视频序列中目标跟踪技术研究
|
摘要
视频目标跟踪研究是视觉领域的一个重要课题，受到国内外学者的普遍关注，具有广泛的应用前景。本论文致力于视频序列中目标跟踪技术的研究，创新点有以下几个方面：
1．针对传统质心位移算法使用单一颜色直方图作为特征描述目标，在跟踪时不能很好地适应目标在相邻帧间移动缓慢和目标与邻域颜色特征相似的情况。本文提出了基于核密度估计相关度量的目标跟踪方法，对参考目标模板和当前帧目标模板进行描述时，在诸如颜色、梯度等目标像点的特征区间内融入了目标像点的空间位置信息。与基于单一颜色直方图所得Bhattacharyya系数比较，本文提出的核密度相关度量的收敛梯度更陡，算法进行目标跟踪时速度更快更稳健，对目标跟踪的位置更加精确。
2．提出了基于高斯混合模型的类EM跟踪方法。算法选用GMM对目标区域内的像点参数建模，以多个高斯分布函数的加权和来逼近目标像点的二维空间位置分布概率函数。同时，将模型中的各个高斯函数的权值与基于颜色特征的目标相似度量联系起来，将目标跟踪问题转化为视频帧之间目标参数的EM估计。每次迭代中，估计目标位置的同时可以得到目标大小的协方差矩阵参数，有效地解决了目标区域的自适应。
3．质心位移算法具有简单快速的优点，但是在目标局部或全部被遮挡的情况下，往往无法得到满意的跟踪效果；与此同时，粒子滤波算法虽具有抗遮挡的优点，但计算过程中需要大量的粒子样本来近似描述目标的状态，使得算法非常费时。混合跟踪算法引入自适应粒子样本数选择的采样策略，保证跟踪精度同时减少了跟踪总体时间花费，有效提高了系统的实时性，更好满足工程实用。
4．多目标视觉目标跟踪相比于单目标跟踪问题，充满了背景嘈杂、目标与目标之间以及目标与背景之间遮挡等许多不确定因素，故而面临着更多困难。本文提出了基于颜色分布的联合多目标概率分布粒子滤波器，以运动学先验概率作为重要性概率密度函数，根据粒子样本中代表不同目标的划分之间的欧式距离判定划分之间是否关联，并据此在独立划分和关联划分两种粒子滤波器之间进行切换。仿真和实际实验证明，该滤波器能够同时有效地对多个目标进行跟踪。
Tracking visual objects in image sequences is an important topic in the field ofcomputer vision. This problem has received wide attention and it has a wide range ofapplication in different fields. In this dissertation, we discuss the problem of objecttracking in image sequences. The innovative points of the dissertation can be listed asfollows.
In the traditional mean shift algorithm, only the color histogram is used fordescribing the feature of an object. The dissimilarity among the reference targets andthe target candidates is expressed by the metric derived from the Bhattacharyyacoefficients. The traditional mean shift procedure is used to find the real location ofthe object through looking for the regional minimum of the distance functioniteratively. However, in the case if the object moves slowly from frame to frame in theconsecutive image sequence or if the color histogram of the target is similar to thecolor histogram of the neighborhood, the algorithm does not work well. To overcomethe difficulty, a concept on the correlation of kernel density estimation of trackingregion and a new generalized distance is proposed. Experiments manifest thataccuracy and robustness of the tracking algorithm can be improved.
We suggest an EM-like algorithm for object tracking based on the Gaussianmixture model (GMM). The algorithm uses the weighted summation of several Gaussfunctions to approach the probability function of position's distribution in twodimensional space. In the meanwhile, the GMM is related with the similarity measureof targets on the basis of their color features. Then, by converting the object trackingalgorithm into the EM estimation of object's parameters from frame to frame, the algorithm estimates the location of the object and updates the variance matrix,simultaneously, in each iterative step. Compared with the traditional Mean shiftalgorithm, the new algorithm presented in this paper can track the object more rapidlyand accurately, and update the object window adaptively.
The traditional mean shift method does not work well when the target gets anocclusion. The tracking algorithm on the basis of particle filtering has the ability tooverpass the occlusion. Unfortunately, its performance relies heavily on the number ofthe used particles. This involves a large number of computations and therefore isdifficult to be implemented in real time. To settle the problem, this article brings abouta hybrid algorithm by combining the mean shift and the particle filter trackingtechnique on the basis of the color histogram distribution. By adopting the strategythat the number of particles is adaptively determined, it amalgamates the virtues of thetwo techniques. As a result, the computational cost can be reduced and the trackingperformance can be ensured simultaneously. The experimental results show that theproposed method is effective and robust.
This article proposes the joint multi-target probability density particle filteringbased on the color distribution to address the problem of tracking multiple movingtargets with difficult conditions such as target crossing, target occlusion andbackground confusion. Here we use the kinematic prior as the importance probabilityfunction. Through comparing the Euclidian distance of the partitions that denotingdifferent targets, we can switch the procedure from the coupled partition particlefiltering to the independent partition particle filtering and inversely. The simulationand experimental results show that the proposed algorithm can track multiple objectseffectively.
1．针对传统质心位移算法使用单一颜色直方图作为特征描述目标，在跟踪时不能很好地适应目标在相邻帧间移动缓慢和目标与邻域颜色特征相似的情况。本文提出了基于核密度估计相关度量的目标跟踪方法，对参考目标模板和当前帧目标模板进行描述时，在诸如颜色、梯度等目标像点的特征区间内融入了目标像点的空间位置信息。与基于单一颜色直方图所得Bhattacharyya系数比较，本文提出的核密度相关度量的收敛梯度更陡，算法进行目标跟踪时速度更快更稳健，对目标跟踪的位置更加精确。
2．提出了基于高斯混合模型的类EM跟踪方法。算法选用GMM对目标区域内的像点参数建模，以多个高斯分布函数的加权和来逼近目标像点的二维空间位置分布概率函数。同时，将模型中的各个高斯函数的权值与基于颜色特征的目标相似度量联系起来，将目标跟踪问题转化为视频帧之间目标参数的EM估计。每次迭代中，估计目标位置的同时可以得到目标大小的协方差矩阵参数，有效地解决了目标区域的自适应。
3．质心位移算法具有简单快速的优点，但是在目标局部或全部被遮挡的情况下，往往无法得到满意的跟踪效果；与此同时，粒子滤波算法虽具有抗遮挡的优点，但计算过程中需要大量的粒子样本来近似描述目标的状态，使得算法非常费时。混合跟踪算法引入自适应粒子样本数选择的采样策略，保证跟踪精度同时减少了跟踪总体时间花费，有效提高了系统的实时性，更好满足工程实用。
4．多目标视觉目标跟踪相比于单目标跟踪问题，充满了背景嘈杂、目标与目标之间以及目标与背景之间遮挡等许多不确定因素，故而面临着更多困难。本文提出了基于颜色分布的联合多目标概率分布粒子滤波器，以运动学先验概率作为重要性概率密度函数，根据粒子样本中代表不同目标的划分之间的欧式距离判定划分之间是否关联，并据此在独立划分和关联划分两种粒子滤波器之间进行切换。仿真和实际实验证明，该滤波器能够同时有效地对多个目标进行跟踪。
Tracking visual objects in image sequences is an important topic in the field ofcomputer vision. This problem has received wide attention and it has a wide range ofapplication in different fields. In this dissertation, we discuss the problem of objecttracking in image sequences. The innovative points of the dissertation can be listed asfollows.
In the traditional mean shift algorithm, only the color histogram is used fordescribing the feature of an object. The dissimilarity among the reference targets andthe target candidates is expressed by the metric derived from the Bhattacharyyacoefficients. The traditional mean shift procedure is used to find the real location ofthe object through looking for the regional minimum of the distance functioniteratively. However, in the case if the object moves slowly from frame to frame in theconsecutive image sequence or if the color histogram of the target is similar to thecolor histogram of the neighborhood, the algorithm does not work well. To overcomethe difficulty, a concept on the correlation of kernel density estimation of trackingregion and a new generalized distance is proposed. Experiments manifest thataccuracy and robustness of the tracking algorithm can be improved.
