智能视觉监控中多运动目标检测与跟踪方法研究
|
摘要
安全防范领域中已广泛采用视觉传感器监控场景,但大多数系统仍停留在半人工式的模拟监控,迫切需要研制智能化的视觉监控系统,而多运动目标检测、跟踪是智能视觉监控的基础性问题,同时也是关键性的难点问题。本论文主要研究了智能视觉监控系统中多运动目标检测与跟踪方法,首先提出了复杂场景中的目标检测方法,然后针对不同跟踪需求,分析提出了多种目标跟踪方法,最后介绍了自主开发的智能网络视觉监控系统。全文主要工作包括如下几个方面。
论文首先介绍了智能视觉监控的研究背景及意义,并对智能视觉监控系统的构成进行了深入分析,系统详细地阐述了智能视觉监控系统及关键技术的国内外研究现状,并以此为基础,分析了智能视觉监控处理中的难点问题,及阐述本论文的研究意义。
目标检测是智能视觉监控的基础,目标检测的准确性直接影响后续跟踪处理,而复杂场景中存在的大量动态变化对目标检测造成极大干扰,因此,论文第二章在分析了常用的参数化、非参数化背景模型的基础上,将复杂场景中的目标检测问题转化为图像像素标记问题,提出了一种非参数目标检测方法：基于MAP-MRF框架的蚁群优化目标检测方法。首先通过混合核密度估计法估计场景的条件概率分布,在马尔可夫随机场(MRF)中得到像素标记的先验概率,并据此推导出后验能量函数,即建立了MAP-MRF框架,采用蚁群算法优化后验能量函数,从而得到像素标记结果,实现了非阈值化、上下文关联的目标检测,在视频序列上的实验结果表明该方法鲁棒性高,能较好地适应场景中的复杂动态变化,准确、有效地检测运动目标。
在检测出目标区域后,可在目标区域提取特征进行目标跟踪。监控场景中的多运动目标往往具有不同外观特征,基于外观模型跟踪多目标是一种常用的跟踪方法,但如何建立有效的外观模型是难点问题。论文第三章分析了目标模型中常用的颜色、运动特征,并结合人体的身体部分间的空间结构特征,提出利用属性关系图建立人体外观模型；为在连续帧间匹配目标,根据推导计算的属性关系图外观模型的相似度,建立匹配矩阵,分析了四种不同的匹配情况下的跟踪策略,如判定多人体相互遮挡,则通过概率松弛法优化匹配遮挡人体的身体部分及上帧的跟踪标记,从而实现遮挡情况下的多人体跟踪。通过比较该方法与其他典型的外观跟踪方法在多个视频序列上的跟踪结果、性能指标,验证了该方法跟踪不同人体外观的有效性、准确性。
传统的基于目标检测——目标特征的跟踪方法依赖于目标检测结果的准确性,而常用的目标检测方法,即便采用形态学滤波等方法对检测结果进行后处理,仍无法做到完全检测出完整的目标,常常存在目标“碎片”或“空洞”,影响后续跟踪的准确性、有效性。论文第四章在前景目标检测结果存在目标“碎片”和“空洞”的情况下,提出了一种优化碎片标记的多运动目标跟踪方法。首先将上一帧跟踪目标划分成“目标碎片”,并赋予跟踪标记,再将当前帧前景区域也划分成具有特征一致性的“前景碎片”,在当前帧将目标碎片的跟踪标记随机分配给前景碎片,则多目标跟踪问题转化为前景碎片的标记优化问题；建立前景碎片的属性关系图及与其标记相同的上一帧目标碎片的属性关系图,采用概率松弛法分析得到前景碎片标记优化的目标函数,并通过遗传算法优化,给前景碎片分配最优的跟踪标记,即可通过前景碎片的跟踪标记进一步分割出完整目标区域的同时完成了目标识别、跟踪。在室内外监控视频序列上实验结果表明,该方法能在前景检测结果存在“碎片”、“空洞”的情况下,准确、有效地跟踪多运动目标。
在监控范围大,运动目标外观特征少或者外观相似的情况下,数据关联是跟踪能否实现的关键问题。论文第五章仅采用目标运动特征,提出一种改进联合概率数据关联的多目标快速跟踪方法,采用简化murty算法求联合概率数据关联(JPDA)的最优K个联合事件,能大大降低计算复杂度,避免在目标较多时的关联匹配呈指数增加,讨论了在目标新出现、消失、遮挡、分离(包括前景检测不准确造成的碎片)等复杂情况下当前帧量测与跟踪目标的数据关联、目标状态估计,从而有效实现了多目标复杂运动的快速跟踪。在标准数据库上的实验证明,该方法能在大范围复杂场景中有效跟踪多个外观相似且外观区域小的目标,跟踪精度比传统JPDA方法大大提高,并能实现实时快速跟踪。
论文第六章介绍了本课题组自主开发的智能化网络视觉监控系统及其软、硬件构成和基本功能,通过实际系统的开发,为本论文的算法研究提供了思路,并为算法的实际应用提供了实验平台。
论文最后总结了全文的主要工作和创新性的研究成果,并对下一步研究工作进行了展望。
In recent decades, since vision sensors have been used extensively in the field of safety precautions, it's vitally necessary to develop the intelligent visual surveillance system which can replace the traditional passive surveillance system that uses analog vision in the semi-manual mode. Most importantly, though, detecting and tracking multiple moving objects are two basic elements in the intelligent visual surveillance system and key difficult points as well. This dissertation focuses on the methods of detecting and tracking multiple moving objects. A method of detecting objects in complex scenes is presented, and three methods of tracking objects are proposed according to different tracking requirements, moreover, an intelligent network visual surveillance system is independently developped to verify these methods. Main results and contributions of this dissertation are as follows:
In chapter 1, the research background of intelligent visual surveillance is introduced firstly. Then, the composition of the intelligent visual surveillance system is analyzed, and the research progresses of key technologies in intelligent visual surveillance are generalized. Furthermore, on the basis of the research, the difficult problems in visual surveillance are discussed and the research significance of this dissertation is also presented.
Nearly every intelligent visual surveillance system starts with object detection, and the performance of tracking objects depends on the accuracy of object detection. Because the background is usually cluttered and not completely static in the real world, it is difficult to detect objects accurately by the traditional method of background subtraction. In chapter 2, on the basis of analyzing traditional parametric models and non-parametric models, we propose an object detection approach using Ant Colony System (ACS) in a MAP-MRF framework. The MAP-MRF framework is built by the conditional probability of scenes computed by the mixed kernel density estimation method and the prior probability of pixel labels acquired in Markov Random Field (MRF). Then, the problem of optimizing pixel labels is represented as the problem of minimizing posterior energy function in the MAP-MRF framework which is implemented by the ACS algorithm. Consequently, multiple objects are detected efficiently according to the optimal pixel labels in the current frame. Extensive experiments show the utility and performance of the proposed approach.
