运动人体跟踪及特征行为识别
|
摘要
利用视频序列自动跟踪人体运动,并在跟踪结果基础上识别人体行为的智能视觉系统,因其广泛的应用前景和实用价值,一直都是具有挑战性的研究热点。一般而言,该热点问题的研究分为两大组成部分,分别为运动人体视频跟踪和特征行为识别。
对于此问题的两个组成部分,存在众多的研究方法。但是由于人体的运动由人体肢体的运动组合而成,而人体肢体运动的复杂多变,导致整个人体的运动方式多样且繁杂,因此人体运动的精准跟踪不容易实现。人体的特征行为识别属于更高层次的计算机视觉课题,用于理解并描述人的特征行为,同样存在众多的研究难点。
本论文在深入总结前人工作的基础上,将人体视频跟踪和人体行为的识别结合,构建了一个自动跟踪视频序列中人体运动,并自动描述视频序列中人体特征行为的智能视觉系统,该视觉系统要解决的问题包括:实时的运动人体跟踪、通过视频序列学习人体模型、利用人体模型实现对人体运动的跟踪、对人体特征行为的识别等。为此论文将研究的内容作如下安排:
首先分析国内外现有的人体视频跟踪方法。对人体跟踪方法做了分类,分析了这些算法的功能,并指出现有算法不适用于本系统的原因。对于现有的行为识别方法,亦进行了回顾与分析。在此基础上,提出视频跟踪与识别系统的整体框架图,同时介绍了本系统所采用的方法。
针对现有经典用于检测运动物体的背景减除法的不足之处,将类哈尔算子和积分图像加以推广,用于在视频中快速检测人体的各种肢体。类哈尔特征(Haar-like Feature)因其固有的特点,适用于检测矩形或类矩形的图像区域;积分图像的特点是可以利用类哈尔特征快速定位人体肢体在图像中的位置,完成对人体各种肢体的检测。
在获得检测肢体基础上,在颜色空间利用聚类算法完成对特征点的分类,将检测得到的不同肢体分类同时去除噪声。由于传统的聚类算法(K-Mean, Mixture-Gaussian)不适用于本研究的视频跟踪系统,为此引入基于核函数的非参数聚类算法,在颜色空间直接计算特征点的梯度,并迭代将该特征点移往特征空间的局部极值处,完成对特征点的分类,同时去除了噪声。
在聚类数据的基础上利用概率推理框架学习人体模型。传统的隐马氏模型用于跟踪人体运动时,容易丢失跟踪目标,最后导致人体模型学习的失败。为此,对隐马氏模型做了改进,并使用动态规划法对改进的隐马氏模型进行推理得到最优的肢体序列,然后利用聚类算法搜索获得最能代表该类肢体的肢体模板。最后利用人体骨骼的限制,对改进的隐马氏模型进行拓展,构建一个可利用视频序列来学习整个人体模型的推理框架。
获得人体模型后实现对视频序列中运动人体的跟踪。通过检测视频序列中每帧图像中的人体模型,用于实现对运动人体的跟踪。人体模型检测过程通过将模型与视频中每帧图像匹配来实现,匹配过程利用代价函数衡量人体模型与图像的匹配效果,该代价函数的最优化可通过动态规划法实现。动态规划法的计算复杂度为二次方,引进了距离转换(Distance Transform),可降低计算复杂度。同时通过改进对人体模型根结点的选择方式,显著缩小匹配过程的搜索空间,从而加快了人体模型与图像的匹配时间。
利用获得的人体跟踪姿态参数实现对视频中人体特征行为的识别。利用经过标注的动作库和跟踪获得的人体姿态参数,构造用于推理的隐马氏模型,然后采用维特比算法,合成一个与跟踪阶段获得的人体姿态相匹配的最优动作序列,因为该动作序列事先已经过标注,因此可实现对视频中人体行为的识别。此外,还针对某些特征行为,基于运动人体的视频跟踪姿态参数构建了一个针对特征行为的二维行为识别系统,有效高速,缺点是适用范围相对较窄。
The intelligent visual system which marries kinetic people tracking with consequent behaviour identifying based on tracks, is always challenging front problem. The research generally consists of two parts, which are tracking people and identifying their behaviour.
At present there were many methods for people tracking and behaviour identifying. Nevertheless, people motion consists of people segments movements, and the movements of the segment are complex. Those factors result in the multiplicity of people motion, and being uneasy to track accurately. The people behaviour identification, which used for understanding and describing people behavour, belongs to higher level task of computer vision, and has many difficulties.
Based on former researches, this paper unites tracking with identifying, and develops an intelligent vision system for tracking people and identifying their feature behavoiur automatically. This system is meant to solving the following problems: real-time tracking, people model learning atomatically, tracking kinetic people with people model, and identifying their behaviour based on tracking. This paper is arranged as follows:
We analyzed the domestic and oversea methods for tracking people, classified those methods into categories, and figured out why they were not fit for our system. Meanwhile, we analyzed the behaviour identification methods. based on that, we proposed our framework for tracking and identifying, and introduced the algorithm we used.
Aiming at the weakness of classical background subtraction, we generalized the haar-like feature and integral image ever used for detecing face, and used them to detect different segments of people in video. For its natural characteristic, Haar-like features were suitable for localizing rectangle or rectangle-like region of the image, and we used integral image to position people parts with those features rapidly.
We classified the points of color space using cluster method, and separated the detections from noise. Traditional cluster algorithm can not used in our system. We brought in non-parametric cluster method which grounds on kernel function, computed the gradient of points, moved the points towards mode iteratively, and assigned the point to one certain cluster. It means we classify the points while removing noise.
Based on clustering, We learned the people model using probabilitic inferences. Traditional HMM was easy to lose target while tracking people, and resulted in the failure of learning. We modified the HMM, and made inferences with dynamic programming to obtain the optimal segment sequence, and searched for the template of that segment, using cluster algorithm. Then we extended the modified HMM making use of the geometric restriction of people, and builded an inference framework learning complete people model with video.
We tracked kinetic people in video using learned people model. We tracked kinetic people by detecting people model in frame of video. By matching the people model to image, we detected the model in image, using a cost function as measure of match. For optimalizing the cost function, we used dynamic programming, and we introduced distance tansform for reducing the computation complexity. At the same time, we improved the selection of root node of people model, remarkedly abbreviated the search space of matching procrdure and speeded up the match of people model to frame of the video.
We identified people behaviour with people pose of tracking stage. Using annotated motion library&people pose obtained by tracking, we builded a HMM for inference, and synthesized an optimal motion sequence which matched the tracked pose best, with Viterbi algorithm.For the motion sequence was annotated in advance, we can identify the people behaviour of video.Furthermore, we developed an identification system based on the pose tracked, aiming at the property of certain behaviour. It was effective and rapid, yet disadvantage in relatively cabined scope of application.