We suggest an EM-like algorithm for object tracking based on the Gaussianmixture model (GMM). The algorithm uses the weighted summation of several Gaussfunctions to approach the probability function of position's distribution in twodimensional space. In the meanwhile, the GMM is related with the similarity measureof targets on the basis of their color features. Then, by converting the object trackingalgorithm into the EM estimation of object's parameters from frame to frame, the algorithm estimates the location of the object and updates the variance matrix,simultaneously, in each iterative step. Compared with the traditional Mean shiftalgorithm, the new algorithm presented in this paper can track the object more rapidlyand accurately, and update the object window adaptively.
The traditional mean shift method does not work well when the target gets anocclusion. The tracking algorithm on the basis of particle filtering has the ability tooverpass the occlusion. Unfortunately, its performance relies heavily on the number ofthe used particles. This involves a large number of computations and therefore isdifficult to be implemented in real time. To settle the problem, this article brings abouta hybrid algorithm by combining the mean shift and the particle filter trackingtechnique on the basis of the color histogram distribution. By adopting the strategythat the number of particles is adaptively determined, it amalgamates the virtues of thetwo techniques. As a result, the computational cost can be reduced and the trackingperformance can be ensured simultaneously. The experimental results show that theproposed method is effective and robust.
This article proposes the joint multi-target probability density particle filteringbased on the color distribution to address the problem of tracking multiple movingtargets with difficult conditions such as target crossing, target occlusion andbackground confusion. Here we use the kinematic prior as the importance probabilityfunction. Through comparing the Euclidian distance of the partitions that denotingdifferent targets, we can switch the procedure from the coupled partition particlefiltering to the independent partition particle filtering and inversely. The simulationand experimental results show that the proposed algorithm can track multiple objectseffectively.
引文
[1] Haritaoglu I, Harwood D., Davis L. W4: Real-time surveillance of people and their activities. IEEE Transac tionson Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
[2] Pavlidis I., Morellas V., Tsiamyrtzis P., Harp S. Urban surveillance system: From the laboratory to the com mercial world. Proceedings of the IEEE, 2001, 89(10): 1478-1497
[3] Magee D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing, 22: 143-155, 2004.
[4] Koller D, Daniilidis K, Nagel H. Model-based object tracking in monocular image sequences of road traffic scene. International Journal of Computer Vision, 1993, 10(3): 257-281
[5] Dubuisson Jolly M., Lakshmanan S., Jain A. K. Vehicle segmentation and classification using deformable templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(3): 293-308
[6] Zhu Z., Xu G., Yang B, Shi D., Lin X. VISATRAM: A real-time vision system for automatic traffic monitoring. Image and Vision Comp., 2000, 18(10): 781-794
[7] Haag M., Nagel H.Tracking of complex driving maneuversin traffic image sequences. Image and Vision Computing, 1998, 16(8): 517-527
[8] Pai C, Tyan H, Liang Y, Liao H M, Chen S. Pedestrian detection and tracking at crossroads. Pattern Recognition, 2004, 37(5): 1025-1034
[9] Masoud O., Papani kolopoulos N P. A novel method for tracking and counting pedestrians in real-time using a single camera. IEEE Transactions on Vehicular Technology, 2001, 50(5): 1267-1278
[10] Foresti G.L., Murino V., Regazzoni C. Vehicle recognition and tracking from road image sequences. IEEE Transactions on Vehicular Technology, 1999, 48(1): 301-318
[11] Betke M., Haritaoglu E., Davis L. S. Real-time multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Applications, 2000, 12(2): 69-83
[12] Ferryman J.M., Maybank S.J., Worrall A.D. Visual surveillance for moving vehicle. International Journal of Computer vision, 2000, 37(2): 187-197
[13] Li Y., S Ma. and Lu H.Human posture recognition using multi scale morpho-logical method and Kalman motion estimation. In: Proc IEEE International Conference on Pattern Recognition, Brisbane, Australia, 1998, 175-177.
[14] Cui Y. and Weng J. Hand segmentation using learning-based prediction and verification for hand sign recognition. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, 1997, 88-93.
[15] Turk M. Visual interaction with life-like characters.In: Proc IEEE International Conference on Automatic Face and Gesture Recognition, Killington, Vermont USA, 1996, 368-373.
[16] Lakany H., Haycs G, Hazlewood M and Hillman S. Human walking: tracking and analysis. In: Proc IEEE Colloquium on Motion Analysis and Tracking, Savoy Place, London, 1999, 5/1-5/14.
[17] Kohle M, Merkl D. and Kastner J. Clinical gait analysis by neural networks: issues and experiences. In: Proc IEEE Symposium on Computer-Based Medical Systems, Maribor, Slovenia, 1997, 138-143.
[18] Tieu K., Viola P. Boosting image retrieval. International Journal of Computer Vision, 2004, 56(1/2/3): 17-36.
[19] Fablet R., Bouthemy P. Non-parametric motion activity analysis for statistical retrieval with partial query. Journal of Mathematical Imaging and Vision, 2001, 14(3): 257-270.
[20] 候志强，韩崇昭．视频跟踪技术综述．自动化学报，第32卷第4期，603-617．
[1] Yilmaz A., Javed O., Shah M. Object tracking: A Survey. ACM Computing Surveys, Vol. 38, No. 4, Article 13, Publication date: December 2006.
[2] Veenman C., Reinders M., and Backer E. Resolving motion correspondence for densely moving points. IEEE Transaction. Pattern Analysis Mach. Intell. 23, 1, 54-72, 2001.
[3] Comaniciu D., Ramesh V., and Meer P. Kernel-based object tracking. IEEE Trans. Pattern Analysis Mach. Intell. 25, 564-575., 2003.
[4] Yilmaz A., Li X., and Shah M. Contour based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans. Pattern Analysis Mace Intell. 26, 11, 1531-1536, 2004.
[5] Cootes T., Edwards G., and Taylor C. Robust real-time periodic motion detection, analysis, and applications. IEEE Trans. Pattern Analysis Mace Intell. 23, 6, 681-685, 2001.
[6] Zhu S., and Yuille A. Region competition: unifying snakes, region growing, and bayes/mdl for multi-band image segmentation. IEEE Trans. Patt. Analy. Mach. Intell. 18, 9, 884-900, 1996.
[7] Paragios N., and Deriche R. Geodesic active regions and level set methods for supervised texture segmentation. Int. J. Comput. Vision 46, 3, 223-247, 2002.
[8] Elgammal A., Duraiswami R., Harwood D., and Davis L. Background and foreground modeling using nonparametrie kernel density estimation for visual surveillance. Proceedings of IEEE 90, 7, 1151-1163, 2002.
[9] Fieguth P., and Terzopoulos D.Color-based tracking of heads and other mobile objects at video flame rates. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 21-27, 1997.
[10] Edwards G., Taylor C., and Cootes T. Interpreting face images using active appearance models. In International Conference on Face and Gesture Recognition. 300-305, 1998.
[11] Haritaoglu I., Harwood D., Davis L. W4: Real-time surveillance of people and their activities. IEEETransac-tionson Pattern Analysis and Machine Intelligence, 2000, 22(8): 809830
[12] Canny J. A computational approach to edge detection. IEEE Trans. Patt. Analy. Math. Intell. 8, 6, 679-698, 1986.
[13] Horn B., and Schunk B. Determining optical flow.Artific. Intell. 17, 185-203, 1981.
[14] Lucas B. D., and Kanade T. An iterative image registration technique with an application to stereo vision. In International Joint Conference on Artificial Intelligence, 1981.