After motion detection, surveillance systems generally track moving objects based on features extracted in the detected regions of objects. Because the appearance of objects is usually different, the appearance model is a traditional method for tracking multiple persons, but the main difficulty is to represent appearance reliably and effectively, especially in presence of occlusions. The traditional appearance model containing color and motion features is introduced in chapter 3, and then, an effective tracking algorithm based on attributed relational graph (ARG) is used to track multiple persons even under occlusions. The appearance of each person is expressed by an ARG model which not only combines color feature with spatial information but also illustrates the relations among body parts. The similarity of ARG models is computed to build a matching matrix in consecutive frames. Four tracking situations are determined according to the matching matrix. In addition, in order to track persons under occlusions, probabilistic relaxation labeling in the ARG models of body parts is deduced to label occluded persons optimally. Experimental validation of the proposed tracking method is verified on indoor and outdoor sequences.
In chapter 4, a novel algorithm is proposed for tracking multiple objects even if the regions of detecting objects are incomplete. According to color and spatial features, the tracked objects in the previous frame and the foreground regions in the current frame are divided into 'object patches' and 'foreground patches' respectively. We consider the problem of object tracking as the problem of optimizing labels of foreground patches. Attributed relational graph (ARG) is employed to describe appearance and structural features of object models and foreground patches, then, the optimized objective function is formed by the matching degree of these ARGs which is solved by probability relaxation. The genetic algorithm is used to compute the objective function to get optimized labels of foreground pixels, therefore, multiple objects is recognized and tracked successfully according to these labels. The experimental results perform suitably in several challenging image sequences with less foreground accuracy, which show that the proposed approach is promising.
It is difficult to solve the problem of data association if objects with little distinguishable features are tracked in large-scale monitoring scenes. In chapter 5, we present a method of tracking multiple objects in real-time based on improved Joint Probabilistic Data Association (JPDA) which only uses objects'motion features. The k-best joint events are computed by the simplified murty algorithm which reduces the complexity. Data association is handled according to the association probability of JPDA even when objects enter and exit the field of view, merge and split (objects are detected as fragments). The experimental results are obtained on the standard video databases. It is shown that the method realizes tracking multiple low-resolution objects effectively in real-time and the performance is improved more greatly than the traditional JPDA method.
In chapter 6, an intelligent network visual surveillance system is developed, and the software and hardware structure of this system is introduced. This system provides us ideas to present these methods in this dissertation, and it can be used as an experiment platform to verify methods.
Finally, the main innovations of the dissertation are summarized, and the fields for further research are prospected at the end of the dissertation.
论文首先介绍了智能视觉监控的研究背景及意义,并对智能视觉监控系统的构成进行了深入分析,系统详细地阐述了智能视觉监控系统及关键技术的国内外研究现状,并以此为基础,分析了智能视觉监控处理中的难点问题,及阐述本论文的研究意义。
目标检测是智能视觉监控的基础,目标检测的准确性直接影响后续跟踪处理,而复杂场景中存在的大量动态变化对目标检测造成极大干扰,因此,论文第二章在分析了常用的参数化、非参数化背景模型的基础上,将复杂场景中的目标检测问题转化为图像像素标记问题,提出了一种非参数目标检测方法：基于MAP-MRF框架的蚁群优化目标检测方法。首先通过混合核密度估计法估计场景的条件概率分布,在马尔可夫随机场(MRF)中得到像素标记的先验概率,并据此推导出后验能量函数,即建立了MAP-MRF框架,采用蚁群算法优化后验能量函数,从而得到像素标记结果,实现了非阈值化、上下文关联的目标检测,在视频序列上的实验结果表明该方法鲁棒性高,能较好地适应场景中的复杂动态变化,准确、有效地检测运动目标。
在检测出目标区域后,可在目标区域提取特征进行目标跟踪。监控场景中的多运动目标往往具有不同外观特征,基于外观模型跟踪多目标是一种常用的跟踪方法,但如何建立有效的外观模型是难点问题。论文第三章分析了目标模型中常用的颜色、运动特征,并结合人体的身体部分间的空间结构特征,提出利用属性关系图建立人体外观模型；为在连续帧间匹配目标,根据推导计算的属性关系图外观模型的相似度,建立匹配矩阵,分析了四种不同的匹配情况下的跟踪策略,如判定多人体相互遮挡,则通过概率松弛法优化匹配遮挡人体的身体部分及上帧的跟踪标记,从而实现遮挡情况下的多人体跟踪。通过比较该方法与其他典型的外观跟踪方法在多个视频序列上的跟踪结果、性能指标,验证了该方法跟踪不同人体外观的有效性、准确性。
传统的基于目标检测——目标特征的跟踪方法依赖于目标检测结果的准确性,而常用的目标检测方法,即便采用形态学滤波等方法对检测结果进行后处理,仍无法做到完全检测出完整的目标,常常存在目标“碎片”或“空洞”,影响后续跟踪的准确性、有效性。论文第四章在前景目标检测结果存在目标“碎片”和“空洞”的情况下,提出了一种优化碎片标记的多运动目标跟踪方法。首先将上一帧跟踪目标划分成“目标碎片”,并赋予跟踪标记,再将当前帧前景区域也划分成具有特征一致性的“前景碎片”,在当前帧将目标碎片的跟踪标记随机分配给前景碎片,则多目标跟踪问题转化为前景碎片的标记优化问题；建立前景碎片的属性关系图及与其标记相同的上一帧目标碎片的属性关系图,采用概率松弛法分析得到前景碎片标记优化的目标函数,并通过遗传算法优化,给前景碎片分配最优的跟踪标记,即可通过前景碎片的跟踪标记进一步分割出完整目标区域的同时完成了目标识别、跟踪。在室内外监控视频序列上实验结果表明,该方法能在前景检测结果存在“碎片”、“空洞”的情况下,准确、有效地跟踪多运动目标。
在监控范围大,运动目标外观特征少或者外观相似的情况下,数据关联是跟踪能否实现的关键问题。论文第五章仅采用目标运动特征,提出一种改进联合概率数据关联的多目标快速跟踪方法,采用简化murty算法求联合概率数据关联(JPDA)的最优K个联合事件,能大大降低计算复杂度,避免在目标较多时的关联匹配呈指数增加,讨论了在目标新出现、消失、遮挡、分离(包括前景检测不准确造成的碎片)等复杂情况下当前帧量测与跟踪目标的数据关联、目标状态估计,从而有效实现了多目标复杂运动的快速跟踪。在标准数据库上的实验证明,该方法能在大范围复杂场景中有效跟踪多个外观相似且外观区域小的目标,跟踪精度比传统JPDA方法大大提高,并能实现实时快速跟踪。
论文第六章介绍了本课题组自主开发的智能化网络视觉监控系统及其软、硬件构成和基本功能,通过实际系统的开发,为本论文的算法研究提供了思路,并为算法的实际应用提供了实验平台。
论文最后总结了全文的主要工作和创新性的研究成果,并对下一步研究工作进行了展望。
In recent decades, since vision sensors have been used extensively in the field of safety precautions, it's vitally necessary to develop the intelligent visual surveillance system which can replace the traditional passive surveillance system that uses analog vision in the semi-manual mode. Most importantly, though, detecting and tracking multiple moving objects are two basic elements in the intelligent visual surveillance system and key difficult points as well. This dissertation focuses on the methods of detecting and tracking multiple moving objects. A method of detecting objects in complex scenes is presented, and three methods of tracking objects are proposed according to different tracking requirements, moreover, an intelligent network visual surveillance system is independently developped to verify these methods. Main results and contributions of this dissertation are as follows:
In chapter 1, the research background of intelligent visual surveillance is introduced firstly. Then, the composition of the intelligent visual surveillance system is analyzed, and the research progresses of key technologies in intelligent visual surveillance are generalized. Furthermore, on the basis of the research, the difficult problems in visual surveillance are discussed and the research significance of this dissertation is also presented.
