随机概率模型视觉目标跟踪理论及应用研究
|
摘要
随着微电子计算机技术的迅猛发展和人们安全意识的日益增长,智能视频监控得到越来越多的重视和进展,有着广阔的应用前景。视觉跟踪是智能视频监控的研究热点和核心技术之一。基于随机概率模型的目标跟踪对非线性问题的处理能力和对背景干扰的鲁棒性等方面相对于其他确定性算法有着明显的优势,是视觉跟踪的一种重要理论和方法。本文针对随机概率模型中的系统动态模型对快速随机运动目标的跟踪鲁棒性和观测模型中强干扰背景下的有效观测以及应用中的关键问题,进行了深入的理论和实验研究。论文的主要内容如下：
第一章,详细地阐述了本课题的研究背景、目的和意义,综述视觉跟踪理论和随机概率模型视觉目标跟踪在国内外的研究应用现状和发展趋势,最后针对随机概率模型视觉目标跟踪方法存在的主要问题和挑战,给出了本课题的主要研究内容和研究思路。
第二章,对随机概率模型视觉目标跟踪的基础理论进行了研究,并深入地分析了随机概率模型视觉目标跟踪中随机动态传播模型和目标似然概率模型对跟踪效果的影响。
第三章,在随机概率模型目标跟踪理论的基础上,对目标快速运动情况下的问题进行了深入的研究。针对复杂动态系统下快速运动目标的跟踪问题,提出了基于运动参数估计和副粒子漂移的运动自适应粒子滤波算法和基于粒子分布临界估计和状态转移的运动自适应粒子滤波算法。通过和CAM-Shift算法、标准粒子滤波算法(PF),速度自适应粒子滤波算法(VAPF)和记忆粒子滤波算法(MPF)算法的实验对比,对算法的有效性和鲁棒性进行了验证。
第四章,研究了轮廓目标的随机概率模型和多目标情况下的概率排他性原则的概率模型。针对复杂场景下的轮廓跟踪鲁棒性问题,提出了基于内侧轮廓模型的多特征融合粒子滤波轮廓跟踪算法。该算法将轮廓特征、局部颜色特征和全局颜色特征自然地融合在一起,构建出一个新的内侧轮廓模型似然函数,在粒子滤波的框架下,实现了复杂动态背景下的轮廓跟踪。同时,本章还将内侧轮廓模型和概率排他性原则相结合,提出了一种基于内侧轮廓模型的多轮廓目标跟踪算法,实现了在复杂场景下,多轮廓目标遮挡情况下的鲁棒跟踪。实验结果表明,所提出的轮廓跟踪算法能在复杂且具有众多类似目标干扰的情况下实现有效的稳定跟踪。
第五章,针对人机交互中手势识别和跟踪的准确性和实时性问题,采用Monte Carlo随机采样来拟合三次Bezier曲线,实现对手部轮廓曲率精确估计的指尖检测。研究了随机概率模型的手势识别和跟踪,提出一种特征三角形分析的特殊手势识别和跟踪方法。通过实验结合分析表明,本章所提出的算法能在不同形态和场景下实时准确地检测出手势、识别手势和跟踪手势。
第六章,阐述了PTZ运动摄像机的模型结构,介绍了基于PTZ运动摄像机伺服控制的实验硬件系统组成,建立了PTZ摄像机的伺服控制模型,并结合随机概率模型目标跟踪方法,提出一种适用于PTZ运动摄像机的目标跟踪和摄像机伺服控制方法。实验结果表明,所提出的算法实现了对快速运动目标、轮廓目标和手势目标的精确平稳跟踪。
第七章对全文作了总结,阐述了本课题的研究结论和创新点,并对后续研究工作做出了展望。
With the growing of universal safety awareness, increasingly grim of global anti-terrorism situation, and the rapid development of computer technology, visual tracking has become a hot spot and core issue in the field of computer vision, and has a broad application prospects in the national defense and security, video surveillance, intelligent navigation, and virtual reality. Using probabilistic models and stochastic algorithms theory and methods to achieve target detection, identification and tracking is an important branch in the field of visual tracking due to its solid mathematical foundation, the practical application versatility and robustness, and it has attracted increasingly more attention of scholars at home and abroad and made a lot of significant progress. Based on the recent theoretical and progress of the visual tracking fields at home and abroad, this thesis focus on two problems in the field of visual tracking using probabilistic models and stochastic algorithms, the first one is the robust tracking of fast random moving target which has complex dynamic model, and the other one is the effecitive tracking of contour objects which have strong clutter background. This thesis also performs a servo control model using PTZ camera to achieve a stable real-time kinematic tracking. The main contents are as follows:
In chapter1, the related study background and significance of the subject are expounded. On the basis of referring to domestic and international associated documents, system components, key technologies and the current application research situation of object tracking using probabilistic models and stochastic algorithms are investigated. The problems and challenges in the research and application of effecitive and consistent tracking of fast moving object are analyzed, and the main research content and research ideas of this study is proposed.
In chapter2, the fundamental theory of visual object tracking using probabilistic models and stochastic algorithms are introduced and analyzed, and the affectness of stochastic dynamic propagation model and target likelihood probability model to the tracking performance are also analyzed in detail.
In chapter3, the problems and challenges of tracking of fast moving object are analyzed in detail, and two algorithms in dealing with these problems are proposed. The first one is a novel particle filter called Motion-Adaptive Particle Filter (MAPF) to track fast moving objects that have complex dynamic movements,and the other algorithm called Critical state transfor particle filter also proposed in this chapter. Experimental results show that the proposed method is robust for tracking objects with complex dynamic movements, and in terms of affine transformation and occlusion. Compared to Continuously Adaptive Mean-shift (CAM-Shift), Standard Particle Filter (PF), Velocity-Adaptive Particle Filter (VAPF), and Memory-based Particle Filter (M-PF), the proposed tracker is superior for objects moving with a large random velocities and accelerations.
In chapter4, the methods of contour object tracking using probabilistic models and stochastic algorithms and muti-contour objects tracking using a probabilistic exclusion principle are studied and analyzed in detail. In order to address the problem of robust tracking under cluster environment, a novel particle filter called Inner-Contour Particle Filter is proposed to track contour under complex background. The proposed algorithm first uses Sobel edge detector to detect the edge information along the normal line of the contour, and then samples the inner part of the normal line to get the local color information and combined with the edge information to construct a new normal line likehood. After that, all the inner color information are used to construct a global color histogram. Finally, the edge information, local color information and global color information are fused together as a new conservation likehood. Experimental results show that the proposed method is robust for tracking contours under complex background, and it is also computationally efficient and can run in real-time completely.
In chapter5, a novel fingertip detection approach using Cubic Bezier Curve fitting based on Monte Carlo Sampling is proposed. We aimed to achieve a robust scheme that could stably detect the fingertips in giving images. To that end, the proposed method first segment the hand region in a cluttered environment using skin color segmentation in YCbCr color space and get the silhouette of the hand. And then a Monte Carlo Sampling method is used to estimate the best fitted Cubic Bezier curves to the sub contour points centered in each contour point. After that, the curvature of the middle point of the estimated Cubic Bezier curve is calculated as the curvature of the point in the contour. Giving the estimated curvatures, the local maximums of a cumulative curvature curve are detected as the candidate fingertips. Finally, geometry feature analysis including convex hull detection and convex defects detection is applied to eliminate the valleys among the candidate fingertips. Experiment results using images including different type of hands show that the proposed approach is robust to noise and can locate the fingertips'position precisely.
In chapter6, the structure model and imaging mechanism of Pan-Tilt-Zoom (PTZ) camera are analyzed, and the effectness to the tracking algorithms of controlling the zoom action of camera while tracking is studied. In order to track fast moving object, contour object and hand gesture using PTZ camera, a servo-model of PTZ camera is introduced to the probabilistic models and stochastic algorithms. The experiment results show that the proposed algorithm is effctive and robust in tracking objects using PTZ camera.
In chapter7, the major work of the study is summarized, and the conclusions and innovations of the study are elaborated. At the same time, future development is predicted in order to provide references for the further research on this project.