[15] Black M., and Anandan P. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput. Vision Image Understand. 63, 1, 75-104, 1996.
[16] Szeliski R., and Coughlan J. Spline-based image registration. Int. J. Comput. Vision 16, 1-3, 185-203., 1997.
[17] 候志强，韩崇昭．视频跟踪技术综述．自动化学报，第32卷第4期，603-617．
[18] Wren C R, Azarbayejani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785
[19] Coifman B, Beymer D, Mclauchlan P, Malik J. A real-time computer vision system for vehicle tracking and traffic surveillance. Transportation Research PartC, 1998, 6(4): 271-288
[20] Magee D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing, 2004, 22(2): 143-155
[21] Pai C, Tyan H., Liang Y., Liao H. M., Chen S. Pedestrian detection and tracking at cross roads. Pattern Recognition, 2004, 37(5): 1025-1034
[22] Masoud O., Papanikolopoulos N P. A novel method for tracking and counting pedestrians in real-time using a single camera. IEEE Transactions on Vehicular Technology, 2001, 50(5): 1267-1278
[23] Wachter S., Nagel H. Tracking persons in monocular image sequences. Computer Vision and Image Under-standing, 1999, 74(3): 174-192
[24] Pavlidis I., Morellas V., Tsiamyrtzis P., Harp S. Urban surveillance system: From the laboratory to the com-mercial world. Proceedings of the IEEE, 2001, 89(10): 1478-1497
[25] Collins R., Lipton A., Ftiiyoshi H., Kanade T. Algorithms for cooperative multi sensor surveillance. Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[26] Matsuyama T., Ukita N. Real-time multi target tracking by a cooperative distributed vision system. Proceedings of the IEEE, 2002, 90(7): 1136-1150
[27] Zhnng W J., Qi F H., Jiang ZJ. A practiceal method for detecting and tracking objects in image sequences in a real-time video surveillance and monitoring system. Chinese Journal of Shanghai Jiao tong University, 2002, 36(12): 1837-1840
[28] Boult T E., Micheals R J., Gao X., Eckmann M. Into the woods: Visual surveillance of noncooperative and camou flaged targets in complex outdoor settings. Proceedings of the IEEE, 2001, 89(10): 1382-1402.
[29] Zhn Z., Xu G., Yang B., Shi D., Lin X. VISATRAM: A real-time vision system for automatic traffic monitoring. Image and Vision omputing, 2000, 18(10): 781-794.
[30] Meier T., Ngan K N. Automatic segmentation of moving objects for video object plane generation. IEEE Transactionson Circuits and Systems for Video Technology, 1998, 8(5): 525-538
[31] Wang D. Unsupervised video segmentation based on watershed sand temporal tracking. IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5): 539-546
[32] Zhao T., Nevatia R. Tracking multiple humans in complex situations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1208-1221.
[33] Yu T., Wu Y. Collaborative tracking of multiple targets. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR'04, Washington, DC, USA: IEEEPress, 2004. 1: 834-841.
[34] Mc Kenna S., Jabri S., Duric Z., Rosenfeld A., Wechsler H. Tracking groups of people. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[35] Koller D., Daniilidis K., Nagel H. Model-based object tracking in monocular image sequences of road traffic scene. International Journal of Computer Vision, 1993, 10(3): 257-281.
[36] Jurie F. Tracking objects with a recognition algorithm. Pattern Recognition Letters, 1998, 19(3-4): 331-340.
[37] Drummond T., Cipolla R. Real-time visual tracking of complex structures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(7):932-946
[38]Leymarie F.,LevineM D. Tracking deformable objects in the plane using an active contour model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993,15(6): 617-624.
[39] Jain A K., Zhong Y., Dubuisson-Jolly M. Deformable template models: A review. Signal Processing, 1998, 71(2): 109-129.
[40]Remondino F. 3-D reconstruction of static human body shape from image sequence. Computer Vision and Image Understanding, 2004, 93(1):65-85.
[41]Gavrila D M. The visual analysis of human movement: Asurvey.Computer Vision and Image Understanding, 1999,73(l):82-98.
[42]Delamarre Q., Faugeras O. 3D articulated model sand multi view tracking with physical forces. Computer Vision and Image Understanding, 2001,81(3):328-357.
[43]Plankers R., Pus P. Tracking and modeling people in video sequences. Computer Vision and Image Understanding, 2001,81(3):285-302.
[44]Marr D. Vision: a computational investigation into the human representation and processing of visual information, Freeman W.H. and Company, SanFrancisco,1982.
[45] Wang S., Ai H Z, He K.Z , Difference-image-based multiple motion targets detection and tracking.Chinese Journal of Image and Graphics, 1999,4 A(6):470-475
[46]Hou Z Q., Han C Z. A background reconstruction algorithm based on pixel intensity classification. Chinese Journal of Software, 2005,16(9): 1568-1576.
[47] Bar-ShalomY, Fortmann T. Tracking and Data Association, Academic Press, 1988.
[48] Oliver N M., Rosario B., Pentland A P. A Bayesian computer vision system for modeling human interactions IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):831-843
[49] Frederic D.,Jean-Pierre L C. Spatio-temporal multi-mode information management for moving target detection [J]. Information Fusion. 2004,5(3):169-178
[50]Bascle B. and Deriche PR. Region tracking through image sequences[J].Proc, IEEE int.ConfComputerVision,1995:302-307
[51] Allen T.G., Luengen M.R., Wills A.S. Multi-scale approaches to moving target detection in image sequences [J].Optical Engineering, 1994,33(7):2248-2254
[52]Stringa E. and Regazzoni C.S.Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing, 2000, 9(1): 69-79
[53] Stauffer C., Eric W., Grimson L.. Leaming patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757.
[54] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis. In: Proc IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78-81.
[55] Barton J., Fleet D., and Beauchemin S. Performance of optical flow techniques. International Journal of Computer Vision, 1994, 12 (1): 42-77.
[56] MuratTekalp A．，数字视频处理[M]，电子工业出版社，1998
[57] Schweitzer H., Bell J., and Wu F.Very fast template matching. In European Conference on Computer Vision (ECCV). 358-372, 2002.
[58] Jepson A., Fleet D., and Elmaraghi T. Robust on-line appearance models for visual tracking. IEEE Trans. Patt. Analy. Mach. Intell. 25, 10, 1296-1311, 2003.
[59] Tao H., and Kumar R.Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. Patt. Analy. Mach. Intell. 24, 1, 75-89, 2002.
[60] Isard M. and Maccormick J. Bramble: A bayesian multiple-blob tracker. In IEEE International Conference on Computer Vision (ICCV). 34-41, 2001.
[61] Broida T., and Chellappa R. Estimation of object motion parameters from noisy images.IEEE Trans. Patt. Analy. Mach. Intell. 8, 1, 90-99, 1986.
[62] Beymer D. and Konolige K. Real-time tracking of multiple people using continuous detection. In IEEE Int. Conf. on Computer Vision Frame-Rate Workshop., 1999
[63] Bar-Shalom Y. and Foreman T. Tracking and Data Association. Academic Press Inc, 1988.
[64] Mackay D.J.C. Introduction to Monte Carlo methods. In Learning in Graphical Models, M.I.Jordan, Ed. N.Science Series. Kluwer Academic Press, 175-204, 1998.
[65] Isard M., and Blake A. Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vision 29, 1, 5-28, 1998.
[66] Isard M., Blake A. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. In European Conf. on Computer Vision[C]. Freiburgim Breisgau: Springer-Verlag, 1998, vol (1), 893-908
[67] MacCormick J.,Blake A.A probabilistic exclusion principle for tracking multiple objects. International Journal of Computer Vision,2000,39(1):57-71.
[68] Nummiaro K., Koller-Meier E.,andGool L.V.An adaptive color-based particle filter. Image and Vision Computing, 2003,21(1): 99-110.