对于此问题的两个组成部分,存在众多的研究方法。但是由于人体的运动由人体肢体的运动组合而成,而人体肢体运动的复杂多变,导致整个人体的运动方式多样且繁杂,因此人体运动的精准跟踪不容易实现。人体的特征行为识别属于更高层次的计算机视觉课题,用于理解并描述人的特征行为,同样存在众多的研究难点。
本论文在深入总结前人工作的基础上,将人体视频跟踪和人体行为的识别结合,构建了一个自动跟踪视频序列中人体运动,并自动描述视频序列中人体特征行为的智能视觉系统,该视觉系统要解决的问题包括:实时的运动人体跟踪、通过视频序列学习人体模型、利用人体模型实现对人体运动的跟踪、对人体特征行为的识别等。为此论文将研究的内容作如下安排:
首先分析国内外现有的人体视频跟踪方法。对人体跟踪方法做了分类,分析了这些算法的功能,并指出现有算法不适用于本系统的原因。对于现有的行为识别方法,亦进行了回顾与分析。在此基础上,提出视频跟踪与识别系统的整体框架图,同时介绍了本系统所采用的方法。
针对现有经典用于检测运动物体的背景减除法的不足之处,将类哈尔算子和积分图像加以推广,用于在视频中快速检测人体的各种肢体。类哈尔特征(Haar-like Feature)因其固有的特点,适用于检测矩形或类矩形的图像区域;积分图像的特点是可以利用类哈尔特征快速定位人体肢体在图像中的位置,完成对人体各种肢体的检测。
在获得检测肢体基础上,在颜色空间利用聚类算法完成对特征点的分类,将检测得到的不同肢体分类同时去除噪声。由于传统的聚类算法(K-Mean, Mixture-Gaussian)不适用于本研究的视频跟踪系统,为此引入基于核函数的非参数聚类算法,在颜色空间直接计算特征点的梯度,并迭代将该特征点移往特征空间的局部极值处,完成对特征点的分类,同时去除了噪声。
在聚类数据的基础上利用概率推理框架学习人体模型。传统的隐马氏模型用于跟踪人体运动时,容易丢失跟踪目标,最后导致人体模型学习的失败。为此,对隐马氏模型做了改进,并使用动态规划法对改进的隐马氏模型进行推理得到最优的肢体序列,然后利用聚类算法搜索获得最能代表该类肢体的肢体模板。最后利用人体骨骼的限制,对改进的隐马氏模型进行拓展,构建一个可利用视频序列来学习整个人体模型的推理框架。
获得人体模型后实现对视频序列中运动人体的跟踪。通过检测视频序列中每帧图像中的人体模型,用于实现对运动人体的跟踪。人体模型检测过程通过将模型与视频中每帧图像匹配来实现,匹配过程利用代价函数衡量人体模型与图像的匹配效果,该代价函数的最优化可通过动态规划法实现。动态规划法的计算复杂度为二次方,引进了距离转换(Distance Transform),可降低计算复杂度。同时通过改进对人体模型根结点的选择方式,显著缩小匹配过程的搜索空间,从而加快了人体模型与图像的匹配时间。
利用获得的人体跟踪姿态参数实现对视频中人体特征行为的识别。利用经过标注的动作库和跟踪获得的人体姿态参数,构造用于推理的隐马氏模型,然后采用维特比算法,合成一个与跟踪阶段获得的人体姿态相匹配的最优动作序列,因为该动作序列事先已经过标注,因此可实现对视频中人体行为的识别。此外,还针对某些特征行为,基于运动人体的视频跟踪姿态参数构建了一个针对特征行为的二维行为识别系统,有效高速,缺点是适用范围相对较窄。
The intelligent visual system which marries kinetic people tracking with consequent behaviour identifying based on tracks, is always challenging front problem. The research generally consists of two parts, which are tracking people and identifying their behaviour.
At present there were many methods for people tracking and behaviour identifying. Nevertheless, people motion consists of people segments movements, and the movements of the segment are complex. Those factors result in the multiplicity of people motion, and being uneasy to track accurately. The people behaviour identification, which used for understanding and describing people behavour, belongs to higher level task of computer vision, and has many difficulties.
Based on former researches, this paper unites tracking with identifying, and develops an intelligent vision system for tracking people and identifying their feature behavoiur automatically. This system is meant to solving the following problems: real-time tracking, people model learning atomatically, tracking kinetic people with people model, and identifying their behaviour based on tracking. This paper is arranged as follows:
We analyzed the domestic and oversea methods for tracking people, classified those methods into categories, and figured out why they were not fit for our system. Meanwhile, we analyzed the behaviour identification methods. based on that, we proposed our framework for tracking and identifying, and introduced the algorithm we used.
Aiming at the weakness of classical background subtraction, we generalized the haar-like feature and integral image ever used for detecing face, and used them to detect different segments of people in video. For its natural characteristic, Haar-like features were suitable for localizing rectangle or rectangle-like region of the image, and we used integral image to position people parts with those features rapidly.
We classified the points of color space using cluster method, and separated the detections from noise. Traditional cluster algorithm can not used in our system. We brought in non-parametric cluster method which grounds on kernel function, computed the gradient of points, moved the points towards mode iteratively, and assigned the point to one certain cluster. It means we classify the points while removing noise.
Based on clustering, We learned the people model using probabilitic inferences. Traditional HMM was easy to lose target while tracking people, and resulted in the failure of learning. We modified the HMM, and made inferences with dynamic programming to obtain the optimal segment sequence, and searched for the template of that segment, using cluster algorithm. Then we extended the modified HMM making use of the geometric restriction of people, and builded an inference framework learning complete people model with video.
We tracked kinetic people in video using learned people model. We tracked kinetic people by detecting people model in frame of video. By matching the people model to image, we detected the model in image, using a cost function as measure of match. For optimalizing the cost function, we used dynamic programming, and we introduced distance tansform for reducing the computation complexity. At the same time, we improved the selection of root node of people model, remarkedly abbreviated the search space of matching procrdure and speeded up the match of people model to frame of the video.
We identified people behaviour with people pose of tracking stage. Using annotated motion library&people pose obtained by tracking, we builded a HMM for inference, and synthesized an optimal motion sequence which matched the tracked pose best, with Viterbi algorithm.For the motion sequence was annotated in advance, we can identify the people behaviour of video.Furthermore, we developed an identification system based on the pose tracked, aiming at the property of certain behaviour. It was effective and rapid, yet disadvantage in relatively cabined scope of application.