第一章,详细地阐述了本课题的研究背景、目的和意义,综述视觉跟踪理论和随机概率模型视觉目标跟踪在国内外的研究应用现状和发展趋势,最后针对随机概率模型视觉目标跟踪方法存在的主要问题和挑战,给出了本课题的主要研究内容和研究思路。
第二章,对随机概率模型视觉目标跟踪的基础理论进行了研究,并深入地分析了随机概率模型视觉目标跟踪中随机动态传播模型和目标似然概率模型对跟踪效果的影响。
第三章,在随机概率模型目标跟踪理论的基础上,对目标快速运动情况下的问题进行了深入的研究。针对复杂动态系统下快速运动目标的跟踪问题,提出了基于运动参数估计和副粒子漂移的运动自适应粒子滤波算法和基于粒子分布临界估计和状态转移的运动自适应粒子滤波算法。通过和CAM-Shift算法、标准粒子滤波算法(PF),速度自适应粒子滤波算法(VAPF)和记忆粒子滤波算法(MPF)算法的实验对比,对算法的有效性和鲁棒性进行了验证。
第四章,研究了轮廓目标的随机概率模型和多目标情况下的概率排他性原则的概率模型。针对复杂场景下的轮廓跟踪鲁棒性问题,提出了基于内侧轮廓模型的多特征融合粒子滤波轮廓跟踪算法。该算法将轮廓特征、局部颜色特征和全局颜色特征自然地融合在一起,构建出一个新的内侧轮廓模型似然函数,在粒子滤波的框架下,实现了复杂动态背景下的轮廓跟踪。同时,本章还将内侧轮廓模型和概率排他性原则相结合,提出了一种基于内侧轮廓模型的多轮廓目标跟踪算法,实现了在复杂场景下,多轮廓目标遮挡情况下的鲁棒跟踪。实验结果表明,所提出的轮廓跟踪算法能在复杂且具有众多类似目标干扰的情况下实现有效的稳定跟踪。
第五章,针对人机交互中手势识别和跟踪的准确性和实时性问题,采用Monte Carlo随机采样来拟合三次Bezier曲线,实现对手部轮廓曲率精确估计的指尖检测。研究了随机概率模型的手势识别和跟踪,提出一种特征三角形分析的特殊手势识别和跟踪方法。通过实验结合分析表明,本章所提出的算法能在不同形态和场景下实时准确地检测出手势、识别手势和跟踪手势。
第六章,阐述了PTZ运动摄像机的模型结构,介绍了基于PTZ运动摄像机伺服控制的实验硬件系统组成,建立了PTZ摄像机的伺服控制模型,并结合随机概率模型目标跟踪方法,提出一种适用于PTZ运动摄像机的目标跟踪和摄像机伺服控制方法。实验结果表明,所提出的算法实现了对快速运动目标、轮廓目标和手势目标的精确平稳跟踪。
第七章对全文作了总结,阐述了本课题的研究结论和创新点,并对后续研究工作做出了展望。
With the growing of universal safety awareness, increasingly grim of global anti-terrorism situation, and the rapid development of computer technology, visual tracking has become a hot spot and core issue in the field of computer vision, and has a broad application prospects in the national defense and security, video surveillance, intelligent navigation, and virtual reality. Using probabilistic models and stochastic algorithms theory and methods to achieve target detection, identification and tracking is an important branch in the field of visual tracking due to its solid mathematical foundation, the practical application versatility and robustness, and it has attracted increasingly more attention of scholars at home and abroad and made a lot of significant progress. Based on the recent theoretical and progress of the visual tracking fields at home and abroad, this thesis focus on two problems in the field of visual tracking using probabilistic models and stochastic algorithms, the first one is the robust tracking of fast random moving target which has complex dynamic model, and the other one is the effecitive tracking of contour objects which have strong clutter background. This thesis also performs a servo control model using PTZ camera to achieve a stable real-time kinematic tracking. The main contents are as follows:
In chapter1, the related study background and significance of the subject are expounded. On the basis of referring to domestic and international associated documents, system components, key technologies and the current application research situation of object tracking using probabilistic models and stochastic algorithms are investigated. The problems and challenges in the research and application of effecitive and consistent tracking of fast moving object are analyzed, and the main research content and research ideas of this study is proposed.
In chapter2, the fundamental theory of visual object tracking using probabilistic models and stochastic algorithms are introduced and analyzed, and the affectness of stochastic dynamic propagation model and target likelihood probability model to the tracking performance are also analyzed in detail.
In chapter3, the problems and challenges of tracking of fast moving object are analyzed in detail, and two algorithms in dealing with these problems are proposed. The first one is a novel particle filter called Motion-Adaptive Particle Filter (MAPF) to track fast moving objects that have complex dynamic movements,and the other algorithm called Critical state transfor particle filter also proposed in this chapter. Experimental results show that the proposed method is robust for tracking objects with complex dynamic movements, and in terms of affine transformation and occlusion. Compared to Continuously Adaptive Mean-shift (CAM-Shift), Standard Particle Filter (PF), Velocity-Adaptive Particle Filter (VAPF), and Memory-based Particle Filter (M-PF), the proposed tracker is superior for objects moving with a large random velocities and accelerations.
In chapter4, the methods of contour object tracking using probabilistic models and stochastic algorithms and muti-contour objects tracking using a probabilistic exclusion principle are studied and analyzed in detail. In order to address the problem of robust tracking under cluster environment, a novel particle filter called Inner-Contour Particle Filter is proposed to track contour under complex background. The proposed algorithm first uses Sobel edge detector to detect the edge information along the normal line of the contour, and then samples the inner part of the normal line to get the local color information and combined with the edge information to construct a new normal line likehood. After that, all the inner color information are used to construct a global color histogram. Finally, the edge information, local color information and global color information are fused together as a new conservation likehood. Experimental results show that the proposed method is robust for tracking contours under complex background, and it is also computationally efficient and can run in real-time completely.
In chapter5, a novel fingertip detection approach using Cubic Bezier Curve fitting based on Monte Carlo Sampling is proposed. We aimed to achieve a robust scheme that could stably detect the fingertips in giving images. To that end, the proposed method first segment the hand region in a cluttered environment using skin color segmentation in YCbCr color space and get the silhouette of the hand. And then a Monte Carlo Sampling method is used to estimate the best fitted Cubic Bezier curves to the sub contour points centered in each contour point. After that, the curvature of the middle point of the estimated Cubic Bezier curve is calculated as the curvature of the point in the contour. Giving the estimated curvatures, the local maximums of a cumulative curvature curve are detected as the candidate fingertips. Finally, geometry feature analysis including convex hull detection and convex defects detection is applied to eliminate the valleys among the candidate fingertips. Experiment results using images including different type of hands show that the proposed approach is robust to noise and can locate the fingertips'position precisely.
In chapter6, the structure model and imaging mechanism of Pan-Tilt-Zoom (PTZ) camera are analyzed, and the effectness to the tracking algorithms of controlling the zoom action of camera while tracking is studied. In order to track fast moving object, contour object and hand gesture using PTZ camera, a servo-model of PTZ camera is introduced to the probabilistic models and stochastic algorithms. The experiment results show that the proposed algorithm is effctive and robust in tracking objects using PTZ camera.
In chapter7, the major work of the study is summarized, and the conclusions and innovations of the study are elaborated. At the same time, future development is predicted in order to provide references for the further research on this project.
引文
[1]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,04)：603-617.
[2]杨戈,刘宏.视觉跟踪算法综述[J].智能系统学报,2010,02)：95-105.
[3]Wax N. Signal-to-Noise Improvement and the Statistics of Track Populations [J]. Journal of Applied Physics,1955,26(586-595.
[4]Kalman R E. A New Approach to Linear Filtering and Prediction Problems [J]. Transactions of the ASME-Journal of Basic Engineering,1960,82 (Series D)): 35-45.
[5]Sittler R W. An Optimal Data Association Problem in Surveillance Theory [J]. Military Electronics, IEEE Transactions on,1964,8(2):125-139.
[6]Robert A S, John J S. An optimal tracking filter for processing sensor data of imprecisely determined origin in surveillance systems; proceedings of the Decision and Control,1971 IEEE Conference on, F Dec.1971,1971 [C].
[7]Sethi I K, Jain R. Finding Trajectories of Feature Points in a Monocular Image Sequence [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1987, PAMI-9(1):56-73.