[69] 薛建儒．视频序列跟踪的统计计算方法：[博士学位论文]西安交通大学，2003
[70] Isard M., MacCormick J.Bramble:A Bayesian multiple-blob tracker. In IEEE Int. Conf. Computer Vision. Vancouver, British Columbia, Canada: IEEE Computer Society, Los AlarnosCA.2001 .Pages34-41,volume2.
[71] MacCormick J., Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. In European Conf. on Computer Vision,2000.vol 1843 of Lecture Notes Computer Science[C].Springer-Verlag,2000.Pages3-19.
[72] P'erez P., Hue C., Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002.661-675.
[73] Hue C., LeCadre J., P'erez P.Sequential monte carlo methods for multiple target tracking and data fusion. IEEE Trans. on Signal Processing,2002,50(2):309-325
[74] Chang Y.L. and Aggarwal J. K. 3D structure reconstruction from an ego motion sequence using statistical estimation and detection theory. In Workshop on Visual Motion. 268-273,1991.
[75] Rasmussen C.,Hager G.Probabilistic data association methods for tracking complex visual objects. IEEE Trans. Part. Analy. Mach. Intell. 23, 6, 560-576,2001.
[76] Streit R.L.,Luginbuhl T.E. Maximum likelihood method for probabilistic multi-hypothesis tracking. In Proceedings of the International Society for Optical Engineering (SPIE.)vol. 2235. 394-405,1994.
[77] Huttenlocher D., Noh J., and Rucklidge W. Tracking nonrigid objects in complex scenes. In IEEE International Conf. on Computer Vision (ICCV). 93-101,1993.
[78] Li B., Chellappa R., Zheng Q., and Der S. Model-based temporal object verification using video. IEEE Trans. Image Process. 10, 6, 897-908,2001.
[79] Kang J.,Cohen I.,and Medioni G. Object reacquisition using geometric invariant appearance model. In Int. Conf. on Pattern Recongnition (ICPR). 759-762,2004.
[80] Kass M., Witkin A., Terzopoulos D. Snakes: Active contour models. International Journal of Computer Vision, 1988, 1(4): 321-331
[81] Terzopoulos D., Szelisld R. Tracking with Kalman Snakes, in Active Vision, Blake A. and Yuille A, Eds. Cambridge, MA: MIT Press, 1992. 3-20.
[82] Vieren C., Cabestaing F., Postaire J. Catching moving objects with snakes for motion tracking. Pattern Recognition Letters, 1995, 16(7): 679-685.
[83] Freedman D., Zhang T.Active Contours for tracking distributions. IEEE Transactions on Image Processing, 2004, 13(4): 518-526.
[84] Chen Y., Rui Y., and Huang T. Jpdaf based hmm for real-time contour tracking. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 543-550,2001.
[85] Dockstader S.,and Tekalp M. On the tracking of articulated and occluded video object motion. Real Time Image 7, 5, 415-432, 2001.
[86] Amaud E., Memin E. An efficient Rao-Blackwellized particle filter for object tracking. Image Processing, 2005. ICIP 2005. IEEE International, 2005.
[87] Chang Ch., Ansari R., Khokhar A. Multiple object tracking with kernel particle filter. Prec. of the 2005 IEEE Comp. Society Conf. on Comp. Vision and Patt. Recognition, 2005.
[88] Cavallaro A.,Steiger O.,Ebrahimi T. Tracking video objects in cluttered background. IEEE Transactions on circuits and system for video technology, Vol.15, 2005.
[89] Yoon Y., Kosaka A., Jae Byung Park and Avinash C. Kak. A new approach to the use of edge Extremities for model-based object Tracking. Proceedings of the 2005 IEEE international conference on robotics and automation,Bacerola,2005.
[1] Fukunage K. and L.D. Hostetler, The estimation of the gradient of a density function with application in pattern recognition. IEEE Trans. Information Theory, 1975.21(1): p.32-40
[2] Cheng Y. Z. Mean Shift, Mode Seeking, and Clustering [J]. IEEE Transactions on Patterns and Machine Intelligence. 1995, 8(17):790-799.
[3] Comaniciu D,Ramesh V, and Meer P. Real-time tracking of non-rigid using mean shift . In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[4] Collins R., Lipton A., Fujiyoshi H.,and Kanade T. Algorithms for Cooperative Multisensor Surveillance [C].Proc.IEEE,Vol,89,No. 10,pp. 1456-1477,2001.
[5] Bradski G.R., Computer Vision Face Tracking as a Component of a Perceptual User Interface[J]. Proc. IEEE Workshop Applications of Computer Vision,1998, (10):214-219.
[6] Comaniciu D., Ramesh V., Meet P. Kernel-Based Object Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2003,5(25): 564-577.
[7] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., May 2002, 24(5):603-619.
[8] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition ,2003, Vol 2. Baltimore: Victor Graphics, 234-240.
[9] Zivkovic Z., Krose Ben. An era-like algorithm for color-histogram-based object tracking. In proc IEEE Conf. Comp. Vision Pattem Recognition, Washington D.C., 2004(1):798-803
[10] Singh M., Arora H., Robust registration and tracking using kernel density correlation. Proc. 2004 Conf. Comp. Vision and Pattern Recognition, Washington, D.C., 2004,vol. 11: 174-174.
[11] Yang, C., Duraiswami, R., Gumerov, N., and Davis, L. 2003. Improved fast Gauss transform and efficient kernel density estimation. In IEEE Int. Conf. on Computer Vision. 464-471.
[12] 时永刚．广义距离度量和多模态图象匹配技术研究：[博士学位论文]北京：中国科学院电子学研究所，2003
[13] Rucldidge W J., Efficiently location objects using hausdorff distance[J]. International Janaual of Computer Vision, 1997; 24(3): 251-270
[14] Daesik Jang, Gye yong Kim. Model-based tracking of moving object[J]. Pattern Recognition, 1997: 30: 999-1008
[1] Comaniciu D,Ramesh V,and Meer P.Real-time tracking of non-rigid using mean shift. In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[2] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619 ,May 2002.
[3] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition, Vol 2. Baltimore: Victor Graphics, 234-240,2003.
[4] Hendrik P. Lopuha. Asynptotics of rewighted estimators of multivariate location and scatter. The Annals of Statistics ,1999, Vol. 27, No. 5, 1638-1665
[5] Zivkovic Z, Krose Ben. An EM-like algorithm for color-histogram-based object tracking. In: Proceedings of IEEE Compute Society Conf. on Computer Vision and Pattern Recognition, Washington, D.C.,USA:IEEE Press,2004.1:798～803
[6] Bilmes J.A. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Department of EE&CS,UC Berkeley, Tech. Rep.:TR-97-021,1998
[7] Lindeberg T.. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):77-116, 1998.
[8] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G].in:Learning in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[9] 邹谋炎．反卷积和信号复原．北京：国防工业出版社，2001．
[10] Birchfield S. Elliptical Head Tracking using intensity gradients and color histogram. IEEE Conf. on Comp. Vis and Pat. Rec., Santa Barara,232-237,1998.
[1] Comaniciu D,Ramesh V,and Meer P.Real-time tracking of non-rigid using mean shift. In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[2] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619 ,May 2002.
[3] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition, Vol 2. Baltimore: Victor Graphics, 234-240,2003.
[4] Isard M,Blake A. Condensation-conditional density propagation for visual tracking|J]. International Journal of computer vision, 1998,29(1 ):5-28.
[5] Katja Nummiaro,Esther Koller-Meier and Luc Van Gool. An adaptive color-based particle filter [J]. Image and vision computing 2003,21(1):99-110.