引文
1 Collins.R.et. A system for video surveillance and monitoring: VSAM final report.Carnegie Mellon University, Techical Report: CMU-RI-TR-00-12, 2000
2 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
3 C. R. Wren, A. Azarbayejani, T. J. Darrell. Pfinder: Real-time tracking of the human body. IEEE T. Pattern Analysis and Machine Intelligence. 199719(7): 780–785
4 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
5 D. Hogg. Model-based Vision: a Program to see a walking person. Image and Vision Computing.1983:1(1):5-20
6 K. Rohr. Towards Model-Based Recognition of Human Movements in Image Sequence.PAMI. 1994.59(1):94-115
7 Bobick, J. Davis. The recognition of Human Movement Using Temporal Templates.PAMI.2001.23(3): 257-267
8 Ross Cutler, Larry Davis. Robust periodic motion and motion symmetry detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2000.2:2615
9 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
10 M. Isard, A. Blake. Condensation– Conditional density propagation for visual tracking. IJCV.1998.29(1):5-28
11 D.M. Gavrila, L.S. Davis. 3-d model-based tracking of humans in action: a multi-view approach. Proceedings of the Conference on Computer Vision and Pattern Recognition.1996:73
12 Sidenbladh, M. Black, D. Fleet. Stochastic Tracking of 3D Human Figures using 2D Image Motion. Proceedings of the 6th European Conference on Computer Vision.2000. 1843: 702– 718
13 Romer Roasales, Stan Sclaroff. Inferring Body Pose without Tracking BodyParts.CVPR. 2000
14 Kentaro Toyama,Andrew Blake.Probabilistic Tracking in a Metric Space. ICCV.2001
15 Plankers, Pascal.Fua. Automatic Detection and Tracking of Human Motion with a View-Based Representation. Proceedings of the 7th European Conference on Computer Vision.2002: 476– 491
16 Sullivan, S. Carlsson. Recognizing and Tracking Human Action. Proceedings of the 7th European Conference on Computer Vision. 2002: 629– 644
17 http: //www. scs. Leeds. ac. uk/imv
18 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
19 S. IOFFE, D. A. FORSYTH. Probabilistic Methods for Finding People. International Journal of Computer Vision. 2001, 43(1): 45-68
20 D. Ramanan and D. A. Forsyth. Finding and tracking people from the bottom up. CVPR, 2003
21 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
22 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
23 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
24 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
25 Okan Arikan, David A. Forsyth, James O'Brien. Motion Synthesis from Annotations. ACM.2003.33(3): 402-408
26 D. Ramanan, D. A. Forsyth. Automatic Annotation of Everyday Movements. Neural Information Processing Systems. 2003
27 A. F. Bobick and J. W. Davis. The recognition of human movement using temporal templates. Pattern Analysis and Machine Intelligence, 2001. 23(3): 257–267
28 A. F. Bobick. Movement, activity, and action: The role of knowledge in the perception of motion. Philosophical Transactions of Royal Society of London. 1997. B-352: 1257–1265
29 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98
30 Weiming Hu, Tieniu Tan, Liang Wang, and Steve Maybank. A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man and Cybernetics. 2004. 34(3): 334–352
31 A.F. Bobick, J. W. Davis. Real-time recognition of activity using temporal templates. In Workshop on Applications of Computer Vision, 1996
32 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98
33 J.W. Davis, A. F. Bobick. The representation and recognition of action using temporal templates. In CVPR, 1997
34 A. Efros, A. Berg, G. Mori, J. Malik. Recognizing action at a distance. In ICCV, 2003
35 R.Polana, R. C. Nelson. Detecting activities. In Proceedings, International Conference on Pattern Recognition, 1994. ( A): 815–818
36 L. Zelnik-Manor and M. Irani. Event-based analysis of video. CVPR, 2001
37 J. Ben-Arie, Z. Wang, P. Pandit, S. Rajaram. Human activity recognition using multidimensional indexing. PAMI, 2002 24(8): 1091–1104
38 M.J.Black, Y. Yacoob. Parametrised modelling and tracking of human activities. Computer Vision and Image Understanding, 1999. 73(2): 232–247
39 J. Sullivan, S. Carlsson. Recognizing and tracking human action. In European Conference on Computer Vision. 2002
40 Xiaolin. Feng, P. Perona. Human action recognition by sequence of movelet codewords. In First International Symposium on 3D Data Processing Visualization andTransmission. 2002: 717–721
41 M. Brand, N. Oliver, A. P. Pentland. Coupled hidden markov models for complex action recognition. In IEEE Conference on Computer Vision and Pattern Recognition, 1997: 994–999
42 N. Oliver, E. Horvitz, A. Garg. Layered representations for human activity recognition. In Fourth IEEE International Conference on Multimodal Interfaces. 2002: 3–8
43 A. D. Wilson, A. F. Bobick. Parametric hidden markov models for gesture recognition. IEEE Transaction Pattern Analysis and Machine Intelligence. 1999. 21(9): 884–900
44 M. Brand, V. Kettnaker. Discovery and segmentation of activities in video. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000: 844–851
45 C. C. Chang, C. J. Lin. Libsvm: Introduction and benchmarks. Technical report. Department of Computer Science and Information Engineering, National Taiwan University. 2000
46 A. Galata, N. Johnson, D. Hogg. Learning structured behavior models using variable length markov models. IEEE International Workshop on Modelling People. 1999
47 O. Arikan, D. A. Forsyth, J. O. Brien. Motion synthesis from annotations. In Proceedings of SIGGRAPH 95. 2003
48 A. Senior. Tracking people with probabilistic appearance models. IEEE Workshop on Performance Evaluation Tracking Surveillance. 2002: 48–55
49 Keinosuke. Fukunaga, Larry. D. Hosteetleer. The Estimation of the gradient of a Density Function, With Applications in Pattern Recognition. Information Theory, IEEE Transactions. 1975, 21(1)
50 C. R. Wren, A. Azarbayejani, T. J. Darrell. Pfinder: Real-time tracking of the human body. IEEE T. Pattern Analysis and Machine Intelligence. 1997.19(7): 780–785
51 Paul Viola, Michael Jones. Rapid Object Detection using a Boosted Cascade of Simple features. Accepted conference on computer vision and pattern recognition. 2001
52 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
53 Duan. Sheng-Chen, Zheng. Kai-Liu. Generalized Haar-like features for fast face detection. Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong. 2007: 19-22
54 T. Mita, T. Kaneko, O. Hori. Joint Haar-like Features for Face Detection. Proceeding Of 10th IEEE International Conference on Computer Vision. 2005. 2: 1619-1626
55 J. Nishimura, T. Kuroda. Low cost speech detection using Haar-like filteringfor sensornet. In Proceedings of ICSP. 2008
56刘贵喜,邵明礼,刘先红,朱东波.真实场景下视频运动目标自动提取方法.光学学报, 2006, 26(8): 1150~1155
57 Polana. R, Nelson. R. Low level recognition of human motion. Proceeding IEEE Workshop on Motion of Non-Rigid and Articulated Objects. 1994: 77-82
58 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
59 Paul Viola, Michael Jones. Rapid Object Detection using a Boosted Cascade of Simple features. Accepted conference on computer vision and pattern recognition. 2001
60 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
61 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
62 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
63 B. W. Silverman. Density estimation for statistics and data analysis. London: Chapman and Hall. 1986
64 Guo Hui-Min, Guo Ping, Lu Han-qing. A Fast Mean Shift Procedure with New Iteration Strategy and Re-Sampling. IEEE International Conference on Systems, Man and Cybernetics. 2006