Nearly every intelligent visual surveillance system starts with object detection, and the performance of tracking objects depends on the accuracy of object detection. Because the background is usually cluttered and not completely static in the real world, it is difficult to detect objects accurately by the traditional method of background subtraction. In chapter 2, on the basis of analyzing traditional parametric models and non-parametric models, we propose an object detection approach using Ant Colony System (ACS) in a MAP-MRF framework. The MAP-MRF framework is built by the conditional probability of scenes computed by the mixed kernel density estimation method and the prior probability of pixel labels acquired in Markov Random Field (MRF). Then, the problem of optimizing pixel labels is represented as the problem of minimizing posterior energy function in the MAP-MRF framework which is implemented by the ACS algorithm. Consequently, multiple objects are detected efficiently according to the optimal pixel labels in the current frame. Extensive experiments show the utility and performance of the proposed approach.
After motion detection, surveillance systems generally track moving objects based on features extracted in the detected regions of objects. Because the appearance of objects is usually different, the appearance model is a traditional method for tracking multiple persons, but the main difficulty is to represent appearance reliably and effectively, especially in presence of occlusions. The traditional appearance model containing color and motion features is introduced in chapter 3, and then, an effective tracking algorithm based on attributed relational graph (ARG) is used to track multiple persons even under occlusions. The appearance of each person is expressed by an ARG model which not only combines color feature with spatial information but also illustrates the relations among body parts. The similarity of ARG models is computed to build a matching matrix in consecutive frames. Four tracking situations are determined according to the matching matrix. In addition, in order to track persons under occlusions, probabilistic relaxation labeling in the ARG models of body parts is deduced to label occluded persons optimally. Experimental validation of the proposed tracking method is verified on indoor and outdoor sequences.
In chapter 4, a novel algorithm is proposed for tracking multiple objects even if the regions of detecting objects are incomplete. According to color and spatial features, the tracked objects in the previous frame and the foreground regions in the current frame are divided into 'object patches' and 'foreground patches' respectively. We consider the problem of object tracking as the problem of optimizing labels of foreground patches. Attributed relational graph (ARG) is employed to describe appearance and structural features of object models and foreground patches, then, the optimized objective function is formed by the matching degree of these ARGs which is solved by probability relaxation. The genetic algorithm is used to compute the objective function to get optimized labels of foreground pixels, therefore, multiple objects is recognized and tracked successfully according to these labels. The experimental results perform suitably in several challenging image sequences with less foreground accuracy, which show that the proposed approach is promising.
It is difficult to solve the problem of data association if objects with little distinguishable features are tracked in large-scale monitoring scenes. In chapter 5, we present a method of tracking multiple objects in real-time based on improved Joint Probabilistic Data Association (JPDA) which only uses objects'motion features. The k-best joint events are computed by the simplified murty algorithm which reduces the complexity. Data association is handled according to the association probability of JPDA even when objects enter and exit the field of view, merge and split (objects are detected as fragments). The experimental results are obtained on the standard video databases. It is shown that the method realizes tracking multiple low-resolution objects effectively in real-time and the performance is improved more greatly than the traditional JPDA method.
In chapter 6, an intelligent network visual surveillance system is developed, and the software and hardware structure of this system is introduced. This system provides us ideas to present these methods in this dissertation, and it can be used as an experiment platform to verify methods.
Finally, the main innovations of the dissertation are summarized, and the fields for further research are prospected at the end of the dissertation.
引文
[1]韩绍超.2001-2005中国安防产品市场回顾.http://www.bspia.com/news/ project/2006-11/17/17091339852.htm,2006-11-17
[2]国内安防行业现状.http://www.anfangnet.com/gushi/20090119/5221.html, 2009-1-19
[3]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报,2002,25(3)：225-237
[4]Haritaoglu I, Harwood D, Davis L. W4:Real-time surveillance of people and their activities. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830
[5]Collins R, Lipton A, Kanade T, et al. A system for video surveillance and monitoring:VSAM final report. Technical CMU-RI-TR-00-12,2000
[6]Remagnino P, Tan T, Baker K. Multi-agent visual surveillance of dynamic scenes. Image and Vision Computing,1998,16(8):529-532
[7]Wren R, Azarbayejani A, Darrell T, et al. Pfinder:real-time tracking of the human body. IEEE Trans on Pattern Analysis and Machine Intelligence,1997, 19(7):780-785
[8]Lipton A J, Fujiyoshi H, Patil R S. Moving target classification and tracking from real-time video. In:Proc of IEEE Workshop on Applications of Computer Vision. Princeton,1998,8-14
[9]Detec-your security. http://www.detec.no/sider/start.htm
[10]Remagnino P, Jones G A, Paragios N, et al. Video-based Surveillance Systems. Boston:Kluwer Academic Publishers,2000:39-51