[6] Cheng Jian,Zhou Yue, Cai Nian,Yang Jie. Infrared object tracking based on particle filters[J]. Infrared Millim. Waves(程建，周越，蔡念，杨杰．基于粒子滤波的红外目标跟踪．红外与毫米波学报，)，2006，Vol．25(2)：113-117．
[7] Doucet A., Freitas J. de, Gordon N. Sequential Monte Carlo methods in practice. New-York: Springer-Verlag[M].2001
[8] Doucet A., Godsill S., Andrieu. On sequential Monte Carlo sampling methods for Bayesian filtering|J]. Statist. Computer, 2000, 10: 197-208.
[9] Arulampalam S. and Ristic B. Comparison of the particle filter with range parameterised and modeified polar EKF's for angle-only tracking|J]. Signal and Data Processing of Small Targets,SPIE,2000,4048: 288-299
[10] Gordon N., Salmon D. and Smith A. A novel approach to nonlinear/nonGaussian Bayesian State estimation. IEEE Proceedings on Radar and Signal Processing, 1993, 140(2): 107-113.
[11] Lindeberg T.. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):77-116,1998.
[12] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G]. In:Learning in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[13] Jepson A.D. ,Fleet D.J. Robust online appearance models for visual tracking ,Proceedings of the International Conference on Computer Vision and Pattern Recognition,Vol I, pp415-422 ,2001.
[14] P'erez P., Hue C, Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002. 661-675.
[15] Nummiaro K., Koller-Meier E. ,Van Gool L. Color features for tracking non-rigid objects ,ACTA Automatica Sinica, 2003.
[16] Strom J., Jebara T. ,Bau S., Pentland A. Real time tracking and modeling of faces: an EKF-based analysis by synthesis approach ,in : Proceedins of the Modelling People Workshop at ICCV ,1999.
[17] Ristic B.,Arulampalam S.,Gordon N. Beyond the kahnan filter ,particle filter for tracking application.Artech House ,B°ston ,London ,2004.
[1] Bar-Shalom,Y.,andBlair, W.D. Multitarget-Multisensor Tracking: Applications and Advances, Vol. Ⅲ. Norwood, MA: ArtechHouse, 2000.
[2] Bar-Shalom,Y. Multitarget Multisensor Tracking: Advanced Applications. Norwood, MA: ArtechHouse, 1990.
[3] Cox I J., Hingorani S L. An efficient implementation of reid's multiple hypotheses tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(2): 138～150
[4] Fortmann T E, Bar-Shalom Y, Scheffe M. Sonar tracking of multiple targets using joint probabilistic data association. IEEE Journal Oceanic Eng, 1983, OE-8: 173～184
[5] Gordon,N.J.,Salmond,D.J.,andSmith,A.F.M. A novel approach to non-linear and non-Gaussian Bayesian state estimation. IEEE Proceedings on Radar and Signal Processing, 140(1993),107—113.
[6] Kastella K. Discrimination gain for sensor management in multitarget detection and tracking. In IEEE-SMC and IMACS Multiconference CESA '96,vol.1 ,Lille,France, July 9-12,1996,167-172
[7] Hue, C., LeCadre,J-P.,andPerez,P. Tracking multiple objects with particle filtering. IEEE Transactions on Aerospace and Electronic Systems, 38,3(2002),791—812.
[8] Kreucher C., Kastella K., Hero A. Multi-target tracking using Joint Multitarget Probability Density. IEEE Transactions on aerospace and electronic system. Vol 41, No. 4,OCTOBER2005:1396-1414.
[9] Isard M.,and Blake A. Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vision 29, 1, 5-28,1998.
[10] Isard M.,Blake A. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. In European Conf. on Computer Vision[C]. Freiburgim Breisgau: Springer-Verlag,1998, vol (1), 893-908
[11] MacCormick J.,Blake A.A probabilistic exclusion principle for tracking multiple objects. International Journal of Computer Vision,2000,39(1):57-71.
[12] Nummiaro K., Koller-Meier E.,andGool L.V.An adaptive color-based particle filter. Image and Vision Computing, 2003,21(1): 99-110.
[13] 薛建儒．视频序列跟踪的统计计算方法：[博士学位论文]西安交通大学，2003
[14] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G].In:Leaming in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[15] Isard M., MaeCormick J.Bramble:A Bayesian multiple-blob tracker. In IEEE Int. Conf. Computer Vision. Vancouver, British Columbia, Canada: IEEE Computer Society, Los AlamosCA.2001.Pages34-41,volume2.
[16] MacCormick J., Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. In European Conf. on Computer Vision,2000.vol 1843 of Lecture Notes Computer Science[C].Springer-Verlag,2000.Pages3-19.
[17] P'erez P., Hue C., Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002. 661-675.
[18] Hue C., LeCadre J., P'erez P.Sequential monte carlo methods for multiple target tracking and data fusion. IEEE Trans. on Signal Processing,2002,50(2):309-325
[2] Pavlidis I., Morellas V., Tsiamyrtzis P., Harp S. Urban surveillance system: From the laboratory to the com mercial world. Proceedings of the IEEE, 2001, 89(10): 1478-1497
[3] Magee D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing, 22: 143-155, 2004.
[4] Koller D, Daniilidis K, Nagel H. Model-based object tracking in monocular image sequences of road traffic scene. International Journal of Computer Vision, 1993, 10(3): 257-281
[5] Dubuisson Jolly M., Lakshmanan S., Jain A. K. Vehicle segmentation and classification using deformable templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(3): 293-308
[6] Zhu Z., Xu G., Yang B, Shi D., Lin X. VISATRAM: A real-time vision system for automatic traffic monitoring. Image and Vision Comp., 2000, 18(10): 781-794
[7] Haag M., Nagel H.Tracking of complex driving maneuversin traffic image sequences. Image and Vision Computing, 1998, 16(8): 517-527
[8] Pai C, Tyan H, Liang Y, Liao H M, Chen S. Pedestrian detection and tracking at crossroads. Pattern Recognition, 2004, 37(5): 1025-1034
[9] Masoud O., Papani kolopoulos N P. A novel method for tracking and counting pedestrians in real-time using a single camera. IEEE Transactions on Vehicular Technology, 2001, 50(5): 1267-1278
[10] Foresti G.L., Murino V., Regazzoni C. Vehicle recognition and tracking from road image sequences. IEEE Transactions on Vehicular Technology, 1999, 48(1): 301-318
[11] Betke M., Haritaoglu E., Davis L. S. Real-time multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Applications, 2000, 12(2): 69-83
[12] Ferryman J.M., Maybank S.J., Worrall A.D. Visual surveillance for moving vehicle. International Journal of Computer vision, 2000, 37(2): 187-197
[13] Li Y., S Ma. and Lu H.Human posture recognition using multi scale morpho-logical method and Kalman motion estimation. In: Proc IEEE International Conference on Pattern Recognition, Brisbane, Australia, 1998, 175-177.
[14] Cui Y. and Weng J. Hand segmentation using learning-based prediction and verification for hand sign recognition. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, 1997, 88-93.
[15] Turk M. Visual interaction with life-like characters.In: Proc IEEE International Conference on Automatic Face and Gesture Recognition, Killington, Vermont USA, 1996, 368-373.
[16] Lakany H., Haycs G, Hazlewood M and Hillman S. Human walking: tracking and analysis. In: Proc IEEE Colloquium on Motion Analysis and Tracking, Savoy Place, London, 1999, 5/1-5/14.
[17] Kohle M, Merkl D. and Kastner J. Clinical gait analysis by neural networks: issues and experiences. In: Proc IEEE Symposium on Computer-Based Medical Systems, Maribor, Slovenia, 1997, 138-143.
[18] Tieu K., Viola P. Boosting image retrieval. International Journal of Computer Vision, 2004, 56(1/2/3): 17-36.
[19] Fablet R., Bouthemy P. Non-parametric motion activity analysis for statistical retrieval with partial query. Journal of Mathematical Imaging and Vision, 2001, 14(3): 257-270.