65 M. Carreira-Perpinan. Fast nonparametric clustering with gaussian blurring mean-shift. In International Conference on Machine Learning. 2006
66 M. Carreira-Perpinan. Gaussian mean-shift is an em algorithm IEEE Transactions on Pattern Analysis and Macnine Intelligence, 2007, 29(5): 767–776
67 M. Fashing and C. Tomasi. Mean shift is a bound optimization IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005, 27: 471–474
68 X. -T. Yuan, B. -G. Hu and R. He. Agglomerative mean-shift clustering via query set compression. In SIAM International Conference on Data Mining (SDM), 2009. 515-518
69 Carreira-Perpin?a′n. Acceleration strategies for Gaussian mean-shift image segmentation. IEEE International Conference on Computer Vision and Pattern Recognition. 2006
70 D. Hogg, Model-based vision: A program to see a walking person, Image and Vision Computing, 1983. 1(1) : 5–20
71 Arnaldo. J. Abrantes, Jorge. S. Marques. The Mean Shift Algorithm and the Unified Framework. The Proceedings of the 17th international conference on Pattern Recognition. 2004, 1: 224-247
72 Zhan Heng, Li Li-Chun, Yu Qi-Feng. Scale and Direction Adaptive Mean Shift Tracking Algorithm. Optics and Precision Engineering. 2008, 16(6)
73 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
74 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
75 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
76 Xiao-Tong Yuan, Stan Z. Li. Stochastic Gradient Kernel Density Mode-Seeking. IEEE International Conference on Computer Vision and Pattern Recognition. 2009
77 K. Rohr, towards model-based recognition of human movements in image sequences, CVGIP: Image Understanding, 1994. 59( 1): 94–115
78 J. Sivic M. Everingham, A. Zisserman. Person spotting: Video shot retrieval for face sets. in International Conference on Image and Video Retrieval . 2005
79 Adir. Even, G. Shankaranarayanan, StephanieWatts. Enhancing Decision Making with Process Metadata: Theoretical Framework, Research Tool, and Exploratory Examination. Proceedings of the 39th Annual Hawaii International Conference on System Sciences. 2006
80 L. Ikemoto, O. Arikan, D. A. Forsyth. Knowing when to put your foot down. in Proccding Symp, Interactive 3D graphics and Games. 2006
81 Thomas. Hanne, Rolf. Dornberger, Lukas Frey. Multiobjective and preference-based decision support for rail crew rostering. 2009 IEEE Congress onEvolutionary Computation. 2009: 990-996
82 Jimin. Gao, Mats Heimdahl, David. Owen, Tim Menzies. On the Distribution of Property Violations in Formal Models: An Initial Study. 30th Annual International Computer Software and Applications Conference. 2006: 150-160
83 Steven. C, H. Hoi, Michael. R. Lyu. A Semi-Supervised Active Learning Framework for Image Retrieval. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005. 2
84 Peter. Nillius, Josephine. Sullivan, Stefan. Carlsson. Multi-Target Tracking - Linking Identities using Bayesian Network Inference. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006. 2: 2187-2194
85 Daniel. Lowd, Pedro. Domingos. Naive Bayes models for probability estimation. Proceedings of the 22nd international conference on Machine learning. 2005. 647-657
86 Onur. C. Hamsici, Aleix. M. Martinez Bayes Optimality in Linear Discriminant Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008. 568-578
87 Shihao. Ji, Balaji Krishnapuram, Lawrence Carin. Variational Bayes for Continuous Hidden Markov Models and Its Application to Active Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 2236-2242
88 Jaemo Sung, Zoubin Ghahramani, Sung-Yang Bang. Latent-Space Variational Bayes. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008: 2236-2242
89 Zhenqiu Zhangy, Gerasimos Potamianos, Stephen Chu, Jilin Tu, Thomas Huang. Person Tracking in Smart Rooms using Dynamic Programming and Adaptive Subspace Learning. 2006 IEEE International Conference on Multimedia. 2006: 2061-2064
90 Brendan J. Frey, Nebojsa Jojic. Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005: 1392-1416
91 Tiberio S. Caetano, Terry Caelli, Dale Schuurmans, Dante A. C. Barone. Graphical Models and Point Pattern Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 1646-1663
92 Shaolei Feng, R. Manmatha, Andrew McCallum. Exploring the Use ofConditional Random Field Models and HMMs for Historical Handwritten Document Recognition. Second International Conference on Document Image Analysis for Libraries. 2006: 30-37
93 Eran Swears, Anthony Hoogs, A. G. Amitha Perera. Learning Motion Patterns in Surveillance Video using HMM Clustering. 2008 IEEE Workshop on Motion and video Computing. 2008: 1-8
94 Pei Yin, Irfan Essa, James M. Rehg. Asymmetrically Boosted HMM for Speech Reading. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004. 2: 755-761
95 M. Barnard, J. -M. Odobez. Sports Event Recognition Using Layered HMMS. 2005 IEEE International Conference on Multimedia and Expo. 2005. 1150-1153
96 Hui Liu, Jun-an Yang, Hao Chen. A Novel Approach Research on Low Altitude Passive Acoustic Target Recognition Based on ICA and HMM. 2008 Fourth International Conference on Natural Computation. 2008. 371-375
97 D. Zhang, D. Gatica-Perez, S. Bengio. Semi-supervised meeting event recognition with adapted HMMs. 2005 IEEE International Conference on Multimedia and Expo. 2005. 4
98 S. Ioffe, D. A. Forsyth. Probabilistic method for finding people. International Journal of computer vision. 2001. 43(1): 45-68
99 C. Bregler, J. Malik. Tracking people with twists and exponential maps. In IEEE Conference on Computer Vision and Pattern Recognition, 1998: 8–15
100 Jonathan Deutscher, Andrew Blake, and Ian Reid. Articulated body motion capture by annealed particle filtering. CVPR. 2000
101 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98, 1999
102 D. M. Gavrila and L. S. Davis. 3d model-based tracking of humans in action: a multiview approach. In CVPR. 1996. 73–80
103 V. Pavlovic, J. M. Rehg, Tat-Jen Cham, and K. P. Murphy. A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV. 1999. 94–101
104 J. Rehg and T. Kanade. Model-based tracking of self-occluding articulated objects. ICCV. 1995. 612–617
105 Eva Kannan Ramanan. Tracking People and Recognizing their Activities.University of California, BERKELEY. PH. D Dissertation. 2005
106 S. IOFFE, D. A. FORSYTH. Probabilistic Methods for Finding People. International Journal of Computer Vision. 2001, 43(1): 45-68
107 Feng Yang, Jianhao Hu, Xingzhong Xiong. EM Combination Channel Estimation Algorithm for Interleave-Division Multiple Access Systems. International Conference on MultiMedia and Information Technology. 2008. 515-518
108 Jonathan Mooser, Suya. You, Ulrich Neumann. Real-Time Object Tracking for Augmented Reality Combining Graph Cuts and Optical Flow. 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. 2007: 1-8
109 Anna. Hilsmann, Peter Eisert. Tracking deformable surfaces with optical flow in the presence of self occlusion in monocular image sequences. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2008: 1-6
110 Masafumi Miyazawa, Peifeng Zeng, Naoyuki Iso. A Systolic Algorithm for Euclidean Distance Transform. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 1127-1134
111 Trevor. Taylor, Shlomo. Geva, Wageeh W. Boles. Directed Exploration Using a Modified Distance Transform. Digital Image Computing: Techniques and Applications. 2005: 53
112 Robin Strand. Using the Hexagonal Grid for Three-Dimensional Images: Direct Fourier Method Reconstruction and Weighted Distance Transform. 18th International Conference on Pattern Recognition. 2006. 2: 1169-1172
113 Kristin. Norell, Joakim. Lindblad, Stina. Svensson. Grey Weighted Polar Distance Transform for Outlining Circular and Approximately Circular Objects.