[11]Pavlids I, Morellas V. Tsiamyrtzis P, et al. Urban surveillance system:from the laboratory to the commercial world. In:Proc of IEEE,2001,89(10): 1478-1497
[12]Prahge J D. Detecting, Recognizing and Understanding Video Events in Surveillance Video. In:Proc of the IEEE Conf on Advanced Video and Signal Based Surveillance. Miami,2003,48-57
[13]Yu JJ, Dai J S, Bi Shusheng, et al. Numeration and type synthesis of 3-DOF orthogonal translational parallel manipulators. Progress in Natural Science,2008,18(5):563-574
[14]庄越挺,刘小明,潘云鹤,等.运动图象序列的人体三维运动骨架重建.计算机辅助设计与图形学报,2000,12(4)：246-250
[15]吴江琴,高文.给于DGMM的中国手语识别系统.计算机研究与发展,2000,37(5)：551-558
[16]Hu W M, Xiao X J, Fu Z Y, et al. A system for learning statistical motion patterns. IEEE Trans on Pattern Analysis and Machine Intelligence,2006, 28(9):1450-1464
[17]Friedman N, Russell S. Image segmentation in video sequences:a probabilistic approach. In:Proc of 13th Conf Uncertainty in Artificial Intelligence. Providence,1997,175-181
[18]McKenna S, Jabri S, Duric Z, et al. Tracking groups of people. Computer Vision and Image Understanding,2000,80(1):42-56
[19]Stauffer C, Grimson W. Leaning patterns of activity using real-time tracking. IEEE Trans on pattern analysis and machine intelligence,2000,22(8):747-757
[20]Elgammal A, Harwood D. Non-parametric model for background subtraction. In:Proc of European Conf on Computer Vision. Dublin,2000,751-767
[21]Tian T Y, Tomasi C, Heeger D J. Comparison of approaches to egomotion computation. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition, San Francisco,1996,315-320
[22]Ying R, Chua C S.Ho Y K. Motion detection with nonstationary background. In:Proc of 11th Int Conf on Image Analysis and Processing. Palermo,2001,78-83
[23]Gargallo P, Sturm P. Bayesian 3D modeling from images using multiple depth maps. In:Proc of IEEE Computer Society Conf on Computer Vision and Pattern Recognition. San Diego,2005,885-891
[24]Arseneau S, Cooperstock J. Real-time image segmentation for action recognition. In:Proc of IEEE Pacific Rim Conference on Communications, Computers and Signal Processing. Victoria,86-89
[25]Hogg D, Model-based vision:A program to see a walking person. Image and Vision Computing,1995,1:5-20
[26]王栓,艾海舟,何克忠.基于差分图象的多运动目标的检测与跟踪.中国图象图形学报,1999,4(6)：1057-1012
[27]Sidenbladh H. Detecting human motion with support vector machines. In: Proc of Int Conf on Pattern Recognition. Cambridge,2004,188-191
[28]Utsumi A, Mori H, Ohya J, et al. Multiple-view-based tracking of multiple humans. In:Proc of Int Conf Pattern Recognition. Brisbane,1998,197-601
[29]Prati A, Mikic I, Trivedi M M, et al. Detecting moving shadows:algorithms and evaluation. IEEE Trans on PatternAnalysis and Machine Intelligence, 2003,25 (7):918-923
[30]Schindler K, Wang H. Smooth foreground-background segmentation for video processing. In:Proc of Asian Conf on Computer Vision. Hyderabad, India, 2006,581-590
[31]Sheikh Y, Shah M. Bayesian modeling of dynamic scenes for object detection. IEEE Trans on Pattern Analysis and Machine Intelligence,2005, 27(11):1778-1792
[32]Chen, Maolin M, Gengyu K, Seokcheol. Pixels classification for moving object extraction. In:Proc of IEEE Workshop on Motion and Video Computing. Breckenridge,2005,44-49
[33]Cucchiara R, Grana C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(10):1337-1342
[34]McKenna S J, Jabri S, Duric Z, et al. Tracking interacting People. In:Proc of Int Conf on Automatic Face and Gesture Recognition. Grenoble, 2000,348-353
[35]Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV Color Information. In:Proc of IEEE Int Conf on Intelligent Transportation Systems. Oakland,2001,334-339
[36]Eng H L, Toh K A, Kam A H, et al. An automatic drowning detection surveillance system for challenging outdoor pool environments. In:Proc of IEEE Int Conf on Computer Vision. Nice,2003,532-536
[37]Kuno Y, Watanabe T, Shimosakoda Y, et al. Automated detection of human for visual surveillance system. In:Proc of Int Conf Pattern Recognition. Vienna,1996,865-869
[38]Jang D S, Choi H I. Active models for tracking moving objects. Pattern Recognition,2000,33(7):1135-1146
[39]Zhao L, Davis L S. Closely coupled object detection and segmentation. In: Proc of Int Conf on Computer Vision. Beijing,2005,454-461
[40]Plankers R, Fua P. Articulated soft objects for video-based body modeling. In:Proc of Int Conf on Computer Vision. Vancouver,2001,394-401
[41]Carranza J, Theobalt C, Magnor M, Seidel H P. Free-viewpoint video of human actors. In:Proc of ACM SIGGRAPH,2003,565-577
[42]Song Y, Goncalves L, Perona P. Unsupervised learning of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7): 814-827
[43]Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proc of Computer Vision and Pattern Recognition. San Diego,2005,886-893
[44]Starck J, Hilton A. Model-based multiple view reconstruction of people. In: Int Conf on Computer Vision. Nice,2003,13-16
[45]Roberts T J, McKenna S J, Ricketts I W. Adaptive learning of statistical appearance models for 3D human tracking. In:Proc of British Machine Vision Conference. Cardiff,2002,333-342
[46]Karaulova I A, Hall P M, Marshall A D. A hierarchical model of dynamics for tracking people with a single video camera. In:Proc of British Machine Vision Conf. Bristol,2000,262-352
[47]Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with physical forces. Computer Vision and Image Understanding,2001, 81(3):328-357
[48]Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with silhouettes. In:Proc of Int Conf on Computer Vision. Kerkyra,1999,716-721
[49]Sminchisescu C, Triggs B. Covariance scaled sampling for monocular 3D body tracking. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition,2001,447-454
[50]Hu W M, Tan T N, Wang L, et al. A survey on visual surveillance of object motion and behaviors. IEEE Trans on Systems Man and Cybernetics,34(3): 334-353
[51]Malik J, Russell S, Weber J,et al. A machine vision based surveillance system for Californaia roads. University of California, PATH project MOU-83 Final Report,1994