[20] 候志强，韩崇昭．视频跟踪技术综述．自动化学报，第32卷第4期，603-617．
[1] Yilmaz A., Javed O., Shah M. Object tracking: A Survey. ACM Computing Surveys, Vol. 38, No. 4, Article 13, Publication date: December 2006.
[2] Veenman C., Reinders M., and Backer E. Resolving motion correspondence for densely moving points. IEEE Transaction. Pattern Analysis Mach. Intell. 23, 1, 54-72, 2001.
[3] Comaniciu D., Ramesh V., and Meer P. Kernel-based object tracking. IEEE Trans. Pattern Analysis Mach. Intell. 25, 564-575., 2003.
[4] Yilmaz A., Li X., and Shah M. Contour based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans. Pattern Analysis Mace Intell. 26, 11, 1531-1536, 2004.
[5] Cootes T., Edwards G., and Taylor C. Robust real-time periodic motion detection, analysis, and applications. IEEE Trans. Pattern Analysis Mace Intell. 23, 6, 681-685, 2001.
[6] Zhu S., and Yuille A. Region competition: unifying snakes, region growing, and bayes/mdl for multi-band image segmentation. IEEE Trans. Patt. Analy. Mach. Intell. 18, 9, 884-900, 1996.
[7] Paragios N., and Deriche R. Geodesic active regions and level set methods for supervised texture segmentation. Int. J. Comput. Vision 46, 3, 223-247, 2002.
[8] Elgammal A., Duraiswami R., Harwood D., and Davis L. Background and foreground modeling using nonparametrie kernel density estimation for visual surveillance. Proceedings of IEEE 90, 7, 1151-1163, 2002.
[9] Fieguth P., and Terzopoulos D.Color-based tracking of heads and other mobile objects at video flame rates. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 21-27, 1997.
[10] Edwards G., Taylor C., and Cootes T. Interpreting face images using active appearance models. In International Conference on Face and Gesture Recognition. 300-305, 1998.
[11] Haritaoglu I., Harwood D., Davis L. W4: Real-time surveillance of people and their activities. IEEETransac-tionson Pattern Analysis and Machine Intelligence, 2000, 22(8): 809830
[12] Canny J. A computational approach to edge detection. IEEE Trans. Patt. Analy. Math. Intell. 8, 6, 679-698, 1986.
[13] Horn B., and Schunk B. Determining optical flow.Artific. Intell. 17, 185-203, 1981.
[14] Lucas B. D., and Kanade T. An iterative image registration technique with an application to stereo vision. In International Joint Conference on Artificial Intelligence, 1981.
[15] Black M., and Anandan P. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput. Vision Image Understand. 63, 1, 75-104, 1996.
[16] Szeliski R., and Coughlan J. Spline-based image registration. Int. J. Comput. Vision 16, 1-3, 185-203., 1997.
[17] 候志强，韩崇昭．视频跟踪技术综述．自动化学报，第32卷第4期，603-617．
[18] Wren C R, Azarbayejani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785
[19] Coifman B, Beymer D, Mclauchlan P, Malik J. A real-time computer vision system for vehicle tracking and traffic surveillance. Transportation Research PartC, 1998, 6(4): 271-288
[20] Magee D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing, 2004, 22(2): 143-155
[21] Pai C, Tyan H., Liang Y., Liao H. M., Chen S. Pedestrian detection and tracking at cross roads. Pattern Recognition, 2004, 37(5): 1025-1034
[22] Masoud O., Papanikolopoulos N P. A novel method for tracking and counting pedestrians in real-time using a single camera. IEEE Transactions on Vehicular Technology, 2001, 50(5): 1267-1278
[23] Wachter S., Nagel H. Tracking persons in monocular image sequences. Computer Vision and Image Under-standing, 1999, 74(3): 174-192
[24] Pavlidis I., Morellas V., Tsiamyrtzis P., Harp S. Urban surveillance system: From the laboratory to the com-mercial world. Proceedings of the IEEE, 2001, 89(10): 1478-1497
[25] Collins R., Lipton A., Ftiiyoshi H., Kanade T. Algorithms for cooperative multi sensor surveillance. Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[26] Matsuyama T., Ukita N. Real-time multi target tracking by a cooperative distributed vision system. Proceedings of the IEEE, 2002, 90(7): 1136-1150
[27] Zhnng W J., Qi F H., Jiang ZJ. A practiceal method for detecting and tracking objects in image sequences in a real-time video surveillance and monitoring system. Chinese Journal of Shanghai Jiao tong University, 2002, 36(12): 1837-1840
[28] Boult T E., Micheals R J., Gao X., Eckmann M. Into the woods: Visual surveillance of noncooperative and camou flaged targets in complex outdoor settings. Proceedings of the IEEE, 2001, 89(10): 1382-1402.
[29] Zhn Z., Xu G., Yang B., Shi D., Lin X. VISATRAM: A real-time vision system for automatic traffic monitoring. Image and Vision omputing, 2000, 18(10): 781-794.
[30] Meier T., Ngan K N. Automatic segmentation of moving objects for video object plane generation. IEEE Transactionson Circuits and Systems for Video Technology, 1998, 8(5): 525-538
[31] Wang D. Unsupervised video segmentation based on watershed sand temporal tracking. IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5): 539-546
[32] Zhao T., Nevatia R. Tracking multiple humans in complex situations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1208-1221.
[33] Yu T., Wu Y. Collaborative tracking of multiple targets. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR'04, Washington, DC, USA: IEEEPress, 2004. 1: 834-841.
[34] Mc Kenna S., Jabri S., Duric Z., Rosenfeld A., Wechsler H. Tracking groups of people. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[35] Koller D., Daniilidis K., Nagel H. Model-based object tracking in monocular image sequences of road traffic scene. International Journal of Computer Vision, 1993, 10(3): 257-281.
[36] Jurie F. Tracking objects with a recognition algorithm. Pattern Recognition Letters, 1998, 19(3-4): 331-340.
[37] Drummond T., Cipolla R. Real-time visual tracking of complex structures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(7):932-946
[38]Leymarie F.,LevineM D. Tracking deformable objects in the plane using an active contour model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993,15(6): 617-624.
[39] Jain A K., Zhong Y., Dubuisson-Jolly M. Deformable template models: A review. Signal Processing, 1998, 71(2): 109-129.
[40]Remondino F. 3-D reconstruction of static human body shape from image sequence. Computer Vision and Image Understanding, 2004, 93(1):65-85.
[41]Gavrila D M. The visual analysis of human movement: Asurvey.Computer Vision and Image Understanding, 1999,73(l):82-98.
[42]Delamarre Q., Faugeras O. 3D articulated model sand multi view tracking with physical forces. Computer Vision and Image Understanding, 2001,81(3):328-357.
[43]Plankers R., Pus P. Tracking and modeling people in video sequences. Computer Vision and Image Understanding, 2001,81(3):285-302.
[44]Marr D. Vision: a computational investigation into the human representation and processing of visual information, Freeman W.H. and Company, SanFrancisco,1982.
[45] Wang S., Ai H Z, He K.Z , Difference-image-based multiple motion targets detection and tracking.Chinese Journal of Image and Graphics, 1999,4 A(6):470-475
[46]Hou Z Q., Han C Z. A background reconstruction algorithm based on pixel intensity classification. Chinese Journal of Software, 2005,16(9): 1568-1576.
[47] Bar-ShalomY, Fortmann T. Tracking and Data Association, Academic Press, 1988.