14th International Conference on Image Analysis and Processing. 2007: 647-652
114 Takashi.Michikawa, Hiromasa.Suzuki. Spherical Distance Transforms. International Conference on Computational Sciences and Its Applications. 2008: 405-412
115 Y. Lamdan, J. T. Schwartz, H. J. Wolfson. Affine invariant model-based object recognition. IEEETransactions on robotics and automation. 1990. 6(5): 578-589
116 B. Moghaddam, A. P. Pentland. Probabilistic visual learning for objectrepresentation. IEEE Transactions on pattern analysis and machine intelligence. 1997. 19(7): 696-710
117 A. Amini, T. Weymouth, R. Jain. Using dynamic programming for solving variational problems in vision. Pattern analysis and machine intelligence. 1990. 12(9): 855-867
118 Paul. Viola, Michael Jones. Rapid object detection using a boosted cascade of simple features. CVPR. 2001
119 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
120 Felzenszwalb, Huttenlocher.D.P. Efficient matching of pictorial structures. IEEE Conference on Computer Vision and Pattern Recognition. 2000.2: 66-73
121 Odest. Chadwicke. Jenkins, German Gonzalez, Matthew Loper. Dynamical Motion Vocabularies for Kinematic Tracking and Activity Recognition. Conference on Computer Vision and Pattern Recognition Workshop. 2006 : 147
122 N. Krahnstoever, J. Rittscher, P. Tu, K. Chean, T. Tomlinson. Activity Recognition using Visual Tracking and RFID. Seventh IEEE Workshops on Application of Computer Vision. 2005. 1: 494-500
123 Michael Harville, Dalong Li. Fast, Integrated Person Tracking and Activity Recognition with Plan-View Templates from a Single Stereo Camera. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004. 2: 398-405
124 Jezekiel Ben-Arie, Zhiqian Wang, Purvin Pandit, Shyamsundar Rajaram. Human Activity Recognition Using Multidimensional Indexing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002: 1091-1104
125 Raffay Hamid, Yan Huang, Irfan Essa. ARGMode - Activity Recognition using Graphical Models. Conference on Computer Vision and Pattern Recognition Workshop. 2003. 4: 38
126 Justin Muncaster, Yunqian Ma. Activity Recognition using Dynamic Bayesian Networks with Automatic State Selection. IEEE Workshop on Motion and Video Computing. 2007: 30
127 Xiaodong Huang, Huadong Ma, Haidong Yuan. Video Mosaic Block Detection Based on Template Matching and SVM. The 9th International Conference forYoung Computer Scientists. 2008 : 1082-1086
128 Jizeng Wang, Hongmei Yang. Face Detection Based on Template Matching and
2DPCA Algorithm. 2008 Congress on Image and Signal Processing. 2008. 4: 575-579
129 Wei Feng, Bo Hu. Quaternion Discrete Cosine Transform and its Application in Color Template Matching. Congress on Image and Signal Processing. 2008. 2: 252-256
130 Kinda Anna Saddi, Christophe. Chefd. Hotel, Mikael Rousson. Region-Based Segmentation via Non-Rigid Template Matching. IEEE 11th International Conference on Computer Vision. 2007: 1-7
131 Feng Tang, Hai Tao. Fast Multi-scale Template Matching Using Binary Features. Eighth IEEE Workshop on Applications of Computer Vision. 2007: 36
132 Inhye Kang, Insup Lee, Young-Si Kim. An Efficient State Space Generation for the Analysis of Real-Time Systems. IEEE Transactions on Software Engineering. 2000: 453-477
133刘相滨,向坚持,王胜春.人行为识别与理解研究探讨.计算机与现代化. 2004. 12: 1-5
134 Ashton E. W. Mason, Edwin H. Blake. A Graphical Representation of the State Spaces of Hierarchical Level-of-Detail Scene Descriptions. IEEE Transactions on Visualization and Computer Graphics. 2001: 70-75
135 Lawrence K. Saul, Satinder P. Singh. Markov decision processes in large state spaces. Proceedings of the eighth annual conference on Computational learning theory. 1995: 281-288
136 J.Gllavata, B. Freisleben. Script recognition in images with complex backgrounds. Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology. 2005: 589-594
137 Polana. R, Nelson. R. Low level recognition of human motion. Proceeding IEEE Workshop on Motion of Non-Rigid and Articulated Objects. 1994. 77-82
138 A. D. Wilson, A. F. Bobick, J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture-Recognition. 1996
139 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004. 96(2):163–180
140 A. Galata, N. Johnson, and D. Hogg. Learning behaviour models of human activities. British Machine Vision Conference page Modelling Human Behaviour. 1999
141 A. Galata, N. Johnson, D. Hogg. Learning structured behavior models using variable length markov models. IEEE International Workshop on Modelling People. 1999
142 J. K. Aggarwal, Q. CAI. Human motion analysis: A review. Computer Vision and Image Understanding: CVIU. 1999. 73(3): 428–440
143 D. Ramanan, D. A. Forsyth. Automatic Annotation of Everyday Movements. Neural Information Processing Systems. 2003
144 M. I. Jordan. Learning in Graphical Models. MIT Press, Cambridge. 1999
2 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
3 C. R. Wren, A. Azarbayejani, T. J. Darrell. Pfinder: Real-time tracking of the human body. IEEE T. Pattern Analysis and Machine Intelligence. 199719(7): 780–785
4 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
5 D. Hogg. Model-based Vision: a Program to see a walking person. Image and Vision Computing.1983:1(1):5-20
6 K. Rohr. Towards Model-Based Recognition of Human Movements in Image Sequence.PAMI. 1994.59(1):94-115
7 Bobick, J. Davis. The recognition of Human Movement Using Temporal Templates.PAMI.2001.23(3): 257-267
8 Ross Cutler, Larry Davis. Robust periodic motion and motion symmetry detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2000.2:2615
9 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
10 M. Isard, A. Blake. Condensation– Conditional density propagation for visual tracking. IJCV.1998.29(1):5-28
11 D.M. Gavrila, L.S. Davis. 3-d model-based tracking of humans in action: a multi-view approach. Proceedings of the Conference on Computer Vision and Pattern Recognition.1996:73
12 Sidenbladh, M. Black, D. Fleet. Stochastic Tracking of 3D Human Figures using 2D Image Motion. Proceedings of the 6th European Conference on Computer Vision.2000. 1843: 702– 718
13 Romer Roasales, Stan Sclaroff. Inferring Body Pose without Tracking BodyParts.CVPR. 2000
14 Kentaro Toyama,Andrew Blake.Probabilistic Tracking in a Metric Space. ICCV.2001
15 Plankers, Pascal.Fua. Automatic Detection and Tracking of Human Motion with a View-Based Representation. Proceedings of the 7th European Conference on Computer Vision.2002: 476– 491
16 Sullivan, S. Carlsson. Recognizing and Tracking Human Action. Proceedings of the 7th European Conference on Computer Vision. 2002: 629– 644
17 http: //www. scs. Leeds. ac. uk/imv
18 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
19 S. IOFFE, D. A. FORSYTH. Probabilistic Methods for Finding People. International Journal of Computer Vision. 2001, 43(1): 45-68