[8]Salari V, Sethi I K. Feature point correspondence in the presence of occlusion [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1990,12(1): 87-91.
[9]Rangarajan K, Shah M. Establishing motion correspondence; proceedings of the Computer Vision and Pattern Recognition,1991 Proceedings CVPR'91, IEEE Computer Society Conference on, F 3-6 Jun 1991,1991 [C].
[10]Veenman C J, Reinders M J T, Backer E. Resolving motion correspondence for densely moving points [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2001,23(1):54-72.
[11]Shafique K, Shah M. A noniterative greedy algorithm for multiframe point correspondence [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005,27(1):51-65.
[12]Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition [J]. Information Theory, IEEE Transactions on, 1975,21(1):32-40.
[13]Yizong C. Mean shift, mode seeking, and clustering [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1995,17(8):790-799.
[14]Bradski G R. Computer Vision Face Tracking For Use in a Perceptual User Interface [J]. Intel Technology Journal,2nd Quarter,1998,
[15]Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image Vis Comput,2003,21(1):99-110.
[16]Hess R, Fern A, Ieee. Discriminatively Trained Particle Filters for Complex Multi-Object Tracking [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee.2009:240-247.
[17]Mikami D, Otsuka K, Yamato J, et al. Memory-based Particle Filter for Face Pose Tracking Robust under Complex Dynamics [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee.2009: 999-1006.
[18]Yuan L, Haizhou A, Yamashita T, et al. Tracking in Low Frame Rate Video:A Cascade Particle Filter with Discriminative Observers of Different Lifespans; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[19]Lun Z, Li S Z, Xiaotong Y, et al. Real-time Object Classification in Video Surveillance Based on Appearance Learning; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007, 2007 [C].
[20]杨进杨杰,王芳林.一种改进的红外多目标跟踪算法[J].上海交通大学学报,2009,43(3)：437-442.
[21]T. Gevers J V D W, H. Stokman. Color Image Processing:Methods and Applications [M]. CRC Press,2006.
[22]Maggio E, Cavallaro A. Multi-part target representation for color tracking; proceedings of the Image Processing,2005 ICIP 2005 IEEE International Conference on, F 11-14 Sept.2005,2005 [C].
[23]郝志会,汪渤,孙杭.基于特征颜色模型的粒子滤波改进算法[J].北京理工大学学报,2011,31(4)：436-440.
[24]Abdel-Hakim A E, Farag A A. CSIFT:A SIFT Descriptor with Color Invariant Characteristics; proceedings of the Computer Vision and Pattern Recognition,2006 IEEE Computer Society Conference on, F 2006,2006 [C].
[25]Van De Sande K E A, Gevers T, Snoek C G M. Evaluating Color Descriptors for Object and Scene Recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2010,32(9):1582-1596.
[26]Van De Weijer J, Gevers T, Bagdanov A D. Boosting color saliency in image feature detection [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2006,28(1):150-156.
[27]Burghouts G J, Geusebroek J-M. Performance evaluation of local colour invariants [J]. Comput Vis Image Underst,2009,113(1):48-62.
[28]Dalal N, Triggs B. Histograms of oriented gradients for human detection; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on, F 25-25 June 2005,2005 [C].
[29]Maji S, Berg A C, Malik J. Classification using intersection kernel support vector machines is efficient; proceedings of the Computer Vision and Pattern Recognition, 2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[30]Felzenszwalb P, Mcallester D, Ramanan D. A discriminatively trained, multiscale, deformable part model; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[31]Qiang Z, Mei-Chen Y, Kwang-Ting C, et al. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients; proceedings of the Computer Vision and Pattern Recognition,2006 IEEE Computer Society Conference on, F 2006, 2006 [C].
[32]Sabzmeydani P, Mori G Detecting Pedestrians by Learning Shapelet Features; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[33]Gavrila D. Pedestrian Detection from a Moving Vehicle [M]. Proceedings of the 6th European Conference on Computer Vision-Part II. Springer-Verlag.2000:37-49.
[34]Zhe L, Davis L S, Doermann D, et al. Hierarchical Part-Template Matching for Human Detection and Segmentation; proceedings of the Computer Vision,2007 ICCV 2007 IEEE 11th International Conference on, F 14-21 Oct.2007,2007 [C].
[35]Ferrari V, Tuytelaars T, Gool L. Object Detection by Contour Segment Networks [M]//Leonardis A, Bischof H, Pinz A. Computer Vision-ECCV 2006. Springer Berlin Heidelberg.2006:14-28.
[36]Bo W, Nevatia R. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors; proceedings of the Computer Vision,2005 ICCV 2005 Tenth IEEE International Conference on, F 17-21 Oct.2005,2005 [C].
[37]Mikolajczyk K, Schmid C, Zisserman A. Human Detection Based on a Probabilistic Assembly of Robust Part Detectors [M]//Pajdla T, Matas J. Computer Vision-ECCV 2004. Springer Berlin Heidelberg.2004:69-82.
[38]Leibe B, Seemann E, Schiele B. Pedestrian detection in crowded scenes; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on, F 20-25 June 2005,2005 [C].
[39]Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features (SURF) [J]. Comput Vis Image Underst,2008,110(3):346-359.
[40]Gall J, Lempitsky V. Class-specific Hough forests for object detection; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[41]Yan K, Sukthankar R, Hebert M. Efficient visual event detection using volumetric features; proceedings of the Computer Vision,2005 ICCV 2005 Tenth IEEE International Conference on, F 17-21 Oct.2005,2005 [C].
[42]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features; proceedings of the Computer Vision and Pattern Recognition,2001 CVPR 2001 Proceedings of the 2001 IEEE Computer Society Conference on, F 2001,2001 [C].
[43]Willems G, Tuytelaars T, Gool L. An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector [M]. Proceedings of the 10th European Conference on Computer Vision:Part Ⅱ. Marseille, France; Springer-Verlag.2008: 650-663.
[44]Laptev I, Marszalek M, Schmid C, et al. Learning realistic human actions from movies; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[45]Scovanner P, Ali S, Shah M. A 3-dimensional sift descriptor and its application to action recognition [M]. Proceedings of the 15th international conference on Multimedia. Augsburg, Germany; ACM.2007:357-360.
[46]Klaser A, Marszalek M. A spatio-temporal descriptor based on 3D-gradients [J]. 2008,
[47]Shao L, Gao R, Liu Y, et al. Transform based spatio-temporal descriptors for human action recognition [J]. Neurocomputing,2011,74(6):962-973.
[48]Wang H, Ullah M M, Klaser A, et al. Evaluation of local spatio-temporal features for action recognition; proceedings of the BMVC 2009-British Machine Vision Conference, F,2009 [C]. INFO:INFO_CV internationale London Royaume-Uni.
[49]Tuzel O, Porikli F, Meer P. Human Detection via Classification on Riemannian Manifolds; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[50]Wang X, Han T X, Yan S. An HOG-LBP human detector with partial occlusion handling; proceedings of the Computer Vision,2009 IEEE 12th International Conference on, F Sept.29 2009-Oct.2 2009,2009 [C].
[51]张波.基于粒子滤波的图像跟踪算法研究[D]；上海交通大学,2007.
[52]Shotton J, Blake A, Cipolla R. Efficiently combining contour and texture cues for object recognition; proceedings of the British Machine Vision Conf, F,2008 [C].
[53]Bo W, Nevatia R. Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[54]Schwartz W R, Kembhavi A, Harwood D, et al. Human detection using partial least squares analysis; proceedings of the Computer Vision,2009 IEEE 12th International Conference on, F,2009 [C]. IEEE.
[55]王昊,张波,田蔚风.一种基于概率神经网络多信息融合的移动目标跟踪算法[J].上海交通大学学报,2007,41(5)：792-796.
[56]Alexe B, Deselaers T, Ferrari V. What is an object?; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[57]Feng H, Ying S, Sawhney H S, et al. Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[58]李安平.复杂环境下的视频目标跟踪算法研究[D]；上海交通大学,2007.
[59]孙伟,郭宝龙,陈龙.非降采样Contourlet域方向区域多聚焦图像融合算法[J].吉林大学学报(工学版),2009,05)：1384-1389.
[60]Liu B, Huang J, Kulikowski C, et al. Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2012, PP(99):1-1.
[61]黄鹤,王小旭,赵春晖,et al.基于后验信息修正的自适应交互多模型跟踪算法[J].西北工业大学学报,2011,06)：829-833.
[62]Junseok K. Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling [J]. IEEE Trans Pattern Anal Mach Intell,2013,99(PrePrints): 1-1.
[63]Holzer S, Ilic S, Navab N. Multilayer Adaptive Linear Predictors for Real-Time Tracking [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013,35(1):105-117.
[64]Grabner H, Matas J, Van Gool L, et al. Tracking the invisible:Learning where the object might be; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[65]Stalder S, Grabner H, Gool L V. Cascaded confidence filtering for improved tracking-by-detection [M]. Proceedings of the 11th European conference on Computer vision:Part I. Heraklion, Crete, Greece; Springer-Verlag.2010:369-382.
[66]Zhaozheng Y, Collins R T. Shape constrained figure-ground segmentation and tracking; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[67]Aeschliman C, Park J, Kak A C. A probabilistic framework for joint segmentation and tracking; proceedings of the Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[68]王芳林.稳健视觉跟踪算法中的关键问题研究[D]；上海交通大学,2009.
[69]Breitenstein M D, Reichlin F, Leibe B, et al. Robust Tracking-by-Detection using a Detector Confidence Particle Filter [M].2009 Ieee 12th International Conference on Computer Vision. New York; Ieee.2009:1515-1522.
[70]胡振涛,潘泉,梁彦,et a1.基于进化采样的粒子滤波算法[J].控制理论与应用,2009,03)：269-273.
[71]胡振涛,潘泉,梁彦,et a1.基于粒子滤波的模型自适应机动目标跟踪算法[J].控制与决策,2008,12)：1333-1337.
[72]Junseok K, Kyoung Mu L. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[73]Junseok K, Kyoung Mu L. Visual tracking decomposition; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[74]梁新华,潘泉,杨峰,et al.基于两级采样的粒子滤波检测前跟踪算法[J].系统工程与电子技术,2011,09)：1921-1926.
[75]Schindler G, Dellaert F. A Rao-Blackwellized Parts-Constellation Tracker [M]//Vidal R, Heyden A, Ma Y. Dynamical Vision. Springer Berlin Heidelberg. 2007:178-189.
[76]Kwon J, Lee K M, Park F C, et al. Visual Tracking via Geometric Particle Filtering on the Affine Group with Optimal Importance Functions [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee. 2009:991-998.
[77]Zhang X, Hu W, Maybank S. A Smarter Particle Filter [M]//Zha H, Taniguchi R-I, Maybank S. Computer Vision-ACCV 2009. Springer Berlin Heidelberg.2010: 236-246.
[78]孟凡彬,郝燕玲,张崇猛,et al.基于无迹粒子PHD滤波的序贯融合算法[J].系统工程与电子技术,2011,01)：30-34.
[79]Kwon J, Lee K. Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation [M]//Forsyth D, Torr P, Zisserman A. Computer Vision-ECCV 2008. Springer Berlin Heidelberg.2008:387-400.
[80]Mckenna S J, Nait-Charif H. Tracking human motion using auxiliary particle filters and iterated likelihood weighting [J]. Image Vis Comput,2007,25(6):852-862.
[81]Xiaoqin Z, Weiming H, Zixiang Z, et al. SVD based Kalman particle filter for robust visual tracking; proceedings of the Pattern Recognition,2008 ICPR 2008 19th International Conference on, F 8-11 Dec.2008,2008 [C].
[82]Li Y, Ai H Z, Yamashita T, et al. Tracking in low frame rate video:A cascade particle filter with discriminative observers of different life spans [J]. IEEE Trans Pattern Anal Mach Intell,2008,30(10):1728-1740.
[83]Ming Y, Ying W, Shihong L. Intelligent Collaborative Tracking by Mining Auxiliary Objects; proceedings of the Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, F 17-22 June 2006,2006 [C].
[84]Kalal Z, Matas J, Mikolajczyk K. Online learning of robust object detectors during unstable tracking; proceedings of the Computer Vision Workshops (ICCV Workshops),2009 IEEE 12th International Conference on, F Sept.272009-Oct.4 2009,2009 [C].
[85]Kalal Z, Mikolajczyk K, Matas J. Forward-Backward Error:Automatic Detection of Tracking Failures; proceedings of the Pattern Recognition (ICPR),2010 20th International Conference on, F 23-26 Aug.2010,2010 [C].
[86]Vondrak M, Sigal L, Jenkins O C. Dynamical Simulation Priors for Human Motion Tracking [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013,35(1):52-65.
[87]Murray D, Basu A. Motion tracking with an active camera [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1994,16(5):449-459.
[88]Jung Y-K, Lee K-W, Ho Y-S. Feature-Based Object Tracking with an Active Camera [M]//Chen Y-C, Chang L-W, Hsu C-T. Advances in Multimedia Information Processing-PCM 2002. Springer Berlin Heidelberg.2002:1137-1144.
[89]Bartoli A, Dalal N, Horaud R. Motion Panoramas [J]. Computer Animation and Virtual Worlds,2004,15(5):501-517.
[90]Bevilacqua A, Azzari P. A Fast and Reliable Image Mosaicing Technique with Application to Wide Area Motion Detection [M]//Kamel M, Campilho A. Image Analysis and Recognition. Springer Berlin Heidelberg.2007:501-512.
[91]Chung-Hao C, Yi Y, Page D, et al. Heterogeneous Fusion of Omnidirectional and PTZ Cameras for Multiple Object Tracking [J]. Circuits and Systems for Video Technology, IEEE Transactions on,2008,18(8):1052-1063.
[92]Micheloni C, Foresti G L. Real-time image processing for active monitoring of wide areas [J]. Journal of Visual Communication and Image Representation,2006, 17(3):589-604.
[93]Jae Kyu S, Ho Gi J, Gen L, et al. Background Compensation for Pan-Tilt-Zoom Cameras Using 1-D Feature Matching and Outlier Rejection [J]. Circuits and Systems for Video Technology, IEEE Transactions on,2011,21(3):371-377.
[94]Songxiao C, Xuanyin W, Ke X. Visual Object Servo Tracking Based on the Particle Filter Method Using a Pan-Tilt-Zoom Camera [J]. Int J Adv Robotic Sy,2012, 9(134):
[95]Varcheie P, Bilodeau G-A. People tracking using a network-based PTZ camera [J]. Machine Vision and Applications,2011,22(4):671-690.
[96]Choi W, Pantofaru C, Savarese S. A General Framework for Tracking Multiple People from a Moving Camera [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2012, PP(99):1-1.
[97]Kennedy J, C.Eberhart R, Shi Y. Swarm Intelligence [M].2009.
[98]Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II [J]. Evolutionary Computation, IEEE Transactions on,2002, 6(2):182-197.
[99]Kirkpatrick S, Vecchi M. Optimization by simmulated annealing [J]. science,1983, 220(4598):671-680.
[100]Eberhart R, Kennedy J. A new optimizer using particle swarm theory; proceedings of the Micro Machine and Human Science,1995 MHS'95, Proceedings of the Sixth International Symposium on, F 4-6 Oct 1995,1995 [C].
[101]朱志宇.粒子滤波算法及其应用[M].北京：科学出版社,2010.
[102]朱新玲.马尔科夫链蒙特卡罗方法研究综述[J].统计与决策,2009,21)：151-153.
[103]M.Ross S.应用随机过程：概率模型导论(第9版)[M].北京：人民邮电出版社,2007.
[104]Cannons K:York University, Department of Computer Science and Engineering,2008.
[105]Khan S, Shah M. A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint Computer Vision-ECCV 2006 [M]//Leonardis A, Bischof H, Pinz A. Springer Berlin/Heidelberg.2006:133-146.
[106]Yang S. Particle Filtering Based Estimation of Consistent Motion and Disparity with Reduced Search Points [J]. IEEE Trans Circuits Syst Video Technol,2012, 22(1):91-104.
[107]Isard M, Blake A. Contour tracking by stochastic propagation of conditional density-Computer Vision-ECCV'96 [M]//Buxton B, Cipolla R. Springer Berlin/ Heidelberg.1996:343-356.
[108]North B, Blake A, Isard M, et al. Learning and classification of complex dynamics [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000,22(9):1016-1034.
[109]Wu Y, Huang T S, Ieee Computer S. A co-inference approach to robust visual tracking [M]. Los Alamitos:Ieee Computer Soc,2001.
[110]Zhou S H K, Chellappa R, Moghaddam B. Visual tracking and recognition using appearance-adaptive models in particle filters [J]. IEEE Trans Image Process, 2004,13(11):1491-1506.
[111]Lui Y M, Beveridge J R, Whitley L D. Adaptive Appearance Model and Condensation Algorithm for Robust Face Tracking [J]. IEEE Trans Syst Man Cybern Paart A-Syst Hum,2010,40(3):437-448.
[112]Del Bimbo A, Dini F. Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation [J]. Comput Vis Image Underst,2011, 115(6):771-786.
[113]Han B, Zhu Y, Comaniciu D, et al. Visual Tracking by Continuous Density Propagation in Sequential Bayesian Filtering Framework [J]. IEEE Trans Pattern Anal Mach Intell,2009,31(5):919-930.
[114]SPEVI dataset [M].
[115]UCF YouTube Action Dataset [M].
[116]胡士强,敬忠良.粒子滤波原理及应用[M].科学出版社,2010.
[117]Yilmaz A, Javed O, Shah M. Object tracking:A survey [J]. ACM Comput Surv, 2006,38(4):13.
[118]Birchfield S, Ieee Comp S O C. Elliptical head tracking using intensity gradients and color histograms [M].1998 Ieee Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings. Los Alamitos; Ieee Computer Soc.1998:232-237.
[119]Li P H, Chaumette F. Image cues fusion for object tracking based on particle filter [M]//Perales F J, Draper B A. Articulated Motion and Deformable Objects, Proceedings. Berlin; Springer-Verlag Berlin.2004:99-110.
[120]Badrinarayanan V, Perez P, Le Clerc F, et al. Probabilistic color and adaptive multi-feature tracking with dynamically switched priority between cues [M].2007 Ieee 11th International Conference on Computer Vision, Vols 1-6. New York; Ieee. 2007:1000-1007.
[121]Bernardin K, Gehrig T, Stiefelhagen R. Multi-level particle filter fusion of features and cues for audio-visual person tracking [M]//Stiefelhagen R, Bowers R, Fiscus J. Multimodal Technologies for Perception of Humans. Berlin; Springer-Verlag Berlin.2008:70-81.
[122]王永忠,梁彦,赵春晖,潘泉.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4)：393-399.
[123]Maccormick J, Blake A. A probabilistic exclusion principle for tracking multiple objects; proceedings of the Computer Vision,1999 The Proceedings of the Seventh IEEE International Conference on, F 1999,1999 [C].
[124]Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computer interaction:A review [J]. IEEE Trans Pattern Anal Mach Intell, 1997,19(7):677-695.
[125]Erol A, Bebis G, Nicolescu M, et al. Vision-based hand pose estimation:A review [J]. Comput Vis Image Underst,2007,108(1-2):52-73.
[126]Matthieu Bray E K-M, Pascal Muller, Luc Van Gool, Nicol N. Schraudolph. 3D hand tracking by rapid stochastic gradient descent using a skinning model [M]. IN 1ST EUROPEAN CONFERENCE ON VISUAL MEDIA PRODUCTION (CVMP).2004:59-68.
[127]Dewaele G, Devernay F, Horaud R. Hand Motion from 3D Point Trajectories and a Smooth Surface Model [M]//Pajdla T, Matas J. Computer Vision-ECCV 2004. Springer Berlin Heidelberg.2004:495-507.
[128]Davis J, Shah M. Visual gesture recognition [J]. Vision, Image and Signal Processing, IEE Proceedings-,1994,141(2):101-106.
[129]Jintae L, Kunii T L. Model-based analysis of hand posture [J]. Computer Graphics and Applications, IEEE,1995,15(5):77-86.
[130]Starner T, Weaver J, Pentland A. A wearable computer-based American sign Language Recogniser [J]. Personal Technologies,1997,1(4):241-250.
[131]Azoz Y, Devi L, Sharma R. Reliable tracking of human arm dynamics by multiple cue integration and constraint fusion; proceedings of the Computer Vision and Pattern Recognition,1998 Proceedings 1998 IEEE Computer Society Conference on, F 23-25 Jun 1998,1998 [C].
[132]Hardenberg C V, Berard F. Bare-hand human-computer interaction [M]. Proceedings of the 2001 workshop on Perceptive user interfaces. Orlando, Florida; ACM.2001:1-8.
[133]Koike. H, Sato. Y, Kobayashi. Y. Integrating paper and digital information on EnhancedDesk:a method for realtime finger tracking on an augmented desk system [J]. ACM Trans Comput-Hum Interact,2001,8(4):307-322.
[134]Oka K, Sato Y, Koike H. Real-time tracking of multiple fingertips and gesture recognition for augmented desk interface systems; proceedings of the Automatic Face and Gesture Recognition,2002 Proceedings Fifth IEEE International Conference on, F 21-21 May 2002,2002 [C].
[135]Letessier J, Berard F. Visual tracking of bare fingers for interactive surfaces [M]. Proceedings of the 17th annual ACM symposium on User interface software and technology. Santa Fe, NM, USA; ACM.2004:119-122.
[136]Segen J, Kumar S. Gesture VR:vision-based 3D hand interace for spatial interaction [M]. Proceedings of the sixth ACM international conference on Multimedia. Bristol, United Kingdom; ACM.1998:455-464.
[137]O'hagan R G, Zelinsky A, Rougeaux S. Visual gesture interfaces for virtual environments [J]. Interact Comput,2002,14(3):231-250.
[138]Malik S, Laszlo J. Visual touchpad:a two-handed gestural input device [M]. Proceedings of the 6th international conference on Multimodal interfaces. State College, PA, USA; ACM.2004:289-296.
[139]Argyros A A, Lourakis M I A. Vision-based interpretation of hand gestures for remote control of a computer mouse [M]//Huang T S, Sebe N, Lew M S, et al. Computer Vision in Human-Computer Interaction. Berlin; Springer-Verlag Berlin. 2006:40-51.
[140]Jo K H, Kuno Y, Shirai Y, et al. Manipulative hand gesture recognition using task knowledge for human computer interaction [M]. Los Alamitos:Ieee Computer Soc,1998.
[141]Mo Z, Lewis J P, Neumann U. SmartCanvas:a gesture-driven intelligent drawing desk system [M]. Proceedings of the 10th international conference on Intelligent user interfaces. San Diego, California, USA; ACM.2005:239-243.
[142]Hsu R L, Abdel-Mottaleb M, Jain A K. Face detection in color images [J]. IEEE Trans Pattern Anal Mach Intell,2002,24(5):696-706.
[143]Chai D, Ngan K N, Ieee. Locating facial region of a head-and-shoulders color image [M]. Los Alamitos:Ieee Computer Soc,1998.
[144]孙家广,胡事民.计算机图形学基础教程[M].清华大学出版社,2005.
[145]Shapiro A. Monte Carlo Sampling Methods [M]//Ruszczynski A, Shapiro A. Handbooks in Operations Research and Management Science. Elsevier.2003: 353-425.
[146]Graham R L. An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set [J]. Information Processing Letters,1972,1(132-133.
[2]杨戈,刘宏.视觉跟踪算法综述[J].智能系统学报,2010,02)：95-105.
[3]Wax N. Signal-to-Noise Improvement and the Statistics of Track Populations [J]. Journal of Applied Physics,1955,26(586-595.
[4]Kalman R E. A New Approach to Linear Filtering and Prediction Problems [J]. Transactions of the ASME-Journal of Basic Engineering,1960,82 (Series D)): 35-45.
[5]Sittler R W. An Optimal Data Association Problem in Surveillance Theory [J]. Military Electronics, IEEE Transactions on,1964,8(2):125-139.
[6]Robert A S, John J S. An optimal tracking filter for processing sensor data of imprecisely determined origin in surveillance systems; proceedings of the Decision and Control,1971 IEEE Conference on, F Dec.1971,1971 [C].
[7]Sethi I K, Jain R. Finding Trajectories of Feature Points in a Monocular Image Sequence [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1987, PAMI-9(1):56-73.
[8]Salari V, Sethi I K. Feature point correspondence in the presence of occlusion [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1990,12(1): 87-91.
[9]Rangarajan K, Shah M. Establishing motion correspondence; proceedings of the Computer Vision and Pattern Recognition,1991 Proceedings CVPR'91, IEEE Computer Society Conference on, F 3-6 Jun 1991,1991 [C].
[10]Veenman C J, Reinders M J T, Backer E. Resolving motion correspondence for densely moving points [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2001,23(1):54-72.
[11]Shafique K, Shah M. A noniterative greedy algorithm for multiframe point correspondence [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005,27(1):51-65.
[12]Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition [J]. Information Theory, IEEE Transactions on, 1975,21(1):32-40.
[13]Yizong C. Mean shift, mode seeking, and clustering [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1995,17(8):790-799.
[14]Bradski G R. Computer Vision Face Tracking For Use in a Perceptual User Interface [J]. Intel Technology Journal,2nd Quarter,1998,
[15]Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image Vis Comput,2003,21(1):99-110.
[16]Hess R, Fern A, Ieee. Discriminatively Trained Particle Filters for Complex Multi-Object Tracking [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee.2009:240-247.
[17]Mikami D, Otsuka K, Yamato J, et al. Memory-based Particle Filter for Face Pose Tracking Robust under Complex Dynamics [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee.2009: 999-1006.
[18]Yuan L, Haizhou A, Yamashita T, et al. Tracking in Low Frame Rate Video:A Cascade Particle Filter with Discriminative Observers of Different Lifespans; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[19]Lun Z, Li S Z, Xiaotong Y, et al. Real-time Object Classification in Video Surveillance Based on Appearance Learning; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007, 2007 [C].
[20]杨进杨杰,王芳林.一种改进的红外多目标跟踪算法[J].上海交通大学学报,2009,43(3)：437-442.
[21]T. Gevers J V D W, H. Stokman. Color Image Processing:Methods and Applications [M]. CRC Press,2006.
[22]Maggio E, Cavallaro A. Multi-part target representation for color tracking; proceedings of the Image Processing,2005 ICIP 2005 IEEE International Conference on, F 11-14 Sept.2005,2005 [C].
[23]郝志会,汪渤,孙杭.基于特征颜色模型的粒子滤波改进算法[J].北京理工大学学报,2011,31(4)：436-440.
[24]Abdel-Hakim A E, Farag A A. CSIFT:A SIFT Descriptor with Color Invariant Characteristics; proceedings of the Computer Vision and Pattern Recognition,2006 IEEE Computer Society Conference on, F 2006,2006 [C].
[25]Van De Sande K E A, Gevers T, Snoek C G M. Evaluating Color Descriptors for Object and Scene Recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2010,32(9):1582-1596.
[26]Van De Weijer J, Gevers T, Bagdanov A D. Boosting color saliency in image feature detection [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2006,28(1):150-156.
[27]Burghouts G J, Geusebroek J-M. Performance evaluation of local colour invariants [J]. Comput Vis Image Underst,2009,113(1):48-62.
[28]Dalal N, Triggs B. Histograms of oriented gradients for human detection; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on, F 25-25 June 2005,2005 [C].
[29]Maji S, Berg A C, Malik J. Classification using intersection kernel support vector machines is efficient; proceedings of the Computer Vision and Pattern Recognition, 2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[30]Felzenszwalb P, Mcallester D, Ramanan D. A discriminatively trained, multiscale, deformable part model; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[31]Qiang Z, Mei-Chen Y, Kwang-Ting C, et al. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients; proceedings of the Computer Vision and Pattern Recognition,2006 IEEE Computer Society Conference on, F 2006, 2006 [C].
[32]Sabzmeydani P, Mori G Detecting Pedestrians by Learning Shapelet Features; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[33]Gavrila D. Pedestrian Detection from a Moving Vehicle [M]. Proceedings of the 6th European Conference on Computer Vision-Part II. Springer-Verlag.2000:37-49.
[34]Zhe L, Davis L S, Doermann D, et al. Hierarchical Part-Template Matching for Human Detection and Segmentation; proceedings of the Computer Vision,2007 ICCV 2007 IEEE 11th International Conference on, F 14-21 Oct.2007,2007 [C].
[35]Ferrari V, Tuytelaars T, Gool L. Object Detection by Contour Segment Networks [M]//Leonardis A, Bischof H, Pinz A. Computer Vision-ECCV 2006. Springer Berlin Heidelberg.2006:14-28.
[36]Bo W, Nevatia R. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors; proceedings of the Computer Vision,2005 ICCV 2005 Tenth IEEE International Conference on, F 17-21 Oct.2005,2005 [C].
[37]Mikolajczyk K, Schmid C, Zisserman A. Human Detection Based on a Probabilistic Assembly of Robust Part Detectors [M]//Pajdla T, Matas J. Computer Vision-ECCV 2004. Springer Berlin Heidelberg.2004:69-82.
[38]Leibe B, Seemann E, Schiele B. Pedestrian detection in crowded scenes; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on, F 20-25 June 2005,2005 [C].
[39]Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features (SURF) [J]. Comput Vis Image Underst,2008,110(3):346-359.
[40]Gall J, Lempitsky V. Class-specific Hough forests for object detection; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[41]Yan K, Sukthankar R, Hebert M. Efficient visual event detection using volumetric features; proceedings of the Computer Vision,2005 ICCV 2005 Tenth IEEE International Conference on, F 17-21 Oct.2005,2005 [C].
[42]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features; proceedings of the Computer Vision and Pattern Recognition,2001 CVPR 2001 Proceedings of the 2001 IEEE Computer Society Conference on, F 2001,2001 [C].
[43]Willems G, Tuytelaars T, Gool L. An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector [M]. Proceedings of the 10th European Conference on Computer Vision:Part Ⅱ. Marseille, France; Springer-Verlag.2008: 650-663.
[44]Laptev I, Marszalek M, Schmid C, et al. Learning realistic human actions from movies; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[45]Scovanner P, Ali S, Shah M. A 3-dimensional sift descriptor and its application to action recognition [M]. Proceedings of the 15th international conference on Multimedia. Augsburg, Germany; ACM.2007:357-360.
[46]Klaser A, Marszalek M. A spatio-temporal descriptor based on 3D-gradients [J]. 2008,
[47]Shao L, Gao R, Liu Y, et al. Transform based spatio-temporal descriptors for human action recognition [J]. Neurocomputing,2011,74(6):962-973.
[48]Wang H, Ullah M M, Klaser A, et al. Evaluation of local spatio-temporal features for action recognition; proceedings of the BMVC 2009-British Machine Vision Conference, F,2009 [C]. INFO:INFO_CV internationale London Royaume-Uni.
[49]Tuzel O, Porikli F, Meer P. Human Detection via Classification on Riemannian Manifolds; proceedings of the Computer Vision and Pattern Recognition,2007 CVPR'07 IEEE Conference on, F 17-22 June 2007,2007 [C].
[50]Wang X, Han T X, Yan S. An HOG-LBP human detector with partial occlusion handling; proceedings of the Computer Vision,2009 IEEE 12th International Conference on, F Sept.29 2009-Oct.2 2009,2009 [C].
[51]张波.基于粒子滤波的图像跟踪算法研究[D]；上海交通大学,2007.
[52]Shotton J, Blake A, Cipolla R. Efficiently combining contour and texture cues for object recognition; proceedings of the British Machine Vision Conf, F,2008 [C].
[53]Bo W, Nevatia R. Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[54]Schwartz W R, Kembhavi A, Harwood D, et al. Human detection using partial least squares analysis; proceedings of the Computer Vision,2009 IEEE 12th International Conference on, F,2009 [C]. IEEE.
[55]王昊,张波,田蔚风.一种基于概率神经网络多信息融合的移动目标跟踪算法[J].上海交通大学学报,2007,41(5)：792-796.
[56]Alexe B, Deselaers T, Ferrari V. What is an object?; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[57]Feng H, Ying S, Sawhney H S, et al. Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F 23-28 June 2008,2008 [C].
[58]李安平.复杂环境下的视频目标跟踪算法研究[D]；上海交通大学,2007.
[59]孙伟,郭宝龙,陈龙.非降采样Contourlet域方向区域多聚焦图像融合算法[J].吉林大学学报(工学版),2009,05)：1384-1389.
[60]Liu B, Huang J, Kulikowski C, et al. Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2012, PP(99):1-1.
[61]黄鹤,王小旭,赵春晖,et al.基于后验信息修正的自适应交互多模型跟踪算法[J].西北工业大学学报,2011,06)：829-833.
[62]Junseok K. Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling [J]. IEEE Trans Pattern Anal Mach Intell,2013,99(PrePrints): 1-1.
[63]Holzer S, Ilic S, Navab N. Multilayer Adaptive Linear Predictors for Real-Time Tracking [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013,35(1):105-117.
[64]Grabner H, Matas J, Van Gool L, et al. Tracking the invisible:Learning where the object might be; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[65]Stalder S, Grabner H, Gool L V. Cascaded confidence filtering for improved tracking-by-detection [M]. Proceedings of the 11th European conference on Computer vision:Part I. Heraklion, Crete, Greece; Springer-Verlag.2010:369-382.
[66]Zhaozheng Y, Collins R T. Shape constrained figure-ground segmentation and tracking; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[67]Aeschliman C, Park J, Kak A C. A probabilistic framework for joint segmentation and tracking; proceedings of the Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[68]王芳林.稳健视觉跟踪算法中的关键问题研究[D]；上海交通大学,2009.
[69]Breitenstein M D, Reichlin F, Leibe B, et al. Robust Tracking-by-Detection using a Detector Confidence Particle Filter [M].2009 Ieee 12th International Conference on Computer Vision. New York; Ieee.2009:1515-1522.
[70]胡振涛,潘泉,梁彦,et a1.基于进化采样的粒子滤波算法[J].控制理论与应用,2009,03)：269-273.
[71]胡振涛,潘泉,梁彦,et a1.基于粒子滤波的模型自适应机动目标跟踪算法[J].控制与决策,2008,12)：1333-1337.
[72]Junseok K, Kyoung Mu L. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F 20-25 June 2009,2009 [C].
[73]Junseok K, Kyoung Mu L. Visual tracking decomposition; proceedings of the Computer Vision and Pattern Recognition (CVPR),2010 IEEE Conference on, F 13-18 June 2010,2010 [C].
[74]梁新华,潘泉,杨峰,et al.基于两级采样的粒子滤波检测前跟踪算法[J].系统工程与电子技术,2011,09)：1921-1926.
[75]Schindler G, Dellaert F. A Rao-Blackwellized Parts-Constellation Tracker [M]//Vidal R, Heyden A, Ma Y. Dynamical Vision. Springer Berlin Heidelberg. 2007:178-189.
[76]Kwon J, Lee K M, Park F C, et al. Visual Tracking via Geometric Particle Filtering on the Affine Group with Optimal Importance Functions [M]. Cvpr:2009 Ieee Conference on Computer Vision and Pattern Recognition, Vols 1-4. New York; Ieee. 2009:991-998.
[77]Zhang X, Hu W, Maybank S. A Smarter Particle Filter [M]//Zha H, Taniguchi R-I, Maybank S. Computer Vision-ACCV 2009. Springer Berlin Heidelberg.2010: 236-246.
[78]孟凡彬,郝燕玲,张崇猛,et al.基于无迹粒子PHD滤波的序贯融合算法[J].系统工程与电子技术,2011,01)：30-34.
[79]Kwon J, Lee K. Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation [M]//Forsyth D, Torr P, Zisserman A. Computer Vision-ECCV 2008. Springer Berlin Heidelberg.2008:387-400.
[80]Mckenna S J, Nait-Charif H. Tracking human motion using auxiliary particle filters and iterated likelihood weighting [J]. Image Vis Comput,2007,25(6):852-862.
[81]Xiaoqin Z, Weiming H, Zixiang Z, et al. SVD based Kalman particle filter for robust visual tracking; proceedings of the Pattern Recognition,2008 ICPR 2008 19th International Conference on, F 8-11 Dec.2008,2008 [C].
[82]Li Y, Ai H Z, Yamashita T, et al. Tracking in low frame rate video:A cascade particle filter with discriminative observers of different life spans [J]. IEEE Trans Pattern Anal Mach Intell,2008,30(10):1728-1740.
[83]Ming Y, Ying W, Shihong L. Intelligent Collaborative Tracking by Mining Auxiliary Objects; proceedings of the Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, F 17-22 June 2006,2006 [C].
[84]Kalal Z, Matas J, Mikolajczyk K. Online learning of robust object detectors during unstable tracking; proceedings of the Computer Vision Workshops (ICCV Workshops),2009 IEEE 12th International Conference on, F Sept.272009-Oct.4 2009,2009 [C].
[85]Kalal Z, Mikolajczyk K, Matas J. Forward-Backward Error:Automatic Detection of Tracking Failures; proceedings of the Pattern Recognition (ICPR),2010 20th International Conference on, F 23-26 Aug.2010,2010 [C].
[86]Vondrak M, Sigal L, Jenkins O C. Dynamical Simulation Priors for Human Motion Tracking [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013,35(1):52-65.
[87]Murray D, Basu A. Motion tracking with an active camera [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1994,16(5):449-459.
[88]Jung Y-K, Lee K-W, Ho Y-S. Feature-Based Object Tracking with an Active Camera [M]//Chen Y-C, Chang L-W, Hsu C-T. Advances in Multimedia Information Processing-PCM 2002. Springer Berlin Heidelberg.2002:1137-1144.
[89]Bartoli A, Dalal N, Horaud R. Motion Panoramas [J]. Computer Animation and Virtual Worlds,2004,15(5):501-517.
[90]Bevilacqua A, Azzari P. A Fast and Reliable Image Mosaicing Technique with Application to Wide Area Motion Detection [M]//Kamel M, Campilho A. Image Analysis and Recognition. Springer Berlin Heidelberg.2007:501-512.
[91]Chung-Hao C, Yi Y, Page D, et al. Heterogeneous Fusion of Omnidirectional and PTZ Cameras for Multiple Object Tracking [J]. Circuits and Systems for Video Technology, IEEE Transactions on,2008,18(8):1052-1063.
[92]Micheloni C, Foresti G L. Real-time image processing for active monitoring of wide areas [J]. Journal of Visual Communication and Image Representation,2006, 17(3):589-604.
[93]Jae Kyu S, Ho Gi J, Gen L, et al. Background Compensation for Pan-Tilt-Zoom Cameras Using 1-D Feature Matching and Outlier Rejection [J]. Circuits and Systems for Video Technology, IEEE Transactions on,2011,21(3):371-377.
[94]Songxiao C, Xuanyin W, Ke X. Visual Object Servo Tracking Based on the Particle Filter Method Using a Pan-Tilt-Zoom Camera [J]. Int J Adv Robotic Sy,2012, 9(134):
[95]Varcheie P, Bilodeau G-A. People tracking using a network-based PTZ camera [J]. Machine Vision and Applications,2011,22(4):671-690.
[96]Choi W, Pantofaru C, Savarese S. A General Framework for Tracking Multiple People from a Moving Camera [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2012, PP(99):1-1.
[97]Kennedy J, C.Eberhart R, Shi Y. Swarm Intelligence [M].2009.
[98]Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II [J]. Evolutionary Computation, IEEE Transactions on,2002, 6(2):182-197.
[99]Kirkpatrick S, Vecchi M. Optimization by simmulated annealing [J]. science,1983, 220(4598):671-680.
[100]Eberhart R, Kennedy J. A new optimizer using particle swarm theory; proceedings of the Micro Machine and Human Science,1995 MHS'95, Proceedings of the Sixth International Symposium on, F 4-6 Oct 1995,1995 [C].
[101]朱志宇.粒子滤波算法及其应用[M].北京：科学出版社,2010.
[102]朱新玲.马尔科夫链蒙特卡罗方法研究综述[J].统计与决策,2009,21)：151-153.
[103]M.Ross S.应用随机过程：概率模型导论(第9版)[M].北京：人民邮电出版社,2007.
[104]Cannons K:York University, Department of Computer Science and Engineering,2008.
[105]Khan S, Shah M. A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint Computer Vision-ECCV 2006 [M]//Leonardis A, Bischof H, Pinz A. Springer Berlin/Heidelberg.2006:133-146.
[106]Yang S. Particle Filtering Based Estimation of Consistent Motion and Disparity with Reduced Search Points [J]. IEEE Trans Circuits Syst Video Technol,2012, 22(1):91-104.
[107]Isard M, Blake A. Contour tracking by stochastic propagation of conditional density-Computer Vision-ECCV'96 [M]//Buxton B, Cipolla R. Springer Berlin/ Heidelberg.1996:343-356.
[108]North B, Blake A, Isard M, et al. Learning and classification of complex dynamics [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000,22(9):1016-1034.
[109]Wu Y, Huang T S, Ieee Computer S. A co-inference approach to robust visual tracking [M]. Los Alamitos:Ieee Computer Soc,2001.
[110]Zhou S H K, Chellappa R, Moghaddam B. Visual tracking and recognition using appearance-adaptive models in particle filters [J]. IEEE Trans Image Process, 2004,13(11):1491-1506.
[111]Lui Y M, Beveridge J R, Whitley L D. Adaptive Appearance Model and Condensation Algorithm for Robust Face Tracking [J]. IEEE Trans Syst Man Cybern Paart A-Syst Hum,2010,40(3):437-448.
[112]Del Bimbo A, Dini F. Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation [J]. Comput Vis Image Underst,2011, 115(6):771-786.
[113]Han B, Zhu Y, Comaniciu D, et al. Visual Tracking by Continuous Density Propagation in Sequential Bayesian Filtering Framework [J]. IEEE Trans Pattern Anal Mach Intell,2009,31(5):919-930.
[114]SPEVI dataset [M].
[115]UCF YouTube Action Dataset [M].
[116]胡士强,敬忠良.粒子滤波原理及应用[M].科学出版社,2010.
[117]Yilmaz A, Javed O, Shah M. Object tracking:A survey [J]. ACM Comput Surv, 2006,38(4):13.
[118]Birchfield S, Ieee Comp S O C. Elliptical head tracking using intensity gradients and color histograms [M].1998 Ieee Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings. Los Alamitos; Ieee Computer Soc.1998:232-237.
[119]Li P H, Chaumette F. Image cues fusion for object tracking based on particle filter [M]//Perales F J, Draper B A. Articulated Motion and Deformable Objects, Proceedings. Berlin; Springer-Verlag Berlin.2004:99-110.
[120]Badrinarayanan V, Perez P, Le Clerc F, et al. Probabilistic color and adaptive multi-feature tracking with dynamically switched priority between cues [M].2007 Ieee 11th International Conference on Computer Vision, Vols 1-6. New York; Ieee. 2007:1000-1007.
[121]Bernardin K, Gehrig T, Stiefelhagen R. Multi-level particle filter fusion of features and cues for audio-visual person tracking [M]//Stiefelhagen R, Bowers R, Fiscus J. Multimodal Technologies for Perception of Humans. Berlin; Springer-Verlag Berlin.2008:70-81.
[122]王永忠,梁彦,赵春晖,潘泉.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4)：393-399.
[123]Maccormick J, Blake A. A probabilistic exclusion principle for tracking multiple objects; proceedings of the Computer Vision,1999 The Proceedings of the Seventh IEEE International Conference on, F 1999,1999 [C].
[124]Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computer interaction:A review [J]. IEEE Trans Pattern Anal Mach Intell, 1997,19(7):677-695.
[125]Erol A, Bebis G, Nicolescu M, et al. Vision-based hand pose estimation:A review [J]. Comput Vis Image Underst,2007,108(1-2):52-73.
[126]Matthieu Bray E K-M, Pascal Muller, Luc Van Gool, Nicol N. Schraudolph. 3D hand tracking by rapid stochastic gradient descent using a skinning model [M]. IN 1ST EUROPEAN CONFERENCE ON VISUAL MEDIA PRODUCTION (CVMP).2004:59-68.
[127]Dewaele G, Devernay F, Horaud R. Hand Motion from 3D Point Trajectories and a Smooth Surface Model [M]//Pajdla T, Matas J. Computer Vision-ECCV 2004. Springer Berlin Heidelberg.2004:495-507.
[128]Davis J, Shah M. Visual gesture recognition [J]. Vision, Image and Signal Processing, IEE Proceedings-,1994,141(2):101-106.
[129]Jintae L, Kunii T L. Model-based analysis of hand posture [J]. Computer Graphics and Applications, IEEE,1995,15(5):77-86.
[130]Starner T, Weaver J, Pentland A. A wearable computer-based American sign Language Recogniser [J]. Personal Technologies,1997,1(4):241-250.
[131]Azoz Y, Devi L, Sharma R. Reliable tracking of human arm dynamics by multiple cue integration and constraint fusion; proceedings of the Computer Vision and Pattern Recognition,1998 Proceedings 1998 IEEE Computer Society Conference on, F 23-25 Jun 1998,1998 [C].
[132]Hardenberg C V, Berard F. Bare-hand human-computer interaction [M]. Proceedings of the 2001 workshop on Perceptive user interfaces. Orlando, Florida; ACM.2001:1-8.
[133]Koike. H, Sato. Y, Kobayashi. Y. Integrating paper and digital information on EnhancedDesk:a method for realtime finger tracking on an augmented desk system [J]. ACM Trans Comput-Hum Interact,2001,8(4):307-322.
[134]Oka K, Sato Y, Koike H. Real-time tracking of multiple fingertips and gesture recognition for augmented desk interface systems; proceedings of the Automatic Face and Gesture Recognition,2002 Proceedings Fifth IEEE International Conference on, F 21-21 May 2002,2002 [C].
[135]Letessier J, Berard F. Visual tracking of bare fingers for interactive surfaces [M]. Proceedings of the 17th annual ACM symposium on User interface software and technology. Santa Fe, NM, USA; ACM.2004:119-122.
[136]Segen J, Kumar S. Gesture VR:vision-based 3D hand interace for spatial interaction [M]. Proceedings of the sixth ACM international conference on Multimedia. Bristol, United Kingdom; ACM.1998:455-464.
[137]O'hagan R G, Zelinsky A, Rougeaux S. Visual gesture interfaces for virtual environments [J]. Interact Comput,2002,14(3):231-250.
[138]Malik S, Laszlo J. Visual touchpad:a two-handed gestural input device [M]. Proceedings of the 6th international conference on Multimodal interfaces. State College, PA, USA; ACM.2004:289-296.
[139]Argyros A A, Lourakis M I A. Vision-based interpretation of hand gestures for remote control of a computer mouse [M]//Huang T S, Sebe N, Lew M S, et al. Computer Vision in Human-Computer Interaction. Berlin; Springer-Verlag Berlin. 2006:40-51.
[140]Jo K H, Kuno Y, Shirai Y, et al. Manipulative hand gesture recognition using task knowledge for human computer interaction [M]. Los Alamitos:Ieee Computer Soc,1998.
[141]Mo Z, Lewis J P, Neumann U. SmartCanvas:a gesture-driven intelligent drawing desk system [M]. Proceedings of the 10th international conference on Intelligent user interfaces. San Diego, California, USA; ACM.2005:239-243.
[142]Hsu R L, Abdel-Mottaleb M, Jain A K. Face detection in color images [J]. IEEE Trans Pattern Anal Mach Intell,2002,24(5):696-706.
[143]Chai D, Ngan K N, Ieee. Locating facial region of a head-and-shoulders color image [M]. Los Alamitos:Ieee Computer Soc,1998.
[144]孙家广,胡事民.计算机图形学基础教程[M].清华大学出版社,2005.
[145]Shapiro A. Monte Carlo Sampling Methods [M]//Ruszczynski A, Shapiro A. Handbooks in Operations Research and Management Science. Elsevier.2003: 353-425.
[146]Graham R L. An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set [J]. Information Processing Letters,1972,1(132-133.