International Joint Conference on Artificial Intelligence[C], Vancouver,1981:674-679.
[Meyer94]Meyer F, Bouthemy P. Region-based tracking using affine motion models in long image sequences[J]. CVGIP:Image understanding,1994,60(2): 119-140.
[Mitiche87]Mitiche A, Wang Y F, Aggarwal. Experiments in computing optical flow with gradient-based multi-constraint method[J]. Pattern Recognition, 1987,20(2):173-179.
[Nguyen04]Nguyen H.T, Smeulders A.W.M. Fast occluded object Tracking by a Robust Appearance Filter[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1099-1104.
[Nickels02]Nickels K, Hutchinson S. Estimating uncertainty in SSD-based feature tracking[J]. Image and Vision Computing,2002,20(1):47-58.
[Nummiaro03] Nummiaro Katja, Koller-meier Esther, Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [A]. In Proceeding of 24th DAGM Symposium on Pattern Recognition[C]. London, UK Springer-Verlag,2003:591-599.
[Objectvideo11] ObjectVideo Company[Online]. http://www.objectvideo.com/. 2011-9-12.
[Ojala02]Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7): 971-987.
[Paragios00]Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (3):266-280.
[PETS00]Performance Evaluation of Tracking and Surveillance 2000 (PETS2000) [Online]. Available:http://ftp.pets.rdg.ac.uk/pub/PETS2000/.2011-9-12.
[PETS01]The Second IEEE International Workshop on Performance Evaluation of Tracking and Surveillance(PETS2001) [Online]. Available: http://www.cvg.cs.rdg.ac.Uk/PETS2001/.2011-9-12.
[Ping03]Ping Lai Lo, B Sun J,Velastin S A. Fusing Visual and Audio Information in Distributed Intelligent Surveillance System for Public Transport Systems[J], Acta Automatica Sinica,2003,29(3):393-407.
[Power02]Power PW, Schoonees JA. Understanding background mixture models for foregrounds segmentation [A]. In Proceedings of Image and Vision Computing[C], New Zealand Auckland,2002:267-271.
[Ristic04]Ristic B, Arulampalam S, Gordon N. Beyond the Kalman Filter: Particle Filters for Tracking Applications[M]. Boston, London: Artech House, 2004.
[Shi94]Jianbo Shi, Carlo tomasi. Good features to track[A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR94) [C], Seattle, June,1994.
[Stauffer99]C. Stauffer, W. Grimson. Adaptive background mixture models for real time tracking[J]. Computer Vision and Pattern Recognition, 1999:252-258.
[Sun09]SUN Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control,2009, 38(1):11-16.
[Teng05]TENG Chin-Hung, LAI Shang-Hong. Accurate optical flow computation under non-uniform brightness variations [J].Computer Vision and Image Understanding,2005, (11):315-346.
[Till]Texas Instrument视频优化硬件与领先视频软件的完美结合必将满足不断壮大的IP视频监控市场需[Online]. http://focus.ti.com.cn/cn/pr/docs/preldetail.tsp?prelld=cnsc00277.2011-9-12
[Tissainayagam05]Tissainayagam P, Suter D. Obkect tracking in image sequences using point feature[J]. Pattern Recognition,2005,38(1):105-113.
[Wang02]WANG Liang, HU Wei-ming, TAN Tie-niu. A Survey of Visual Analysis of Human Motion [J]. Chinese Journal of Computers,2002,25(3):225-237.
[Wang09]WANG Huan, Wang Jiang-tao, REN Ming-wu, YANG Jing-yu. A New Robust Objects Tracking Algorithm by Fusing Multi-features[J]. Journal of Image and Graphics,2009,14(3):489-498.
[Watcher99]Watcher S, Nagel H H. Tracking persons in monocular image sequences[J]. Computer Vision and Image Understanding,1999,74(3): 174-192.
[Xu04]Xu L Q,Landabaso J L,Lei B. Segmentation and track-ing of multiple moving objects for intelligent video analysis [J].BT Technology Journal,2004, 22(3):140-150.
[Yu00]Yu Z, Jain A K, Dubuisson-Jolly M. Object tracking using deformable teplates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(5):544-549.
[Zhang06a]ZHANG Juan, MAO Xiao-bo, CHEN Tie-jun. Survey of moving object tracking algorithm[J]. Application Research of Computers,2006, 26(12):4407-4410.
[Zhang06b]ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object tracking algorithm based on CamShift [J]. Computer Engineering and Design,2006,27(11):108-110.
[Zhang08]ZHANG Hai-qing, LI Hou-qiang. Object Tracking Through Multiple Cues [J]. Journal of Image and Graphics,2008,13(11):2187-2196.
[Zhou 04]Zhou S K,Chellappa R,Moghaddan B. Visual tracking and recognition using appearance-adaptive medels in Particle filters[J]. IEEE Transactions on Image Proeessing,2004,13(11):1491-1506.
[Zhu00]Zhu Z, Xu G, Yang B, et al. VISATRAM: A real-time vision system for automatic traffic monitoring[J]. Image and Vision Computing,2000,18(10): 781-794.
[博睿视11]北京博睿视科技有限责任公司[Online].http://www.bravevideo.com/. 2011-9-12.