[48] Oliver N M., Rosario B., Pentland A P. A Bayesian computer vision system for modeling human interactions IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):831-843
[49] Frederic D.,Jean-Pierre L C. Spatio-temporal multi-mode information management for moving target detection [J]. Information Fusion. 2004,5(3):169-178
[50]Bascle B. and Deriche PR. Region tracking through image sequences[J].Proc, IEEE int.ConfComputerVision,1995:302-307
[51] Allen T.G., Luengen M.R., Wills A.S. Multi-scale approaches to moving target detection in image sequences [J].Optical Engineering, 1994,33(7):2248-2254
[52]Stringa E. and Regazzoni C.S.Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing, 2000, 9(1): 69-79
[53] Stauffer C., Eric W., Grimson L.. Leaming patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757.
[54] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis. In: Proc IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78-81.
[55] Barton J., Fleet D., and Beauchemin S. Performance of optical flow techniques. International Journal of Computer Vision, 1994, 12 (1): 42-77.
[56] MuratTekalp A．，数字视频处理[M]，电子工业出版社，1998
[57] Schweitzer H., Bell J., and Wu F.Very fast template matching. In European Conference on Computer Vision (ECCV). 358-372, 2002.
[58] Jepson A., Fleet D., and Elmaraghi T. Robust on-line appearance models for visual tracking. IEEE Trans. Patt. Analy. Mach. Intell. 25, 10, 1296-1311, 2003.
[59] Tao H., and Kumar R.Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. Patt. Analy. Mach. Intell. 24, 1, 75-89, 2002.
[60] Isard M. and Maccormick J. Bramble: A bayesian multiple-blob tracker. In IEEE International Conference on Computer Vision (ICCV). 34-41, 2001.
[61] Broida T., and Chellappa R. Estimation of object motion parameters from noisy images.IEEE Trans. Patt. Analy. Mach. Intell. 8, 1, 90-99, 1986.
[62] Beymer D. and Konolige K. Real-time tracking of multiple people using continuous detection. In IEEE Int. Conf. on Computer Vision Frame-Rate Workshop., 1999
[63] Bar-Shalom Y. and Foreman T. Tracking and Data Association. Academic Press Inc, 1988.
[64] Mackay D.J.C. Introduction to Monte Carlo methods. In Learning in Graphical Models, M.I.Jordan, Ed. N.Science Series. Kluwer Academic Press, 175-204, 1998.
[65] Isard M., and Blake A. Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vision 29, 1, 5-28, 1998.
[66] Isard M., Blake A. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. In European Conf. on Computer Vision[C]. Freiburgim Breisgau: Springer-Verlag, 1998, vol (1), 893-908
[67] MacCormick J.,Blake A.A probabilistic exclusion principle for tracking multiple objects. International Journal of Computer Vision,2000,39(1):57-71.
[68] Nummiaro K., Koller-Meier E.,andGool L.V.An adaptive color-based particle filter. Image and Vision Computing, 2003,21(1): 99-110.
[69] 薛建儒．视频序列跟踪的统计计算方法：[博士学位论文]西安交通大学，2003
[70] Isard M., MacCormick J.Bramble:A Bayesian multiple-blob tracker. In IEEE Int. Conf. Computer Vision. Vancouver, British Columbia, Canada: IEEE Computer Society, Los AlarnosCA.2001 .Pages34-41,volume2.
[71] MacCormick J., Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. In European Conf. on Computer Vision,2000.vol 1843 of Lecture Notes Computer Science[C].Springer-Verlag,2000.Pages3-19.
[72] P'erez P., Hue C., Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002.661-675.
[73] Hue C., LeCadre J., P'erez P.Sequential monte carlo methods for multiple target tracking and data fusion. IEEE Trans. on Signal Processing,2002,50(2):309-325
[74] Chang Y.L. and Aggarwal J. K. 3D structure reconstruction from an ego motion sequence using statistical estimation and detection theory. In Workshop on Visual Motion. 268-273,1991.
[75] Rasmussen C.,Hager G.Probabilistic data association methods for tracking complex visual objects. IEEE Trans. Part. Analy. Mach. Intell. 23, 6, 560-576,2001.
[76] Streit R.L.,Luginbuhl T.E. Maximum likelihood method for probabilistic multi-hypothesis tracking. In Proceedings of the International Society for Optical Engineering (SPIE.)vol. 2235. 394-405,1994.
[77] Huttenlocher D., Noh J., and Rucklidge W. Tracking nonrigid objects in complex scenes. In IEEE International Conf. on Computer Vision (ICCV). 93-101,1993.
[78] Li B., Chellappa R., Zheng Q., and Der S. Model-based temporal object verification using video. IEEE Trans. Image Process. 10, 6, 897-908,2001.
[79] Kang J.,Cohen I.,and Medioni G. Object reacquisition using geometric invariant appearance model. In Int. Conf. on Pattern Recongnition (ICPR). 759-762,2004.
[80] Kass M., Witkin A., Terzopoulos D. Snakes: Active contour models. International Journal of Computer Vision, 1988, 1(4): 321-331
[81] Terzopoulos D., Szelisld R. Tracking with Kalman Snakes, in Active Vision, Blake A. and Yuille A, Eds. Cambridge, MA: MIT Press, 1992. 3-20.
[82] Vieren C., Cabestaing F., Postaire J. Catching moving objects with snakes for motion tracking. Pattern Recognition Letters, 1995, 16(7): 679-685.
[83] Freedman D., Zhang T.Active Contours for tracking distributions. IEEE Transactions on Image Processing, 2004, 13(4): 518-526.
[84] Chen Y., Rui Y., and Huang T. Jpdaf based hmm for real-time contour tracking. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 543-550,2001.
[85] Dockstader S.,and Tekalp M. On the tracking of articulated and occluded video object motion. Real Time Image 7, 5, 415-432, 2001.
[86] Amaud E., Memin E. An efficient Rao-Blackwellized particle filter for object tracking. Image Processing, 2005. ICIP 2005. IEEE International, 2005.
[87] Chang Ch., Ansari R., Khokhar A. Multiple object tracking with kernel particle filter. Prec. of the 2005 IEEE Comp. Society Conf. on Comp. Vision and Patt. Recognition, 2005.
[88] Cavallaro A.,Steiger O.,Ebrahimi T. Tracking video objects in cluttered background. IEEE Transactions on circuits and system for video technology, Vol.15, 2005.
[89] Yoon Y., Kosaka A., Jae Byung Park and Avinash C. Kak. A new approach to the use of edge Extremities for model-based object Tracking. Proceedings of the 2005 IEEE international conference on robotics and automation,Bacerola,2005.
[1] Fukunage K. and L.D. Hostetler, The estimation of the gradient of a density function with application in pattern recognition. IEEE Trans. Information Theory, 1975.21(1): p.32-40
[2] Cheng Y. Z. Mean Shift, Mode Seeking, and Clustering [J]. IEEE Transactions on Patterns and Machine Intelligence. 1995, 8(17):790-799.
[3] Comaniciu D,Ramesh V, and Meer P. Real-time tracking of non-rigid using mean shift . In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[4] Collins R., Lipton A., Fujiyoshi H.,and Kanade T. Algorithms for Cooperative Multisensor Surveillance [C].Proc.IEEE,Vol,89,No. 10,pp. 1456-1477,2001.
[5] Bradski G.R., Computer Vision Face Tracking as a Component of a Perceptual User Interface[J]. Proc. IEEE Workshop Applications of Computer Vision,1998, (10):214-219.
[6] Comaniciu D., Ramesh V., Meet P. Kernel-Based Object Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2003,5(25): 564-577.
[7] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., May 2002, 24(5):603-619.
[8] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition ,2003, Vol 2. Baltimore: Victor Graphics, 234-240.
[9] Zivkovic Z., Krose Ben. An era-like algorithm for color-histogram-based object tracking. In proc IEEE Conf. Comp. Vision Pattem Recognition, Washington D.C., 2004(1):798-803
[10] Singh M., Arora H., Robust registration and tracking using kernel density correlation. Proc. 2004 Conf. Comp. Vision and Pattern Recognition, Washington, D.C., 2004,vol. 11: 174-174.