20 D. Ramanan and D. A. Forsyth. Finding and tracking people from the bottom up. CVPR, 2003
21 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
22 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
23 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
24 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
25 Okan Arikan, David A. Forsyth, James O'Brien. Motion Synthesis from Annotations. ACM.2003.33(3): 402-408
26 D. Ramanan, D. A. Forsyth. Automatic Annotation of Everyday Movements. Neural Information Processing Systems. 2003
27 A. F. Bobick and J. W. Davis. The recognition of human movement using temporal templates. Pattern Analysis and Machine Intelligence, 2001. 23(3): 257–267
28 A. F. Bobick. Movement, activity, and action: The role of knowledge in the perception of motion. Philosophical Transactions of Royal Society of London. 1997. B-352: 1257–1265
29 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98
30 Weiming Hu, Tieniu Tan, Liang Wang, and Steve Maybank. A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man and Cybernetics. 2004. 34(3): 334–352
31 A.F. Bobick, J. W. Davis. Real-time recognition of activity using temporal templates. In Workshop on Applications of Computer Vision, 1996
32 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98
33 J.W. Davis, A. F. Bobick. The representation and recognition of action using temporal templates. In CVPR, 1997
34 A. Efros, A. Berg, G. Mori, J. Malik. Recognizing action at a distance. In ICCV, 2003
35 R.Polana, R. C. Nelson. Detecting activities. In Proceedings, International Conference on Pattern Recognition, 1994. ( A): 815–818
36 L. Zelnik-Manor and M. Irani. Event-based analysis of video. CVPR, 2001
37 J. Ben-Arie, Z. Wang, P. Pandit, S. Rajaram. Human activity recognition using multidimensional indexing. PAMI, 2002 24(8): 1091–1104
38 M.J.Black, Y. Yacoob. Parametrised modelling and tracking of human activities. Computer Vision and Image Understanding, 1999. 73(2): 232–247
39 J. Sullivan, S. Carlsson. Recognizing and tracking human action. In European Conference on Computer Vision. 2002
40 Xiaolin. Feng, P. Perona. Human action recognition by sequence of movelet codewords. In First International Symposium on 3D Data Processing Visualization andTransmission. 2002: 717–721
41 M. Brand, N. Oliver, A. P. Pentland. Coupled hidden markov models for complex action recognition. In IEEE Conference on Computer Vision and Pattern Recognition, 1997: 994–999
42 N. Oliver, E. Horvitz, A. Garg. Layered representations for human activity recognition. In Fourth IEEE International Conference on Multimodal Interfaces. 2002: 3–8
43 A. D. Wilson, A. F. Bobick. Parametric hidden markov models for gesture recognition. IEEE Transaction Pattern Analysis and Machine Intelligence. 1999. 21(9): 884–900
44 M. Brand, V. Kettnaker. Discovery and segmentation of activities in video. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000: 844–851
45 C. C. Chang, C. J. Lin. Libsvm: Introduction and benchmarks. Technical report. Department of Computer Science and Information Engineering, National Taiwan University. 2000
46 A. Galata, N. Johnson, D. Hogg. Learning structured behavior models using variable length markov models. IEEE International Workshop on Modelling People. 1999
47 O. Arikan, D. A. Forsyth, J. O. Brien. Motion synthesis from annotations. In Proceedings of SIGGRAPH 95. 2003
48 A. Senior. Tracking people with probabilistic appearance models. IEEE Workshop on Performance Evaluation Tracking Surveillance. 2002: 48–55
49 Keinosuke. Fukunaga, Larry. D. Hosteetleer. The Estimation of the gradient of a Density Function, With Applications in Pattern Recognition. Information Theory, IEEE Transactions. 1975, 21(1)
50 C. R. Wren, A. Azarbayejani, T. J. Darrell. Pfinder: Real-time tracking of the human body. IEEE T. Pattern Analysis and Machine Intelligence. 1997.19(7): 780–785
51 Paul Viola, Michael Jones. Rapid Object Detection using a Boosted Cascade of Simple features. Accepted conference on computer vision and pattern recognition. 2001
52 Haritaoglu I, Harwood. D, Davis. L. VV: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830
53 Duan. Sheng-Chen, Zheng. Kai-Liu. Generalized Haar-like features for fast face detection. Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong. 2007: 19-22
54 T. Mita, T. Kaneko, O. Hori. Joint Haar-like Features for Face Detection. Proceeding Of 10th IEEE International Conference on Computer Vision. 2005. 2: 1619-1626
55 J. Nishimura, T. Kuroda. Low cost speech detection using Haar-like filteringfor sensornet. In Proceedings of ICSP. 2008
56刘贵喜,邵明礼,刘先红,朱东波.真实场景下视频运动目标自动提取方法.光学学报, 2006, 26(8): 1150~1155
57 Polana. R, Nelson. R. Low level recognition of human motion. Proceeding IEEE Workshop on Motion of Non-Rigid and Articulated Objects. 1994: 77-82
58 Deva Kannan Ramanan. Tracking People and Recognizing their Activities. University of California, BERKELEY. PH. D Dissertation. 2005
59 Paul Viola, Michael Jones. Rapid Object Detection using a Boosted Cascade of Simple features. Accepted conference on computer vision and pattern recognition. 2001
60 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
61 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
62 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
63 B. W. Silverman. Density estimation for statistics and data analysis. London: Chapman and Hall. 1986
64 Guo Hui-Min, Guo Ping, Lu Han-qing. A Fast Mean Shift Procedure with New Iteration Strategy and Re-Sampling. IEEE International Conference on Systems, Man and Cybernetics. 2006
65 M. Carreira-Perpinan. Fast nonparametric clustering with gaussian blurring mean-shift. In International Conference on Machine Learning. 2006
66 M. Carreira-Perpinan. Gaussian mean-shift is an em algorithm IEEE Transactions on Pattern Analysis and Macnine Intelligence, 2007, 29(5): 767–776
67 M. Fashing and C. Tomasi. Mean shift is a bound optimization IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005, 27: 471–474
68 X. -T. Yuan, B. -G. Hu and R. He. Agglomerative mean-shift clustering via query set compression. In SIAM International Conference on Data Mining (SDM), 2009. 515-518
69 Carreira-Perpin?a′n. Acceleration strategies for Gaussian mean-shift image segmentation. IEEE International Conference on Computer Vision and Pattern Recognition. 2006
70 D. Hogg, Model-based vision: A program to see a walking person, Image and Vision Computing, 1983. 1(1) : 5–20
71 Arnaldo. J. Abrantes, Jorge. S. Marques. The Mean Shift Algorithm and the Unified Framework. The Proceedings of the 17th international conference on Pattern Recognition. 2004, 1: 224-247
72 Zhan Heng, Li Li-Chun, Yu Qi-Feng. Scale and Direction Adaptive Mean Shift Tracking Algorithm. Optics and Precision Engineering. 2008, 16(6)
73 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004, 96(2): 163-180
74 A. D. Wilson, A. F. Bobick, and J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture Recognition. 1996
75 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
76 Xiao-Tong Yuan, Stan Z. Li. Stochastic Gradient Kernel Density Mode-Seeking. IEEE International Conference on Computer Vision and Pattern Recognition. 2009
77 K. Rohr, towards model-based recognition of human movements in image sequences, CVGIP: Image Understanding, 1994. 59( 1): 94–115
78 J. Sivic M. Everingham, A. Zisserman. Person spotting: Video shot retrieval for face sets. in International Conference on Image and Video Retrieval . 2005
79 Adir. Even, G. Shankaranarayanan, StephanieWatts. Enhancing Decision Making with Process Metadata: Theoretical Framework, Research Tool, and Exploratory Examination. Proceedings of the 39th Annual Hawaii International Conference on System Sciences. 2006
80 L. Ikemoto, O. Arikan, D. A. Forsyth. Knowing when to put your foot down. in Proccding Symp, Interactive 3D graphics and Games. 2006
81 Thomas. Hanne, Rolf. Dornberger, Lukas Frey. Multiobjective and preference-based decision support for rail crew rostering. 2009 IEEE Congress onEvolutionary Computation. 2009: 990-996
82 Jimin. Gao, Mats Heimdahl, David. Owen, Tim Menzies. On the Distribution of Property Violations in Formal Models: An Initial Study. 30th Annual International Computer Software and Applications Conference. 2006: 150-160
83 Steven. C, H. Hoi, Michael. R. Lyu. A Semi-Supervised Active Learning Framework for Image Retrieval. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005. 2
84 Peter. Nillius, Josephine. Sullivan, Stefan. Carlsson. Multi-Target Tracking - Linking Identities using Bayesian Network Inference. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006. 2: 2187-2194
85 Daniel. Lowd, Pedro. Domingos. Naive Bayes models for probability estimation. Proceedings of the 22nd international conference on Machine learning. 2005. 647-657
86 Onur. C. Hamsici, Aleix. M. Martinez Bayes Optimality in Linear Discriminant Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008. 568-578
87 Shihao. Ji, Balaji Krishnapuram, Lawrence Carin. Variational Bayes for Continuous Hidden Markov Models and Its Application to Active Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 2236-2242
88 Jaemo Sung, Zoubin Ghahramani, Sung-Yang Bang. Latent-Space Variational Bayes. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008: 2236-2242
89 Zhenqiu Zhangy, Gerasimos Potamianos, Stephen Chu, Jilin Tu, Thomas Huang. Person Tracking in Smart Rooms using Dynamic Programming and Adaptive Subspace Learning. 2006 IEEE International Conference on Multimedia. 2006: 2061-2064
90 Brendan J. Frey, Nebojsa Jojic. Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005: 1392-1416
91 Tiberio S. Caetano, Terry Caelli, Dale Schuurmans, Dante A. C. Barone. Graphical Models and Point Pattern Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 1646-1663
92 Shaolei Feng, R. Manmatha, Andrew McCallum. Exploring the Use ofConditional Random Field Models and HMMs for Historical Handwritten Document Recognition. Second International Conference on Document Image Analysis for Libraries. 2006: 30-37
93 Eran Swears, Anthony Hoogs, A. G. Amitha Perera. Learning Motion Patterns in Surveillance Video using HMM Clustering. 2008 IEEE Workshop on Motion and video Computing. 2008: 1-8
94 Pei Yin, Irfan Essa, James M. Rehg. Asymmetrically Boosted HMM for Speech Reading. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004. 2: 755-761
95 M. Barnard, J. -M. Odobez. Sports Event Recognition Using Layered HMMS. 2005 IEEE International Conference on Multimedia and Expo. 2005. 1150-1153
96 Hui Liu, Jun-an Yang, Hao Chen. A Novel Approach Research on Low Altitude Passive Acoustic Target Recognition Based on ICA and HMM. 2008 Fourth International Conference on Natural Computation. 2008. 371-375
97 D. Zhang, D. Gatica-Perez, S. Bengio. Semi-supervised meeting event recognition with adapted HMMs. 2005 IEEE International Conference on Multimedia and Expo. 2005. 4
98 S. Ioffe, D. A. Forsyth. Probabilistic method for finding people. International Journal of computer vision. 2001. 43(1): 45-68
99 C. Bregler, J. Malik. Tracking people with twists and exponential maps. In IEEE Conference on Computer Vision and Pattern Recognition, 1998: 8–15
100 Jonathan Deutscher, Andrew Blake, and Ian Reid. Articulated body motion capture by annealed particle filtering. CVPR. 2000
101 D. M. Gavrila. The visual analysis of human movement: A survey. Computer Vision and Image Understanding: CVIU. 1999. 73(1): 82–98, 1999
102 D. M. Gavrila and L. S. Davis. 3d model-based tracking of humans in action: a multiview approach. In CVPR. 1996. 73–80
103 V. Pavlovic, J. M. Rehg, Tat-Jen Cham, and K. P. Murphy. A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV. 1999. 94–101
104 J. Rehg and T. Kanade. Model-based tracking of self-occluding articulated objects. ICCV. 1995. 612–617
105 Eva Kannan Ramanan. Tracking People and Recognizing their Activities.University of California, BERKELEY. PH. D Dissertation. 2005
106 S. IOFFE, D. A. FORSYTH. Probabilistic Methods for Finding People. International Journal of Computer Vision. 2001, 43(1): 45-68
107 Feng Yang, Jianhao Hu, Xingzhong Xiong. EM Combination Channel Estimation Algorithm for Interleave-Division Multiple Access Systems. International Conference on MultiMedia and Information Technology. 2008. 515-518
108 Jonathan Mooser, Suya. You, Ulrich Neumann. Real-Time Object Tracking for Augmented Reality Combining Graph Cuts and Optical Flow. 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. 2007: 1-8
109 Anna. Hilsmann, Peter Eisert. Tracking deformable surfaces with optical flow in the presence of self occlusion in monocular image sequences. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2008: 1-6
110 Masafumi Miyazawa, Peifeng Zeng, Naoyuki Iso. A Systolic Algorithm for Euclidean Distance Transform. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006: 1127-1134
111 Trevor. Taylor, Shlomo. Geva, Wageeh W. Boles. Directed Exploration Using a Modified Distance Transform. Digital Image Computing: Techniques and Applications. 2005: 53
112 Robin Strand. Using the Hexagonal Grid for Three-Dimensional Images: Direct Fourier Method Reconstruction and Weighted Distance Transform. 18th International Conference on Pattern Recognition. 2006. 2: 1169-1172
113 Kristin. Norell, Joakim. Lindblad, Stina. Svensson. Grey Weighted Polar Distance Transform for Outlining Circular and Approximately Circular Objects.
14th International Conference on Image Analysis and Processing. 2007: 647-652
114 Takashi.Michikawa, Hiromasa.Suzuki. Spherical Distance Transforms. International Conference on Computational Sciences and Its Applications. 2008: 405-412
115 Y. Lamdan, J. T. Schwartz, H. J. Wolfson. Affine invariant model-based object recognition. IEEETransactions on robotics and automation. 1990. 6(5): 578-589
116 B. Moghaddam, A. P. Pentland. Probabilistic visual learning for objectrepresentation. IEEE Transactions on pattern analysis and machine intelligence. 1997. 19(7): 696-710
117 A. Amini, T. Weymouth, R. Jain. Using dynamic programming for solving variational problems in vision. Pattern analysis and machine intelligence. 1990. 12(9): 855-867
118 Paul. Viola, Michael Jones. Rapid object detection using a boosted cascade of simple features. CVPR. 2001
119 A. Galata, N. Johnson, D. Hogg. Learning behaviour models of human activities. In British Machine Vision Conference, page Modelling Human Behaviour. 1999
120 Felzenszwalb, Huttenlocher.D.P. Efficient matching of pictorial structures. IEEE Conference on Computer Vision and Pattern Recognition. 2000.2: 66-73
121 Odest. Chadwicke. Jenkins, German Gonzalez, Matthew Loper. Dynamical Motion Vocabularies for Kinematic Tracking and Activity Recognition. Conference on Computer Vision and Pattern Recognition Workshop. 2006 : 147
122 N. Krahnstoever, J. Rittscher, P. Tu, K. Chean, T. Tomlinson. Activity Recognition using Visual Tracking and RFID. Seventh IEEE Workshops on Application of Computer Vision. 2005. 1: 494-500
123 Michael Harville, Dalong Li. Fast, Integrated Person Tracking and Activity Recognition with Plan-View Templates from a Single Stereo Camera. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004. 2: 398-405
124 Jezekiel Ben-Arie, Zhiqian Wang, Purvin Pandit, Shyamsundar Rajaram. Human Activity Recognition Using Multidimensional Indexing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002: 1091-1104
125 Raffay Hamid, Yan Huang, Irfan Essa. ARGMode - Activity Recognition using Graphical Models. Conference on Computer Vision and Pattern Recognition Workshop. 2003. 4: 38
126 Justin Muncaster, Yunqian Ma. Activity Recognition using Dynamic Bayesian Networks with Automatic State Selection. IEEE Workshop on Motion and Video Computing. 2007: 30
127 Xiaodong Huang, Huadong Ma, Haidong Yuan. Video Mosaic Block Detection Based on Template Matching and SVM. The 9th International Conference forYoung Computer Scientists. 2008 : 1082-1086
128 Jizeng Wang, Hongmei Yang. Face Detection Based on Template Matching and
2DPCA Algorithm. 2008 Congress on Image and Signal Processing. 2008. 4: 575-579
129 Wei Feng, Bo Hu. Quaternion Discrete Cosine Transform and its Application in Color Template Matching. Congress on Image and Signal Processing. 2008. 2: 252-256
130 Kinda Anna Saddi, Christophe. Chefd. Hotel, Mikael Rousson. Region-Based Segmentation via Non-Rigid Template Matching. IEEE 11th International Conference on Computer Vision. 2007: 1-7
131 Feng Tang, Hai Tao. Fast Multi-scale Template Matching Using Binary Features. Eighth IEEE Workshop on Applications of Computer Vision. 2007: 36
132 Inhye Kang, Insup Lee, Young-Si Kim. An Efficient State Space Generation for the Analysis of Real-Time Systems. IEEE Transactions on Software Engineering. 2000: 453-477
133刘相滨,向坚持,王胜春.人行为识别与理解研究探讨.计算机与现代化. 2004. 12: 1-5
134 Ashton E. W. Mason, Edwin H. Blake. A Graphical Representation of the State Spaces of Hierarchical Level-of-Detail Scene Descriptions. IEEE Transactions on Visualization and Computer Graphics. 2001: 70-75
135 Lawrence K. Saul, Satinder P. Singh. Markov decision processes in large state spaces. Proceedings of the eighth annual conference on Computational learning theory. 1995: 281-288
136 J.Gllavata, B. Freisleben. Script recognition in images with complex backgrounds. Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology. 2005: 589-594
137 Polana. R, Nelson. R. Low level recognition of human motion. Proceeding IEEE Workshop on Motion of Non-Rigid and Articulated Objects. 1994. 77-82
138 A. D. Wilson, A. F. Bobick, J. Cassell. Recovering the temporal structure of natural gesture. In Proceedings of the Second International Workshop on Automatic Face and Gesture-Recognition. 1996
139 N. Oliver, A. Garg, E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. CVIU. 2004. 96(2):163–180
140 A. Galata, N. Johnson, and D. Hogg. Learning behaviour models of human activities. British Machine Vision Conference page Modelling Human Behaviour. 1999
141 A. Galata, N. Johnson, D. Hogg. Learning structured behavior models using variable length markov models. IEEE International Workshop on Modelling People. 1999
142 J. K. Aggarwal, Q. CAI. Human motion analysis: A review. Computer Vision and Image Understanding: CVIU. 1999. 73(3): 428–440
143 D. Ramanan, D. A. Forsyth. Automatic Annotation of Everyday Movements. Neural Information Processing Systems. 2003
144 M. I. Jordan. Learning in Graphical Models. MIT Press, Cambridge. 1999