[52]Cucchiara R, Grana C, Tardini G, et al. Probabilistic people tracking for occlusion handling. In:Proc of Int Conf on Pattern Recognition. Cambridge, 2004,132-135
[53]Polat E, Yeasin M, Sharma R. Robust tracking of human body parts for collaborative human computer interaction. Computer Vision and Image Understanding,2003,89:44-69
[54]Hoshino J, Yamamoto M, Saito H. A match moving technique for merging CG cloth and human video sequences. Journal of Visualization and Computer Animation,2001,12(1):23-29
[55]Isard M, Blake A. Condensation—conditional density propagation for visual tracking. International Journal on Computer Vision,1998,29 (1):5-28
[56]Green P J. Highly structured stochastic systems. Chapter Transdimensional Markov Chain Monte Carlo, Oxford University Press,2003
[57]Smith K, Perez D G, Odobez J M. Using particles to track varying numbers of interacting people. In:Proc of Computer Vision and Pattern Recognition. San Diego,2005,877-880
[58]Li Y, Hilton A, Illingworth J. A relaxation algorithm for real-time multiple view 3D-tracking. Image and Vision Computing,2002,20(12):841-859
[59]Khan S, Shah M. Tracking people in presence of occlusion. In:Proc of Asian Conference on Computer Vision. Taiwan,2000,1132-1137
[60]Park S, Aggarwal J.K. Recognition of human interaction using multiple features in grayscale images. In:Proc of Int Conf on Pattern Recognition. Barcelona,2000,51-54
[61]Cutler R, Davis L S. Robust real-time periodic motion detection, analysis, and applications. IEEE Trans on Pattern Analysis and Machine Intelligence,2000, 22:781-796
[62]Yang H D, Lee S W. Multiple pedestrian detection and tracking based on weighted temporal texture features. In:Int Conf on Pattern Recognition. Cambridge,2004,248-251
[63]Xu L Q, Puig P. A hybrid blob and appearance-based framework for multi-object tracking through complex occlusions. In:Proc of Int Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Beijing,2005,73-80
[64]Zhang Z Y. Modeling geometric structure and illumination variation of a scene from real images. In:Proc of Int Conf on Computer Vision. Bombay,1998, 4-7
[65]Tan T N, Sullivan G D, Baker K D. Model-based localization and recognition of road vehicles. International Journal of Computer Vision,1998,29(1):22-25
[66]Billard A, Epars Y, Calinon S, et al. Discovering optimal imitation strategies. Robotics and Autonomous Systems,2004,47:69-77
[67]Calinon S, Billard A. Stochastic gesture production and recognition model for a humanoid robot. In:Proc of Int Conf on Intelligent Robots and Systems. Alberta,2005,2769-2774
[68]Yu X, Yang S X. A study of motion recognition from video sequences. Computing and Visualization in Science,2005,8:19-25
[69]Malik J, Russell S. Traffic Surveillance and Detection Technology Development:New Traffic Sensor Technology. Univ. of California, Berkeley, California PATH Research Final Rep.,1997
[70]Polana R, Nelson R. Low level recognition of human motion. In:P roc of IEEE Work shop on Motion of Non-Rigid and Articulated Objects. Austin, 1994,77-82
[71]Bobick A, Davis J. Realtime recognition of activity using temporal templates. In:Proc of IEEE Work shop on Applications of Computer Vision, Sarasota, 1996,39-42
[72]Bregler C. Learning and recognizing human dynamics in video sequences. In: Proc of IEEE Conf on Computer Vision and Pattern Recognition, Puerto Rico, 1997,568-574
[73]Kojima A, Izumi M, Tamura T, et al. Generating natural language description of human behaviors from video images. In:Proc of IEEE International Conference on Pattern Recognition. Barcelona,2000,728-731
[74]Koller D, Weber J, Huang T, et al. Towards robust automatic traffic scene analysis in real-time. In:Proc of IEEE Conference on Decision and Control. Lake Buena Vista,1994,3776-3781
[75]Webb A R.统计模式识别(第二版).王萍,杨培龙,罗颖昕.北京：电子工业出版社,2004,65-96
[76]Mittal. A, Paragios. N. Motion-based background subtraction using adaptive kernel density estimation. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition. Washington DC,2004,302-309
[77]龚光鲁,钱敏平.应用随机过程教程及在算法和智能计算中的随机模型.北京：清华大学出版社,2004,209-230
[78]刘晓翔.卫星多源遥感图像融合技术的研究：[西北工业大学硕士学位论文].西安：西北工业大学,2004,39—60
[79]罗述谦,周果宏.医学图象处理与分析.北京：科学出版社,2003,106-107
[80]熊和金,陈德军.智能信息处理.北京：国防工业出版社,2006,141-183
[81]Spagnolo P, Orazio T D, Leo M, et al. Moving object segmentation by background subtraction and temporal analysis. Image and Vision Computing, 2006,24:411-423
[82]Hu M, Hu W, Tan T. Tracking people through occlusion. In:Proc of Int Conf on Pattern Recognition. Cambridge,2004,724-727
[83]Wang H, Suter D, Schindler K. Adaptive object tracking based on an effective appearance filter. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007,9(29):1661-1667
[84]Capellader M B, Doermann D, DeMenthon D, et al. An appearance based approach for human and object tracking. In:Proc of Int Conf on Image Processing, Barcelona,2003,85-88
[85]Zhao Q, Tao H. Object tracking using color correlogram. In:Proc of IEEE Int Workshop on VS-PETS. Beijing,2005,263-270
[86]Park S, Aggarwal J K. Simultaneous tracking of multiple body parts of interacting persons. Computer Vision and Image Understanding,2006, 1(102):1-21
[87]Tang F, Tao H. Object tracking with dynamic feature graph. In:Proc of IEEE Int Workshop on VS-PETS. Beijing,2005,25-32
[88]章毓晋.图像工程(上册)——图像处理(第2版).北京：清华大学出版社,2006,158-179
[89]李国辉,柳伟,曹莉华.一种基于颜色特征的图像检索方法.中国图象图形学报,1999,4(3)：248-251
[90]Swain M J, Ballard D H. Color indexing. International Journal of Computer Vision,1991,7(1):1127-1138
[91]Forsyth D A, Ponce J. Computer vision:a modern approach. NJ:Prentice Hall,2003,58-102
[92]马颂德,张正友著.计算机视觉——计算理论与算法基础.北京：科学出版社,2003：81-110
[93]Eshera M A, Fu K S. A graph distance measure for image analysis. IEEE Trans on Systems, Man, and Cybernetics,1984,3(14):398-408
[94]Xu X G, Sun Z X, Liu W Y. Matching spatial relation graphs using a constrained partial permutation strategy. Journal of Southeast Universtiy (English Edition),2003,19(3):236-239
[95]徐雷.模拟退火组合优化法在模式识别中的若干应用.自动化学报,1989,15(2)：114-121
[96]Graciano A B V, Cesar R M, Bloch I,et al. Graph-based object tracking using structural pattern recognition. In:Proc of Computer Graphics and Image Processing. Minas Gerais,2007,179-186
[97]Christmas W J, Kittler J. Structural matching in computer vision using probabilistic relaxation. IEEE Trans on Pattern Analysis and Machine Intelligence,1995,8(17):749-764
[98]Sonka M, Hlavac V, Boyle R.图像处理、分析与机器视觉(第二版).艾海舟,武勃.北京：人民邮电出版社,2003,275-285
[99]KaewTrakulPong P, Bowden R. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image and Vision Computing,2003,21:913-929
[100]Cavallaro A, Steiger O, Ebrahimi T. Tracking video objects in cluttered background. IEEE Trans on Circuits and Systems for Video Technology,2005, 15(4):575-584
[101]乔长阁,高德远.分配问题的计算机方法.计算机研究与发展1995,32(6)：29-34
[102]韩中庚.用“匈牙利算法”求解一类最优化问题.信息工程大学学报,2004,35(1)：60-62
[103]Carpaneto G, Toth P. Solution of the assignment problem. ACM Transactions on Mathematical Software,1980,6(1):104-111
[104]Conte D, Foggia P, Jolion J M, et al. A graph-based, multi-resolution algorithm for tracking objects in presence of occlusions.2006,39:562-572
[105]Fuentes L M, Velastin S A. People tracking in surveillance applications. Image and Vision Computing,2006,24:1165-1171
[106]Zhao J W, Wang P, Liu C Q. An object tracking algorithm based on occlusion mesh model. In:Proc of Int Conf Machine Learning and Cybernetics,2002, 288-292
[107]李正周,金钢,董能力.基于改进概率数据关联滤波的红外小目标运动目标跟踪.电子与信息学报,2008,30(4)：953-956
[108]耿峰,祝小平.一种改进的多传感器多目标跟踪联合概率数据关联算法研究.系统仿真学报,2007,19(20)：4671-4675
[109]Setubal J. Sequential and parallel experimental results with bipartite matching algorithms. Institute of Computing, State University of Campinas, Brazil, 1996
[110]韩崇昭,朱洪艳,段战胜.多源信息融合.北京：清华大学出版社,2006,297-302
[111]Fisher J L, Casasent D P. Fast JPDA multitarget tracking algorithm. Applied Optics,1989,28(2),371-376
[112]Cox I J, Hingorani S. An efficient implemantation of reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans on Pattern Analysis and Machine Intelligence,1996, 18(2):138-150
[113]卢开澄,卢华明.图论及其应用(第2版).北京：清华大学出版社,2005,189-202
[114]王磊.网络视频监控系统的关键设备研究：[湖南大学硕士学位论文].长沙：湖南大学,2008,18-78
[115]崔波亮.网络化视频监控系统中流媒体技术研究：[湖南大学硕士学位论文].长沙：湖南大学,2008,44-59
[116]王耀南,王磊,陈斯斯,万琴,崔波亮.智能视觉监控方法和装置.中国专利.发明专利申请号：200710035636.X
[117]Gonzalez R C, Woods R E.数字图像处理(第二版).阮秋琦,阮宇智.北京：电子工业出版社,2003,412-414
[118]张蒲生,何升.SQL Server数据库应用技术.北京：清华大学出版社,2005,27-44
[2]国内安防行业现状.http://www.anfangnet.com/gushi/20090119/5221.html, 2009-1-19
[3]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报,2002,25(3)：225-237
[4]Haritaoglu I, Harwood D, Davis L. W4:Real-time surveillance of people and their activities. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830
[5]Collins R, Lipton A, Kanade T, et al. A system for video surveillance and monitoring:VSAM final report. Technical CMU-RI-TR-00-12,2000
[6]Remagnino P, Tan T, Baker K. Multi-agent visual surveillance of dynamic scenes. Image and Vision Computing,1998,16(8):529-532
[7]Wren R, Azarbayejani A, Darrell T, et al. Pfinder:real-time tracking of the human body. IEEE Trans on Pattern Analysis and Machine Intelligence,1997, 19(7):780-785
[8]Lipton A J, Fujiyoshi H, Patil R S. Moving target classification and tracking from real-time video. In:Proc of IEEE Workshop on Applications of Computer Vision. Princeton,1998,8-14
[9]Detec-your security. http://www.detec.no/sider/start.htm
[10]Remagnino P, Jones G A, Paragios N, et al. Video-based Surveillance Systems. Boston:Kluwer Academic Publishers,2000:39-51
[11]Pavlids I, Morellas V. Tsiamyrtzis P, et al. Urban surveillance system:from the laboratory to the commercial world. In:Proc of IEEE,2001,89(10): 1478-1497
[12]Prahge J D. Detecting, Recognizing and Understanding Video Events in Surveillance Video. In:Proc of the IEEE Conf on Advanced Video and Signal Based Surveillance. Miami,2003,48-57
[13]Yu JJ, Dai J S, Bi Shusheng, et al. Numeration and type synthesis of 3-DOF orthogonal translational parallel manipulators. Progress in Natural Science,2008,18(5):563-574
[14]庄越挺,刘小明,潘云鹤,等.运动图象序列的人体三维运动骨架重建.计算机辅助设计与图形学报,2000,12(4)：246-250
[15]吴江琴,高文.给于DGMM的中国手语识别系统.计算机研究与发展,2000,37(5)：551-558
[16]Hu W M, Xiao X J, Fu Z Y, et al. A system for learning statistical motion patterns. IEEE Trans on Pattern Analysis and Machine Intelligence,2006, 28(9):1450-1464
[17]Friedman N, Russell S. Image segmentation in video sequences:a probabilistic approach. In:Proc of 13th Conf Uncertainty in Artificial Intelligence. Providence,1997,175-181
[18]McKenna S, Jabri S, Duric Z, et al. Tracking groups of people. Computer Vision and Image Understanding,2000,80(1):42-56
[19]Stauffer C, Grimson W. Leaning patterns of activity using real-time tracking. IEEE Trans on pattern analysis and machine intelligence,2000,22(8):747-757
[20]Elgammal A, Harwood D. Non-parametric model for background subtraction. In:Proc of European Conf on Computer Vision. Dublin,2000,751-767
[21]Tian T Y, Tomasi C, Heeger D J. Comparison of approaches to egomotion computation. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition, San Francisco,1996,315-320
[22]Ying R, Chua C S.Ho Y K. Motion detection with nonstationary background. In:Proc of 11th Int Conf on Image Analysis and Processing. Palermo,2001,78-83
[23]Gargallo P, Sturm P. Bayesian 3D modeling from images using multiple depth maps. In:Proc of IEEE Computer Society Conf on Computer Vision and Pattern Recognition. San Diego,2005,885-891
[24]Arseneau S, Cooperstock J. Real-time image segmentation for action recognition. In:Proc of IEEE Pacific Rim Conference on Communications, Computers and Signal Processing. Victoria,86-89
[25]Hogg D, Model-based vision:A program to see a walking person. Image and Vision Computing,1995,1:5-20
[26]王栓,艾海舟,何克忠.基于差分图象的多运动目标的检测与跟踪.中国图象图形学报,1999,4(6)：1057-1012
[27]Sidenbladh H. Detecting human motion with support vector machines. In: Proc of Int Conf on Pattern Recognition. Cambridge,2004,188-191
[28]Utsumi A, Mori H, Ohya J, et al. Multiple-view-based tracking of multiple humans. In:Proc of Int Conf Pattern Recognition. Brisbane,1998,197-601
[29]Prati A, Mikic I, Trivedi M M, et al. Detecting moving shadows:algorithms and evaluation. IEEE Trans on PatternAnalysis and Machine Intelligence, 2003,25 (7):918-923
[30]Schindler K, Wang H. Smooth foreground-background segmentation for video processing. In:Proc of Asian Conf on Computer Vision. Hyderabad, India, 2006,581-590
[31]Sheikh Y, Shah M. Bayesian modeling of dynamic scenes for object detection. IEEE Trans on Pattern Analysis and Machine Intelligence,2005, 27(11):1778-1792
[32]Chen, Maolin M, Gengyu K, Seokcheol. Pixels classification for moving object extraction. In:Proc of IEEE Workshop on Motion and Video Computing. Breckenridge,2005,44-49
[33]Cucchiara R, Grana C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(10):1337-1342
[34]McKenna S J, Jabri S, Duric Z, et al. Tracking interacting People. In:Proc of Int Conf on Automatic Face and Gesture Recognition. Grenoble, 2000,348-353
[35]Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV Color Information. In:Proc of IEEE Int Conf on Intelligent Transportation Systems. Oakland,2001,334-339
[36]Eng H L, Toh K A, Kam A H, et al. An automatic drowning detection surveillance system for challenging outdoor pool environments. In:Proc of IEEE Int Conf on Computer Vision. Nice,2003,532-536
[37]Kuno Y, Watanabe T, Shimosakoda Y, et al. Automated detection of human for visual surveillance system. In:Proc of Int Conf Pattern Recognition. Vienna,1996,865-869
[38]Jang D S, Choi H I. Active models for tracking moving objects. Pattern Recognition,2000,33(7):1135-1146
[39]Zhao L, Davis L S. Closely coupled object detection and segmentation. In: Proc of Int Conf on Computer Vision. Beijing,2005,454-461
[40]Plankers R, Fua P. Articulated soft objects for video-based body modeling. In:Proc of Int Conf on Computer Vision. Vancouver,2001,394-401
[41]Carranza J, Theobalt C, Magnor M, Seidel H P. Free-viewpoint video of human actors. In:Proc of ACM SIGGRAPH,2003,565-577
[42]Song Y, Goncalves L, Perona P. Unsupervised learning of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7): 814-827
[43]Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proc of Computer Vision and Pattern Recognition. San Diego,2005,886-893
[44]Starck J, Hilton A. Model-based multiple view reconstruction of people. In: Int Conf on Computer Vision. Nice,2003,13-16
[45]Roberts T J, McKenna S J, Ricketts I W. Adaptive learning of statistical appearance models for 3D human tracking. In:Proc of British Machine Vision Conference. Cardiff,2002,333-342
[46]Karaulova I A, Hall P M, Marshall A D. A hierarchical model of dynamics for tracking people with a single video camera. In:Proc of British Machine Vision Conf. Bristol,2000,262-352
[47]Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with physical forces. Computer Vision and Image Understanding,2001, 81(3):328-357
[48]Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with silhouettes. In:Proc of Int Conf on Computer Vision. Kerkyra,1999,716-721
[49]Sminchisescu C, Triggs B. Covariance scaled sampling for monocular 3D body tracking. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition,2001,447-454
[50]Hu W M, Tan T N, Wang L, et al. A survey on visual surveillance of object motion and behaviors. IEEE Trans on Systems Man and Cybernetics,34(3): 334-353
[51]Malik J, Russell S, Weber J,et al. A machine vision based surveillance system for Californaia roads. University of California, PATH project MOU-83 Final Report,1994
[52]Cucchiara R, Grana C, Tardini G, et al. Probabilistic people tracking for occlusion handling. In:Proc of Int Conf on Pattern Recognition. Cambridge, 2004,132-135
[53]Polat E, Yeasin M, Sharma R. Robust tracking of human body parts for collaborative human computer interaction. Computer Vision and Image Understanding,2003,89:44-69
[54]Hoshino J, Yamamoto M, Saito H. A match moving technique for merging CG cloth and human video sequences. Journal of Visualization and Computer Animation,2001,12(1):23-29
[55]Isard M, Blake A. Condensation—conditional density propagation for visual tracking. International Journal on Computer Vision,1998,29 (1):5-28
[56]Green P J. Highly structured stochastic systems. Chapter Transdimensional Markov Chain Monte Carlo, Oxford University Press,2003
[57]Smith K, Perez D G, Odobez J M. Using particles to track varying numbers of interacting people. In:Proc of Computer Vision and Pattern Recognition. San Diego,2005,877-880
[58]Li Y, Hilton A, Illingworth J. A relaxation algorithm for real-time multiple view 3D-tracking. Image and Vision Computing,2002,20(12):841-859
[59]Khan S, Shah M. Tracking people in presence of occlusion. In:Proc of Asian Conference on Computer Vision. Taiwan,2000,1132-1137
[60]Park S, Aggarwal J.K. Recognition of human interaction using multiple features in grayscale images. In:Proc of Int Conf on Pattern Recognition. Barcelona,2000,51-54
[61]Cutler R, Davis L S. Robust real-time periodic motion detection, analysis, and applications. IEEE Trans on Pattern Analysis and Machine Intelligence,2000, 22:781-796
[62]Yang H D, Lee S W. Multiple pedestrian detection and tracking based on weighted temporal texture features. In:Int Conf on Pattern Recognition. Cambridge,2004,248-251
[63]Xu L Q, Puig P. A hybrid blob and appearance-based framework for multi-object tracking through complex occlusions. In:Proc of Int Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Beijing,2005,73-80
[64]Zhang Z Y. Modeling geometric structure and illumination variation of a scene from real images. In:Proc of Int Conf on Computer Vision. Bombay,1998, 4-7
[65]Tan T N, Sullivan G D, Baker K D. Model-based localization and recognition of road vehicles. International Journal of Computer Vision,1998,29(1):22-25
[66]Billard A, Epars Y, Calinon S, et al. Discovering optimal imitation strategies. Robotics and Autonomous Systems,2004,47:69-77
[67]Calinon S, Billard A. Stochastic gesture production and recognition model for a humanoid robot. In:Proc of Int Conf on Intelligent Robots and Systems. Alberta,2005,2769-2774
[68]Yu X, Yang S X. A study of motion recognition from video sequences. Computing and Visualization in Science,2005,8:19-25
[69]Malik J, Russell S. Traffic Surveillance and Detection Technology Development:New Traffic Sensor Technology. Univ. of California, Berkeley, California PATH Research Final Rep.,1997
[70]Polana R, Nelson R. Low level recognition of human motion. In:P roc of IEEE Work shop on Motion of Non-Rigid and Articulated Objects. Austin, 1994,77-82
[71]Bobick A, Davis J. Realtime recognition of activity using temporal templates. In:Proc of IEEE Work shop on Applications of Computer Vision, Sarasota, 1996,39-42
[72]Bregler C. Learning and recognizing human dynamics in video sequences. In: Proc of IEEE Conf on Computer Vision and Pattern Recognition, Puerto Rico, 1997,568-574
[73]Kojima A, Izumi M, Tamura T, et al. Generating natural language description of human behaviors from video images. In:Proc of IEEE International Conference on Pattern Recognition. Barcelona,2000,728-731
[74]Koller D, Weber J, Huang T, et al. Towards robust automatic traffic scene analysis in real-time. In:Proc of IEEE Conference on Decision and Control. Lake Buena Vista,1994,3776-3781
[75]Webb A R.统计模式识别(第二版).王萍,杨培龙,罗颖昕.北京：电子工业出版社,2004,65-96
[76]Mittal. A, Paragios. N. Motion-based background subtraction using adaptive kernel density estimation. In:Proc of IEEE Conf on Computer Vision and Pattern Recognition. Washington DC,2004,302-309
[77]龚光鲁,钱敏平.应用随机过程教程及在算法和智能计算中的随机模型.北京：清华大学出版社,2004,209-230
[78]刘晓翔.卫星多源遥感图像融合技术的研究：[西北工业大学硕士学位论文].西安：西北工业大学,2004,39—60
[79]罗述谦,周果宏.医学图象处理与分析.北京：科学出版社,2003,106-107
[80]熊和金,陈德军.智能信息处理.北京：国防工业出版社,2006,141-183
[81]Spagnolo P, Orazio T D, Leo M, et al. Moving object segmentation by background subtraction and temporal analysis. Image and Vision Computing, 2006,24:411-423
[82]Hu M, Hu W, Tan T. Tracking people through occlusion. In:Proc of Int Conf on Pattern Recognition. Cambridge,2004,724-727
[83]Wang H, Suter D, Schindler K. Adaptive object tracking based on an effective appearance filter. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007,9(29):1661-1667
[84]Capellader M B, Doermann D, DeMenthon D, et al. An appearance based approach for human and object tracking. In:Proc of Int Conf on Image Processing, Barcelona,2003,85-88
[85]Zhao Q, Tao H. Object tracking using color correlogram. In:Proc of IEEE Int Workshop on VS-PETS. Beijing,2005,263-270
[86]Park S, Aggarwal J K. Simultaneous tracking of multiple body parts of interacting persons. Computer Vision and Image Understanding,2006, 1(102):1-21
[87]Tang F, Tao H. Object tracking with dynamic feature graph. In:Proc of IEEE Int Workshop on VS-PETS. Beijing,2005,25-32
[88]章毓晋.图像工程(上册)——图像处理(第2版).北京：清华大学出版社,2006,158-179
[89]李国辉,柳伟,曹莉华.一种基于颜色特征的图像检索方法.中国图象图形学报,1999,4(3)：248-251
[90]Swain M J, Ballard D H. Color indexing. International Journal of Computer Vision,1991,7(1):1127-1138
[91]Forsyth D A, Ponce J. Computer vision:a modern approach. NJ:Prentice Hall,2003,58-102
[92]马颂德,张正友著.计算机视觉——计算理论与算法基础.北京：科学出版社,2003：81-110
[93]Eshera M A, Fu K S. A graph distance measure for image analysis. IEEE Trans on Systems, Man, and Cybernetics,1984,3(14):398-408
[94]Xu X G, Sun Z X, Liu W Y. Matching spatial relation graphs using a constrained partial permutation strategy. Journal of Southeast Universtiy (English Edition),2003,19(3):236-239
[95]徐雷.模拟退火组合优化法在模式识别中的若干应用.自动化学报,1989,15(2)：114-121
[96]Graciano A B V, Cesar R M, Bloch I,et al. Graph-based object tracking using structural pattern recognition. In:Proc of Computer Graphics and Image Processing. Minas Gerais,2007,179-186
[97]Christmas W J, Kittler J. Structural matching in computer vision using probabilistic relaxation. IEEE Trans on Pattern Analysis and Machine Intelligence,1995,8(17):749-764
[98]Sonka M, Hlavac V, Boyle R.图像处理、分析与机器视觉(第二版).艾海舟,武勃.北京：人民邮电出版社,2003,275-285
[99]KaewTrakulPong P, Bowden R. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image and Vision Computing,2003,21:913-929
[100]Cavallaro A, Steiger O, Ebrahimi T. Tracking video objects in cluttered background. IEEE Trans on Circuits and Systems for Video Technology,2005, 15(4):575-584
[101]乔长阁,高德远.分配问题的计算机方法.计算机研究与发展1995,32(6)：29-34
[102]韩中庚.用“匈牙利算法”求解一类最优化问题.信息工程大学学报,2004,35(1)：60-62
[103]Carpaneto G, Toth P. Solution of the assignment problem. ACM Transactions on Mathematical Software,1980,6(1):104-111
[104]Conte D, Foggia P, Jolion J M, et al. A graph-based, multi-resolution algorithm for tracking objects in presence of occlusions.2006,39:562-572
[105]Fuentes L M, Velastin S A. People tracking in surveillance applications. Image and Vision Computing,2006,24:1165-1171
[106]Zhao J W, Wang P, Liu C Q. An object tracking algorithm based on occlusion mesh model. In:Proc of Int Conf Machine Learning and Cybernetics,2002, 288-292
[107]李正周,金钢,董能力.基于改进概率数据关联滤波的红外小目标运动目标跟踪.电子与信息学报,2008,30(4)：953-956
[108]耿峰,祝小平.一种改进的多传感器多目标跟踪联合概率数据关联算法研究.系统仿真学报,2007,19(20)：4671-4675
[109]Setubal J. Sequential and parallel experimental results with bipartite matching algorithms. Institute of Computing, State University of Campinas, Brazil, 1996
[110]韩崇昭,朱洪艳,段战胜.多源信息融合.北京：清华大学出版社,2006,297-302
[111]Fisher J L, Casasent D P. Fast JPDA multitarget tracking algorithm. Applied Optics,1989,28(2),371-376
[112]Cox I J, Hingorani S. An efficient implemantation of reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans on Pattern Analysis and Machine Intelligence,1996, 18(2):138-150
[113]卢开澄,卢华明.图论及其应用(第2版).北京：清华大学出版社,2005,189-202
[114]王磊.网络视频监控系统的关键设备研究：[湖南大学硕士学位论文].长沙：湖南大学,2008,18-78
[115]崔波亮.网络化视频监控系统中流媒体技术研究：[湖南大学硕士学位论文].长沙：湖南大学,2008,44-59
[116]王耀南,王磊,陈斯斯,万琴,崔波亮.智能视觉监控方法和装置.中国专利.发明专利申请号：200710035636.X
[117]Gonzalez R C, Woods R E.数字图像处理(第二版).阮秋琦,阮宇智.北京：电子工业出版社,2003,412-414
[118]张蒲生,何升.SQL Server数据库应用技术.北京：清华大学出版社,2005,27-44