[昌娅01]昌娅,胡卫明,谭铁牛.交通视觉监控系统中的三维车辆线框模型可视化算法[A].中国工程图学学会会议集[C],中国工程图学学会,2001.
[代科学06]代科学,李国辉,涂丹等.监控视频运动目标检测减背景技术的研究现状和展望[J].中国图象图形学报,2006,vol.11(7)：919-927.
[冯蓓蓓09]冯蓓蓓.运动目标检测系统的设计与实现[D].大连理工大学硕士论文,2009.
[冈萨雷斯04]冈萨雷斯.数字图像处理[M].电子工业出版社,2004.
[郝菲09]郝菲.智能监控系统中运动目标检测跟踪的研究[D].北京交通大学硕士论文,2009.
[宏电11]深圳市宏电技术股份有限公司[Online]. http://www.hongdian.com. 2011-9-12.
[侯志强06]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,vo132(4)：603-617.
[胡学友11]胡学友,陶亮,倪敏生.基于混合粒子滤波的目标跟踪[J].计算机应用.2011,31(6)：1602-1604+1608.
[华亿11]苏州华亿安防科技有限公司[Online], http://www.cnivs.com/. 2011-9-12.
[黄超群10]黄超群.基于混合高斯模型和Kalman滤波器的运动目标检测与跟踪[D].云南大学硕士学位论文,2010.
[贾桂敏08]贾桂敏.基于物体局部信息的跟踪算法研究[D].天津大学硕士论文,2008.
[乐应英10]乐应英.智能视频监控系统中目标检测与跟踪关键技术研究[D].云南大学硕士学位论文,2010.
[雷雨权04]雷雨权.多媒体电视监控与报警系统[M].北京：国防工业出版社2004.1.
[李爽07]李爽.运动目标识别和跟踪的智能化视频监控系统研究[D].辽宁工学院硕士学位论文,2007.
[刘光宇09]刘光宇,刘国栋.基于混合高斯模型的运动目标检测方法[J].计算机工程与应用,2009,vo1.45(24)：180-182.
[刘瑞祯07]刘瑞祯,于仕琪OpenCV教程-基础篇[M].北京：北京航空航天大学出版社,2007.
[刘雪07]刘雪.研究运动目标检测与跟踪技术[D].山东大学硕士学位论文,2007.
[刘一山07]刘一山.智能监控系统中运动目标检测与跟踪技术的研究[D].西安科技大学硕士学位论文,2007.
[楼建光02]楼建光,柳崎峰,胡卫明,谭铁牛.交通视觉监控中的摄像机参数求解[J].计算机学报,2002,(11)：1269-1273.
[楼建光03]楼建光,柳崎峰,谭铁牛,胡卫明.基于三维模型的交通场景视觉监控(英文)[J].自动化学报,2003,(3)：434-449
[卢璇10]卢璇,雷航,郝宗波.联合多特征的自动CamShift跟踪算法[J].计算机应用,2010,30(3)：650-652.
[孟凤07]孟凤.视频监控系统中运动目标检测与跟踪算法的研究[D].燕山大学硕士学位论文,2007.
[谭铁牛09a]谭铁牛,黄凯奇,王莹.基于轮廓的异常行为识别方法[Z].CN101464952,2009.
[谭铁牛09b]谭铁牛,黄凯奇,张兆翔,李敏.一种基于运动目标表象和运动信息的摄像机自标定方法[Z].CN101488222,2009.
[田原01]田原,谭铁牛,孙洪赞,胡卫明.一种能处理部分遮挡的鲁棒性实时跟踪方法[A].中国工程图学学会会议集[C],中国工程图学学会,2001.
[田原02]田原,谭铁牛,孙洪赞.一种具有良好鲁棒性的实时跟踪方法[J].自动化学报,2002,(5)：851-853.
[王亮02]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,(3)：225-237.
[王绍钰08]王绍钰.基于粒子滤波器的运动目标跟踪方法研究[D].中南大学硕士论文,2008.
[王新余04]王新余,张桂林.基于光流的运动目标实时检测方法研究[J].计算机工程与应用,2004(1)：43-46.
[工耀南03]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京：高等教育出版社,2003.
[文灏07]文灏,陈红涛.基于减背景与对称差分的运动目标检测[J].微计算机信息,2007,23(9-1)：99-101.
[徐慧04]徐慧VisuaIC++数字图像实用工程案例精选[M].北京：人民邮电出版社,2004.
[徐剑09]徐剑,丁晓青,王生进等.一种融合局部纹理和颜色信息的背景减除方法[J].自动化学报,2009,vo1.35(9)：1145-1150.
[张海清07]张海清.计算机智能视频监控系统的目标运动检测和跟踪研究[D].中国科学技术大学,2007.
[章毓晋00]章毓晋.图像理解与计算机视觉[M].北京：清华大学出版社,2000
[赵俊07]赵俊.智能视频监控系统关键技术研究[D].西安电子科技大学硕士论文,2007.
[智安邦11]北京智安邦科技有限公司.安防智能视频监控系统[Online]. http://www.zanb.com.cn/.2011-9-12.
[周西汉05]周西汉,刘勃,周荷琴.一种基于对称差分和背景消减的运动检测方法[J].计算机仿真,2005,22(4)：117-119.