[11] Yang, C., Duraiswami, R., Gumerov, N., and Davis, L. 2003. Improved fast Gauss transform and efficient kernel density estimation. In IEEE Int. Conf. on Computer Vision. 464-471.
[12] 时永刚．广义距离度量和多模态图象匹配技术研究：[博士学位论文]北京：中国科学院电子学研究所，2003
[13] Rucldidge W J., Efficiently location objects using hausdorff distance[J]. International Janaual of Computer Vision, 1997; 24(3): 251-270
[14] Daesik Jang, Gye yong Kim. Model-based tracking of moving object[J]. Pattern Recognition, 1997: 30: 999-1008
[1] Comaniciu D,Ramesh V,and Meer P.Real-time tracking of non-rigid using mean shift. In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[2] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619 ,May 2002.
[3] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition, Vol 2. Baltimore: Victor Graphics, 234-240,2003.
[4] Hendrik P. Lopuha. Asynptotics of rewighted estimators of multivariate location and scatter. The Annals of Statistics ,1999, Vol. 27, No. 5, 1638-1665
[5] Zivkovic Z, Krose Ben. An EM-like algorithm for color-histogram-based object tracking. In: Proceedings of IEEE Compute Society Conf. on Computer Vision and Pattern Recognition, Washington, D.C.,USA:IEEE Press,2004.1:798～803
[6] Bilmes J.A. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Department of EE&CS,UC Berkeley, Tech. Rep.:TR-97-021,1998
[7] Lindeberg T.. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):77-116, 1998.
[8] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G].in:Learning in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[9] 邹谋炎．反卷积和信号复原．北京：国防工业出版社，2001．
[10] Birchfield S. Elliptical Head Tracking using intensity gradients and color histogram. IEEE Conf. on Comp. Vis and Pat. Rec., Santa Barara,232-237,1998.
[1] Comaniciu D,Ramesh V,and Meer P.Real-time tracking of non-rigid using mean shift. In: Werner B, ed. IEEE Int'l Proc. of the Computer Vision and Pattern Recognition. Stoughton: Printing House, 2000, Vol 2:142-149.
[2] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619 ,May 2002.
[3] Collins R. Mean-shift blob tracking through scale space. In proc IEEE Conf. Comp. Vision Pattern Recognition, Vol 2. Baltimore: Victor Graphics, 234-240,2003.
[4] Isard M,Blake A. Condensation-conditional density propagation for visual tracking|J]. International Journal of computer vision, 1998,29(1 ):5-28.
[5] Katja Nummiaro,Esther Koller-Meier and Luc Van Gool. An adaptive color-based particle filter [J]. Image and vision computing 2003,21(1):99-110.
[6] Cheng Jian,Zhou Yue, Cai Nian,Yang Jie. Infrared object tracking based on particle filters[J]. Infrared Millim. Waves(程建，周越，蔡念，杨杰．基于粒子滤波的红外目标跟踪．红外与毫米波学报，)，2006，Vol．25(2)：113-117．
[7] Doucet A., Freitas J. de, Gordon N. Sequential Monte Carlo methods in practice. New-York: Springer-Verlag[M].2001
[8] Doucet A., Godsill S., Andrieu. On sequential Monte Carlo sampling methods for Bayesian filtering|J]. Statist. Computer, 2000, 10: 197-208.
[9] Arulampalam S. and Ristic B. Comparison of the particle filter with range parameterised and modeified polar EKF's for angle-only tracking|J]. Signal and Data Processing of Small Targets,SPIE,2000,4048: 288-299
[10] Gordon N., Salmon D. and Smith A. A novel approach to nonlinear/nonGaussian Bayesian State estimation. IEEE Proceedings on Radar and Signal Processing, 1993, 140(2): 107-113.
[11] Lindeberg T.. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):77-116,1998.
[12] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G]. In:Learning in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[13] Jepson A.D. ,Fleet D.J. Robust online appearance models for visual tracking ,Proceedings of the International Conference on Computer Vision and Pattern Recognition,Vol I, pp415-422 ,2001.
[14] P'erez P., Hue C, Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002. 661-675.
[15] Nummiaro K., Koller-Meier E. ,Van Gool L. Color features for tracking non-rigid objects ,ACTA Automatica Sinica, 2003.
[16] Strom J., Jebara T. ,Bau S., Pentland A. Real time tracking and modeling of faces: an EKF-based analysis by synthesis approach ,in : Proceedins of the Modelling People Workshop at ICCV ,1999.
[17] Ristic B.,Arulampalam S.,Gordon N. Beyond the kahnan filter ,particle filter for tracking application.Artech House ,B°ston ,London ,2004.
[1] Bar-Shalom,Y.,andBlair, W.D. Multitarget-Multisensor Tracking: Applications and Advances, Vol. Ⅲ. Norwood, MA: ArtechHouse, 2000.
[2] Bar-Shalom,Y. Multitarget Multisensor Tracking: Advanced Applications. Norwood, MA: ArtechHouse, 1990.
[3] Cox I J., Hingorani S L. An efficient implementation of reid's multiple hypotheses tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(2): 138～150
[4] Fortmann T E, Bar-Shalom Y, Scheffe M. Sonar tracking of multiple targets using joint probabilistic data association. IEEE Journal Oceanic Eng, 1983, OE-8: 173～184
[5] Gordon,N.J.,Salmond,D.J.,andSmith,A.F.M. A novel approach to non-linear and non-Gaussian Bayesian state estimation. IEEE Proceedings on Radar and Signal Processing, 140(1993),107—113.
[6] Kastella K. Discrimination gain for sensor management in multitarget detection and tracking. In IEEE-SMC and IMACS Multiconference CESA '96,vol.1 ,Lille,France, July 9-12,1996,167-172
[7] Hue, C., LeCadre,J-P.,andPerez,P. Tracking multiple objects with particle filtering. IEEE Transactions on Aerospace and Electronic Systems, 38,3(2002),791—812.
[8] Kreucher C., Kastella K., Hero A. Multi-target tracking using Joint Multitarget Probability Density. IEEE Transactions on aerospace and electronic system. Vol 41, No. 4,OCTOBER2005:1396-1414.
[9] Isard M.,and Blake A. Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vision 29, 1, 5-28,1998.
[10] Isard M.,Blake A. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. In European Conf. on Computer Vision[C]. Freiburgim Breisgau: Springer-Verlag,1998, vol (1), 893-908
[11] MacCormick J.,Blake A.A probabilistic exclusion principle for tracking multiple objects. International Journal of Computer Vision,2000,39(1):57-71.
[12] Nummiaro K., Koller-Meier E.,andGool L.V.An adaptive color-based particle filter. Image and Vision Computing, 2003,21(1): 99-110.
[13] 薛建儒．视频序列跟踪的统计计算方法：[博士学位论文]西安交通大学，2003
[14] Neal R.M.,Hinton G.E. A new view of the WM algorithm that justifies incremental and other variants[G].In:Leaming in Graphical Models.Cambridge,MA: Kluwer Academic Publishers, 1998.355_368
[15] Isard M., MaeCormick J.Bramble:A Bayesian multiple-blob tracker. In IEEE Int. Conf. Computer Vision. Vancouver, British Columbia, Canada: IEEE Computer Society, Los AlamosCA.2001.Pages34-41,volume2.
[16] MacCormick J., Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. In European Conf. on Computer Vision,2000.vol 1843 of Lecture Notes Computer Science[C].Springer-Verlag,2000.Pages3-19.
[17] P'erez P., Hue C., Vermaak J.,andGangnet M.Color-based probabilistic tracking. In European Conf. on Computer Vision, No.2350 in Lecture Notes in Computer Science[C]. 2002. 661-675.
[18] Hue C., LeCadre J., P'erez P.Sequential monte carlo methods for multiple target tracking and data fusion. IEEE Trans. on Signal Processing,2002,50(2):309-325
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |