摘要
基于视觉的人体运动分析是指对视频中的运动人体进行检测、识别和跟踪,并理解和描述人体行为,它是计算机视觉领域中一个新兴的研究方向。人体运动分析系统通常涉及图像预处理、运动目标检测和识别、运动人体跟踪、人体行为理解与描述等几个主要研究内容。目前在运动目标检测、识别及跟踪上得到相对成熟的研究成果,而在人体行为理解与描述方面,仍然存在大量问题亟待解决。
本文就人体运动分析系统中的图像平滑、跟踪算法的尺度自适应性,以及人体行为理解等问题展开研究,取得的主要成果包括：
(1)提出了一种基于视觉掩蔽效应的各向异性扩散系数方程,改进了各向异性扩散图像平滑算法,能有效滤除人体运动序列图像中的噪声。比较了现有几种基于各向异性扩散方程的平滑算法的性能,实验结果表明,本文方法不仅使恢复图像质量更好,信噪比更高,且算法的收敛速度快。
(2)由于Mean-Shift算法和粒子滤波算法在目标尺寸变化大时不能准确跟踪,定义了多尺度图像信息量(MSIIM),基于此信息量,提出了一种自动更新跟踪窗口尺寸的目标跟踪算法。实验结果表明,本文改进的跟踪算法,对逐渐增大的运动目标和逐渐减小的运动目标都能实现准确地实时跟踪。
(3)提出了一种无监督的人体运动序列分割算法,并对分割出的行为段采用隐马尔可夫模型(HMM)识别。然而,当前多数行为识别算法只关注于识别包含单个行为模式的行为段,忽略了运动序列的分割。本文提出通过检测特征向量的本征维数的突变点实现运动序列的分割,本征维数采用主成分分析(PCA)方法估计。提出了一种基于紧轮廓编码的点集特征描述运动人体。在当前最常用的两个公共数据库上的实验结果表明本文算法的有效性。
(4)采用安装在室内墙体上的Panasonic (WV-CW960)摄像头自行拍摄了人体各类行为视频,建立了行为数据库OwnSet,作为后续行为识别和异常检测算法的研究对象。实验场景符合实际监控场景,数据库共包含六种行为：行走、慢跑、坐下、蹲下、跌倒和不动行为(站立、蹲着、坐着)。
(5)提出了一个多类行为分类识别系统,包含四个模块：视频采集、运动目标检测与定位、特征提取以及行为分类识别。在运动目标检测与定位模块,采用背景减除法；在特征提取模块,分别提出了运动能量序列(MES)和运动能量图像轮廓编码(CCMEI)特征；在行为识别模块,引入了分层分类的思想,分别提出了基于先验知识的决策树支持向量机多分类器和基于聚类的决策树支持向量机多分类器,且后者比前者更具有通用性。在数据库OwnSet和公共数据库上的实验结果表明本文提出的系统对不完整的运动人体块,严重的阴影,以及各种不同的衣着等都表现出了稳定的识别性能,识别率明显高于已有算法。
(6)研究了人体运动分析在智能监控中的应用,提出了家居看护中的日常行为异常检测算法,实现在无人照看的老人、小孩或病人遇到跌倒危险时监控系统给出及时告警。提出了基于组合分类器的跌倒检测算法,从OwnSet数据库的六种行为中检测出跌倒；提出了基于支持向量机分类器的跌倒检测算法,不仅能检测跌倒行为,还能区分是行进中发生的跌倒行为还是原地跌倒行为,从而判断跌倒的危害程度。实验结果表明算法的识别性能较高,且由于算法简单,系统实时性高,易于在实际应用中推广。
最后,分析了目前人体运动分析系统中存在的一些困难和亟待解决的问题,指出了进一步的研究方向。
Vision-based human motion analysis aims at detecting, identifying and tracking moving people from video sequences, and furthermore understanding and describing human activities. It is one of the most active research topics in computer vision. Human motion analysis sytem usually involves image preprocessing, moving object detection and identification, object tracking, and human behavior understanding and description. Although many research results have been achieved on object detection and tracking, there are still a lot of issues to be settled in behavior understanding and description.
In this dissertation, image smoothing, adaptability to scale changes of tracking algorithm and human behavior understanding are considered. The main research achievements include:
An anisotropic diffusion coefficient equation based on visual masking effect is proposed, which improves the performance of anisotropic diffusion image smoothing method. The noise in image sequences is removed effectively by the improved smoothing method. It is compared with several existed image smoothing algorithms. Experimental results show that not only the smoothed image by our method is better according to the signal-to-noise ratio and the mean structure similarity, but the convergence speed of our method is faster.
The information measurement of multi-scale images in scale space is investigated, based on which an object tracking algorithm with self-updating tracking window is proposed. The algorithm improves the Mean-Shift and partical filtering tracking methods and makes the moving objects with increasing scales or decreasing scales are both tracked exactly. And the improved tracking algorithms also run in real time.
An unsupervised temporal segmentation algorithm of human motion sequences is proposed, and then the obtained activity segments are recognized by HMM. However, most of the existed activity recognition algorithms are conducted on the segmented activities. In this dissertation, moving human blobs are described by a new feature which is a compact contour point set. Then temporal segmentation of human motion sequences is achieved by detecting the change point of the intrinsic dimensionality of feature vector, which is estimated by PCA. Experiments on two commonly used public databases demonstrate the effectiveness of our algorithm.
Videos consist of multiple types of human actions are collected by a Panasonic camera (WV-CW960) mounted on the wall, and the experimental environment coincides with the real surveillance system. An activity data set called OwnSet is constructed by the collected videos, on which the subsequent activity recognition and abnormality detection algorithms are conducted. There are six kinds of actions in OwnSet, which are walk, jogging, sitting down, squatting down, falling down, and immovability (including stand, squat, and sitting).
A system to recognize multiple kinds of activities is presented. It consists of four modules:video collection, moving objects detection and location, feature extraction, and activity classification. Background subtraction is employed to detecting moving persons. Two new features named Motion Energy Sequences (MES) and Contour Code of Motion Energy Image (CCMEI) are extracted. In the activity recognition module, the hierarchical classification thought is introduced. Two support vector machine decision-tree classifiers based on apriori knowledge and clustering results respectively are used to recognize multiple kinds of actions, and the latter classifier is more universal than the former. Experimental results on the OwnSet and a public database show that the recognition accuracy of our algorithm is bigger than other algorithms and it is roubst to incomplete human blob, heavy shadows, as well as human appearance variation.
The application of human motion analysis in intelligent surveillance is studied in this paper. Abnormality detection from multiple daily activities is conducted. Alarms will be issued in time when the olders, the children or the patients encounter a fall. An abnormality detection algorithm based on a combined classifier is presented to detect fall from the six types of actions in OwnSet. Since the causes and dangers of on-marching falling down and in-place falling down are usually different, another detection algorithm based on support vector machine is proposed. Experimental results demonstrate that both algorithms have good recognition performance and real-time performance. Therefore, the proposed algorithms are easily extended in real applications.
Finally, some difficult problems to be settled in human motion analysis system as well as the future work are listed out.
引文
[1]I. Laptev. Human actions in computer vision[R].湖北鄂州：中国莲花山研究院,2008
[2]G. Johansson. Visual Perception of biological motion and a model for its analysis[J]. Perception & Psychophysics,1973,14(2):201-211
[3]D. M. Gavrila. The visual analysis of human movement:a survey[J]. Computer vision and image understanding,1999,73(1):82-98
[4]N. M. Oliver, B. Rosario, A. P. Pentland. A Bayesian Computer Vision System for Modeling Human Interactions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):831-843
[5]S. Maybank, T. Tan. Introduction-special section on visual surveillance[J]. International Journal of Computer Vision,2000,37(2):173-173
[6]F. Lempelius, J. Pauli. Active contour based object detection[A]. International Conference on Pattern Recognition and Information Processing[C],1997,171-175
[7]王长军,朱善安.基于统计模型和活动轮廓的运动目标检测与跟踪[J].浙江大学学报(工学版),2006,40(2)：249-253
[8]郑世友,费树岷,龙飞.基于小波提升框架的图像序列中运动目标检测算法[J].中国图象图形学报,2005,10(5)：596-602
[9]S. K. Rogers, J. M. Colombi, C. E. Martin, J. C. Gainey, K. H. Fielding, T. J. Burns, D. W. Ruck, M. Kabrisky, M. Oxley. Neural networks for automatic target recognition[J]. Neural Network,1995,18(7-8):1153-1184
[10]A. Lipton, H. Fujiyoshi, R. Patil. Moving target classification and tracking from real-time video[A]. IEEE Workshop on Applications of Computer Vision[C],1998,8-14
[11]A. Verri, S. Uras, E. DeMicheli. Motion Segmentation from optical flow[A]. The 5th Alvey Vision Conference[C],1989,209-214
[12]J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques[J]. International Journal of Computer Vision,1994,12(1):42-77
[13]侯志强,韩崇昭.基于像素灰度归类的背景重构算法[J].软件学报,2005,16(9)：1568-1576
[14]C. Stauffer, W. E. L. Grimson. Adaptive background mixture models for real-time tracking[A]. Computer Vision and Pattern Recognition[C],1999,246-252
[15]A. Elgammal, D. Harwood, L. Davis. Non-Parametric model for background subtraction[A]. ECCV[C],2000,751-767
[16]C. R. Wren, A. Azarbayejani, T. Darrell, A. P. Pentland. Pfinder:real-time tracking of the human body[J]. IEEE Trans. Pattern Analysis Machine Intelligence,1997,19(7):780-785
[17]P. KaewTrakulPong, R. Bowden. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes [J]. Image and Vision Computing,2003,21:913-929
[18]岑峰,戚飞虎,陈茂林.长期视频监控系统的多分布模型背景差方法[J].红外与毫米波学报,2002,21(1)：59-63
[19]O. M. C. Ridder, H. Kirchner. Adaptive background estimation and foreground detection using Kalman-filter[A]. International Conference on Recent Advances in Mechatronics[C], 1995,193-199
[20]余胜生,肖德贵,周敬利,蒋纲.自适应背景抽取算法[J].小型微型计算机系统,2003,24(7)：1331-1334
[21]K. Kim, T. H. Chalidabhongse, D. Harwood, L. Davis. Real-time foreground-background segmentation using codebook model[J]. Real-time Imaging,2005,11(3):172-185
[22]W. Long, Y. Yang. Stationary background generation:An alternative to the difference of two images[J]. Pattern Recognition,1990,23(12):1351-1359
[23]D. Gutchess, M. Trajkonic, E. Cohen-Solal, D. Lyons, A. Jain. A background model initialization algorithm for video surveillance [A]. The 8th IEEE International Conference on Computer Vision[C],2001,733-740
[24]B. Gloyer, HK Aghajan, KY Siu, T. Kailath. Video-Based freeway monitoring system using recursive vehicle tracking[J]. The IS& T-SPIE Symp. on Electronic Imaging:Image and Video Processing,1995,2421:173-180
[25]P. Kornprobst, R. Deriche, G Aubert. Image sequence analysis via partial difference equations[J]. Journal of Mathematical Imaging and Vision,1999,11(1):5-26
[26]Y. Kuno, T. Watanabe, Y. Shimosakoda, S. Nakagawa. Automated detection of human for visual surveillance system[A]. IEEE International Conference on Pattern Recognition[C], 1996,865-869
[27]R. Collins, A. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa. A system for video surveillance and monitoring[R]. Carnegie Mellon University,2000
[28]R. Cutler, L. Davis. Robust real-time periodic motion detection, analysis, and applications[J]. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):781-796
[29]A. Lipton. Local application of optic flow to analyse rigid versus non-rigid motion. http://www.eecs.lehigh.edu/FRAME/Lipton/iccvframe.html
[30]R. T. Collins, A. J. Lipton, H. Fujiyoshi, T. Kanade. Algorithms for cooperative multisensor surveillance [A]. Proceedings of the IEEE[C],2001,1456-1477
[31]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4)：603-617
[32]D. Marr. Vision:a computational investigation into the human representation and processing of visual information[M]. San Francisco:W. H. Freeman Company,1982
[33]P. Viola. Rapid object detection using a Boosted cascade of simple features [A]. IEEE Conference on Computer Vision and Pattern Recognition[C],2001,511-518
[34]Y. Bar-Shalom, T. Fortmann. Tracking and Data Association[M]. Academic Press,1988
[35]R. E. Kalman. A New Approach to Linear Filtering and Prediction Problems[J]. Transactions of the ASME-Journal of Basic Engineering,1960,82(Series D):35-45
[36]M. Isard, A. Blake. Condensation-conditional density propagation for visual tracking[J]. International Journal of Computer Vision,1998,29(1):5-28
[37]V. Pavlovic, J. Rehg, T-J. Cham, K. Murphy. A dynamic Bayesian network approach to figure tracking using learned dynamic models[A]. IEEE International Conference on Computer Vision[C],1999,94-101
[38]W. M. Hu, T. N. Tan, L. Wang, S. Maybank. A survey on visual surveillance of object motion and behaviors [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,2004,34(3):334-352
[39]I. Karaulova, P. Hall, A. Marshall. A hierarchical model of dynamics for tracking people with a single video camera[A]. British Machine Vision Conference[C],2000,352-361
[40]S. X. Ju, M. J. Black, Y. Yacoob. Cardboard people:a parameterized model of articulated image motion[A]. International Conference on Automatic Face and Gesture Recognition[C], 1996,38-44
[41]S. Wachter, H. H. Nagel. Tracking persons in monocular image sequences[J]. Computer vision and image understanding,1999,74(3):174-192
[42]M. Kass, A. Witkin, D. Terzopoulous. Snake:active contour models[J]. International Journal of Computer Vision,1987,1(4):321-331
[43]N. Peterfreund. Robust tracking of position and velocity with Kalman snakes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(6):564-569
[44]R. Polana, R. Nelson. Low level recognition of human motion[A]. IEEE Workshop on Motion of Non-Rigid and Articulated Objects[C],1994,77-82
[45]J. Segen, S. Pingali. A camera-based system for tracking people in real time[A]. International Conference on Pattern recognition[C],1996,63-67
[46]I. Haritaoglu, D. Harwood, L.Davis. W4:who? when? where? what? A real time system for detecting and tracking people[A]. IEEE International Conference on Automatic Face and Gesture Recognition[C],1998:222-227
[47]T. Darrell, G. Gordon, M. Harville, J. Woodfill. Integrated person tracking using stereo, color, and pattern detection[J]. International Journal of Computer Vision,2000,37(2): 175-185
[48]T. Chang, S. Gong, E. Ong. Tracking multiple people under occlusion using multiple cameras[A]. British Machine Vision Conference[C],2000,566-575
[49]Q. Cai, J. K. Aggarwal. Tracking human motion using multiple cameras[A]. The 13th International Conference on Pattern Recognition[C],1996,68-72
[50]A. Utsumi, H. Mori, J. Ohya, M. Yachida. Multiple-view-based tracking of multiple humans[A]. IEEE International Conference on Pattern Recognition[C],1998,597-601
[51]D. Wei, P. Justus. Multi-Camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration[A]. Asian Conference on Computer Vision[C],2007, 365-374
[52]J. Tai, S. Tsang, C. Lin, K. Song. Real-time image tracking for automatic traffic monitoring and enforcement application[J]. Image and Vision Computing,2004,22(6): 485-501
[53]C. Pai, H. Tyan, Y. Liang, H. M. Liao, S. Chen. Pedestrian detection and tracking at crossroads[J]. Pattern Recognition,2004,37(5):1025-1034
[54]O. Masoud, N. P. Papanikolopoulos. A novel method for tracking and counting pedestrians in real-time using a single camera[J]. IEEE Transactions on Vehicular Technology, 2001,50(5):1267-1278
[55]Y. Ye, J. K. Tsotsos, E. Harley, K. Bennet. Tracking a person with prerecorded image database and a pan, tilt and zoom camera[J]. Machine Vision and Application,2000,12(1): 32-43
[56]S. M. Smith, J. M. Brady. ASSET-2:Real-time motion segmentation and shape tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8): 814-820
[57]T. Zhao, R. Nevatia. Tracking multiple humans in complex situations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1208-1221
[58]T. Yu, Y. Wu. Collaborative tracking of multiple targets[A]. IEEE Conference on Computer Vision and Pattern Recognition[C],2004,834-841
[59]S. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, H. Wechsler. Tracking groups of people[J]. Computer Vision and Image Understanding,2000,80(1):42-56
[60]M. H. Yang, N. Ahuja. Recognizing hand gesture using motion trajectories [A]. IEEE Conference on Computer Vision and Pattern Recognition[C],1999,468-472
[61]J. Yang, A. Waibel. A real-time face tracker[A]. IEEE Workshop on Applications of Computer Vision[C],1996,142-147
[62]P. Fieguth, D. Terzopoulos. Color-based tracking of heads and other mobile objects at video frame rate [A]. IEEE Conference on Computer vision and Pattern Recognition [C],1997, 21-27
[63]D. Meyer, H. Niemann. Gait classification with HMMs for Trajectories of body parts extracted by mixture densities[A]. British Machine Vision Conference[C],1998,459-468
[64]Q. Cai, A. Mitiche, J. Aggarwal. Tracking human motions in an indoor environment[A]. International Conference on Image Processing [C],1995,215-218
[65]I. Pavlidis, V. Morellas, P. Tsiamyrtzis, S. Harp. Urban surveillance system:From the laboratory to the commercial world[A]. Proceedings of the IEEE[C],2001,1478-1497
[66]T. E. Boult, R. J. Micheals, X. Gao, M. Eckmann. Into the woods:Visual surveillance of noncooperative and camouflaged targets in complex outdoor settings [A]. Proceedings of the IEEE[C],2001,1382-1402
[67]P. Remagnino, T. Tan, K.Baker. Agent orientated annotation in model based visual surveillance [A]. IEEE International Conference on Computer Vision[C],1998,857-862
[68]T. Huang, D. Koller, J. Malik, G. Ogasawara, B. Rao, S. Russell, J. Weber. Automatic symbolic traffic scene analysis using belief networks[A]. National Conference Artificial Intelligence[C],1994,966-972
[69]P. Remagnino, T. N. Tan, A. D. Worrall, K. D. Baker. Multi-agent visual surveillance of dynamic scenes[J]. Image Vision Computing,1998,16(8):529-532
[70]A. Kojima, M. Izumi, T. Tamura, K. Fukunaga. Generating natural language description of human behaviors from video images [A]. IEEE International Conference on Pattern Recognition[C],2000,728-731
[71]M. Mohnhaupy, B. Neumann. On the use of motion concepts for top-down control in traffic scene[A]. European Conference Computer Vision[C],1990,542-550
[72]Y. D. Rubinstein, T. Hastie. Discriminative vs informative learning[A]. Third International Conference on Knowledge Discovery and Data Mining[C],1997,49-53
[73]J. K. Aggarwal, Q. Cai. Human motion analysis:A review[J]. Computer Vision and Image Understanding,1999,73(3):428-440
[74]A. Bobick, J. Davis. Real-time recognition of activity using temporal templates[A]. IEEE Workshop on Applications of Computer Vision[C],1996,39-42
[75]J. Farmer, M. Casdagli, S. Eubank, J. Gibson. State-space reconstruction in the presence of noise[J]. Physics D,1991,51D:52-98
[76]L.W. Campbell, A. F. Bobick. Recognition of human body motion using phase space constraints [A]. Fifth International conference on computer vision[C],1995,624-630
[77]C. Bregler. Learning and recognizing human dynamics in video sequences [A]. IEEE Conference on Computer Vision and Pattern Recognition[C],1997,568-574
[78]Y. Luo, T. D. Wu, J. N. Hwang. Object-based analysis and interpretation of human motion in sports video sequences by dynamic Bayesian networks[J]. Computer vision and image understanding,2003,92(2):196-216
[79]A. F. Bobick, J. W. Davis. The recognition of human movement using temporal templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(3): 257-267
[80]D. Weinland, R. Ronfarda, E. Boyer. Free viewpoint action recognition using motion history volumes[J]. Computer vision and image understanding,2006,104(2):249-257
[81]T. Xiang, S. Gong, D. Parkinson. Autonomous visual events detection and classification without explicit object-centered segmentation and tracking [A]. British Machine Vision Conference[C],2002,133-242
[82]H. Y. Meng, N. Pears. Descriptive temporal template features for visual motion recognition[J]. Pattern Recognition Letters,2009,30(12):1049-1058
[83]A. Y. Ng, M. I. Jordan. On discriminative vs. generative classifiers:A comparison of logistic regression and naive bayes[J]. Advances in Neural Information Processing Systems, 2002,14:841-848
[84]L. Rabinier. A tutorial on hidden Markov models and selected applications in speech recognition[A]. Proceedings of the IEEE[C],1989,257-285
[85]J. Yamato, J. Ohya, K. Ishii. Recognizing human action in time-sequential images using hidden Markov model[A]. IEEE Conference on Computer Vision and Pattern Recognition[C], 1992,379-385
[86]S. Gong, T. Xiang. Recognition of group activities using dynamic probabilistic networks[A]. International Conference on Computer Vision[C],2003,742-749
[87]V. Pavlovic, B. J. Grey, T. S. Huang. Time-series classification using mixed-stated dynamic Bayesian networks[A]. Proceedings of Computer Vision and Pattern Recognition[C], 1999,609-615
[88]I. Kolonias, W. Christmas, J. Kittler. Use of context in automatic annotation of sports videos[A]. Iberoamerican Congress on Pattern Recognition [C],2004,1-12
[89]H. Ren, G. Xu. Human action recognition with primitive-based coupled HMM[A]. International Conference on Pattern Recognition[C],2002,494-498
[90]M. Brand, N. Oliver, A. Pentland. Coupled hidden markov models for complex action recognition[A]. Proceedings of Computer Vision and Pattern Recognition[C],1997,994-999
[91]N. T. Nguyen, D. Q. Phung, S. Venkatesh, H. Bui. Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model [A]. Proceedings of Computer Vision and Pattern Recognition[C],2005,955-960
[92]S. Park, J. K. Aggarwal. A hierarchical Bayesian network for event recognition of human actions and interactions[J]. Multi-media Systems,2004,10(2):164-179
[93]T. V. Duong, H. H. Bui, D. Q. Phung, S. Venkatesh. Activity recognition and abnormality detection with the switching hidden semi-Markov model [A]. Proceedings of Computer Vision and Pattern Recognition[C],2005,838-845
[94]H. H. Bui, S. Venkatesh, G. West. Policy recognition in the Abstract Hidden Markov Model[J]. Journal of Artificial Intelligence Research,2002,17:451-499
[95]N. Oliver, Eric Horvitz, A. Garg. Layered Representations for Human Activity Recognition[A]. IEEE International Conference on Multimodal Interfaces[C],2002,3-8
[96]N. Oliver, E. Horvitz. A comparison of HMMs and dynamic Bayesian networks for recognizing office activities [A]. User Modeling[C],2005,199-209
[97]O. Boiman, M. Irani. Detecting Irregularities in Images and in Video [A]. International Conference on Computer Vision[C],2005,462-469
[98]H. Zhong, J. Shi, V. Mirk'o. Detecting Unusual Activity in Video [A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],2004,819-826
[99]H. N. Zhou, D. Kimber. Unusual event detection via multi-camera video mining[A]. International conference on Pattern Recognition[C],2006,1161-1166
[100]P. C. Chung, C. D. Liu. A daily behavior enabled hidden Markov model for human behavior understanding [J]. Pattern Recognition,2008,41(5):1589-1597
[101]Y. T. Du, F. Chen, W. L. Xu, Y. B. Li. Recognizing interaction activities using dynamic Bayesian network[A]. International conference on Pattern Recognition[C],2006,618-621
[102]C. Piciarelli, G. L. Foresti. On-line trajectory clustering for anomalous event detection[J]. Pattern Recognition Letters,2006,27:1835-1842
[103]N. Suzuki, K. Hirasawa, K. Tanaka, Y. Kobayashi, Y. Sato, Y. Fujino. Learning motion patterns and anomaly detection by human trajectory analysis[A]. IEEE international conference on Systems, Man and Cybernetics[C],2007,498-503
[104]A. Mokhber, C. Achard, M. Milgram. Recognition of human behavior by space-time silhouette characterization[J]. Pattern Recognition Letters,2008,29:81-89
[105]X. Y. Wu, Y. S. Ou, H. H. Qian, Y. S. Xu. A detection system for human abnormal behavior[A]. IEEE international conference on Intelligent Robots and Systems[C],2005, 1204-1208
[106]Y. Wang, K. Q. Huang, T. T. Tan. Abnormal activity recognition in office based on R transform[A]. IEEE international conference on Image Processing[C],2007,341-344
[107]A. Adam, E. Rivlin, I. Shimshoni, D. Reinitz. Robust real-time unusual event detection using multiple fixed-location monitors[J]. IEEE transactions on Pattern Analysis and Machine Intelligence,2008,30(3):555-560
[108]J. K. Aggarwal, Q. Cai, W. Liao, B. Sabata. Articulated and elastic non-rigid motion:A review [A]. IEEE Workshop on Motion of Non-Rigid and Articulated Objects [C],1994,2-14
[109]C. Cedras, M. A. Shah. Motion Based Recognition:A Survey[J]. Image and Vision Computing,1995,13(2):129-155
[110]A. Pentland. Looking at people:sensing for ubiquitous and wearable computing[J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(1):107-119
[111]T. B. Moeslund, E. Granum. A Survey of Computer Vision-Based Human Motion Capture [J]. Computer Vision and Image Understanding 2001,81(3):231-268
[112]J. J. Wang, S. Singh. Video Analysis of Human Dynamics-a Survey[J]. Real-Time Imaging,2003,9(5):321-346
[113]R. Poppe. Vision-based human motion analysis:An overview[J]. Computer Vision and Image Understanding,2007,108(1-2):4-18
[114]王亮,胡卫明,谭铁牛。人运动的视觉分析综述[J].计算机学报,2002,25(3)：225-237
[115]刘相滨,向坚持,王胜春.人行为识别与理解研究探讨[J].计算机与现代化,2004,12：1-5,27
[116]杜友田,陈峰,徐文立,李永彬.基于视觉的人的运动识别综述[J].电子学报,2007,35(1)：84-90
[117]凌志刚,赵春晖,梁彦,潘泉,王燕.基于视觉的人行为理解综述[J].计算机应用研究,2008,25(9)：2570-2578
[118]L. Wang, W. M. Hu, T. N. Tan. Recent Developments in Human Motion Analysis[J]. Pattern Recognition,2003,36(3):585-601
[119]X. Feng, P. Perona. Human action recognition by sequence of movelet codewords[A]. International Symposium on 3D Data Processing Visualization and Transmission[C],2002, 717-721
[120]J. Ben-Arie, Z. Wang, P. Pandit, S. Rajaram. Human activity recognition using multidimensional indexing[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(8):1091-1104
[121]A. Yilmaz, M. Shah. Actions sketch:a novel action representation[A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],2005,984-989
[122]A. Yilmaz, M. Shah. Recognizing human actions in videos acquired by uncalibrated moving cameras[A]. IEEE International Conference on Computer Vision[C],2005,150-157
[123]V. Kellokumpu, M. Pietikainen, J. Heikkila. Human activity recognition using sequences of postures[A]. IAPR conference on Machine Vision Applications[C],2005, 570-573
[124]A. A. Efros, A. C. Berg, G. Mori, J. Malik. Recognizing action at a distance[A]. IEEE International Conference on Computer Vision[C],2003,726-733
[125]C. Schuldt, I. Laptev, B. Caputo. Recognizing human actions:A local svm approach[A]. 17th International Conference on Pattern Recognition[C],2004,32-36
[126]P. Dollar, V. Rabaud, G. Cottrell, S. Belongie. Behavior recognition via sparse spatio-temporal features [A]. IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance[C],2005,65-72
[127]Y. Yacoob, M. J. Black. Parameterized modelling and recognition of activities [J]. Computer Vision and Image Understanding,1999,73 (2):232-247
[128]A. Madabhushi, J. K. Aggarwal. A bayesian approach to human activity recognition[A]. IEEE Workshop on Visual Surveillance[C],1999,25-32
[129]C. Roberto, A. P. Pentland. Computer Vision for Human-Machine Interaction[M]. Cambridge University Press,1998
[130]W. Freeman, C. Weissman. Television control by hand gestures[A]. International Conference on Automatic Face and Gesture Recognition[C],1995,179-183
[131]Human ID at a Distance. http://infowar.net/tia/www.darpa.mil/iao/HID.htm
[132]B. Boghossian, S. Velastin. Image processing system for pedestrian monitoring using neural classification of normal motion patterns[J]. Measurement and Control,1999,32(9): 261-264
[133]B. Boghossian, S. Velastin. Motion-based machine vision techniques for the management of large crowds[A]. IEEE 6th International Conference on Electronics, Circuits and systems[C],1999,961-964
[134]P. Ribeiro, J. Santos-Victor. Human Activities Recognition from Video:modeling, feature selection and classification architecture [A]. Workshop on Human Activity Recognition and Modeling[C],2005,61-70
[135]J. L. Crowley, P. Reignier. Dynamic Composition of Process Federations for Context Aware Perception of Human Activity [A]. International Conference on Integration of Knowledge Intensive Multi-Agent Systems[C],2003,300-305
[136]Esprit project:Image processing operations for forensic support. http://cordis.europa.eu/esprit/src/23515.htm
[137]BEHAVE:Computed-assisted prescreening of video streams for unusual activities. http://homepages.inf.ed.ac.uk/rbf/BEHAVE/
[138]I. Haritaoglu, D. Harwood, L. S. Davis. W4:real-time surveillance of people and their activities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8): 809-830
[139]The Multiple-camera/Multiple-video Database of the PERCEPTION group. https://charibdis.inrialpes.fr/html/non-secure-sequence.php?s=IXMAS
[140]M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri. http://www.wisdom.weizmann.ac.il/-vision/SpaceTimeActions.html#Database
[141]C. Schuldt, I. Laptev, B. Caputo. http://www.nada.kth.se/cvap/actions/
[142]Computatinal Perception Lab http://www.cc.gatech.edu/cpl/projects/monsoon/PropagationNet/PropagationNet.htm
[143]Center for Intelligent Systems http://cis.cs.technion.ac.il/index.php?option=com frontpage&Itemid=1
[144]P. Perona, J. Malik. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1990,12(7):629-639
[145]F. Catte, P. L. Lions, J. M. Morel, T. Coll. Image selective smoothing and edge detection by nonlinear diffusion[J]. SIAM Journal on Numerical Analysis,1992,29(1):182-193
[146]Y. M. Chen, P. Bose. On the incorporation of time-delay regularization into curvature-based diffudion[J]. Journal of Mathematical Imaging and Vision,2001,14:149-164
[147]G. Guy, A. S. Nir, Y. Z. Yehoshua. Image enhancement and denoising by complex diffusion process[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2004, 29(8):1021-1036
[148]F. Voci, S. Eiho, N. Sugimoto, H. Sekiguchi. Estimating the gradient threshold in the Perona-Malik equation[J]. IEEE Signal Processing Magazine,2004:39-46,65
[149]余庆军,谢胜利.基于人类视觉系统的各向异性扩散图像平滑方法[J].电子学报,2004,32(1)：17-20
[150]G. L. Anderson, A. N. Netravali. Image restoration based on a subjective criterion[J]. IEEE Transactions on System, Man, and Cybernetics,1976, SMC-6:845-853
[151]A. K. Katsaggelos, J. Biemond,R.W. Schafer,R.M.Mersereau. A regularized iterative image restoration algorithm[J]. IEEE Transaction on Signal Processing,1991,39(4):914-929
[152]J. Weickert, B. Benamouda. A semi-discrete non-linear scale-space theory and its relation to the Perona-Malik paradox[A]. Advances in Computer Vision[C],1997,1-10
[153]Z. Wang, A. C. Bovik, H. R. Sheikh, E. P. Simoncelli. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4): 600-612
[154]D. Comaniciu, V. Ramesh, P. Meer. Kernel-Based object tracking[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(5):64-575
[155]彭宁嵩,杨杰,刘志,张风超.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9)：1542-1550
[156]彭宁嵩,杨杰,周大可,刘志.Mean-Shift跟踪算法中目标模型的自适应更新[J].数据采集与处理,2005,20(2)：125-129
[157]R. T. Collins. Mean-Shift blob tracking through scale space[A]. IEEE International Conference on Computer Vision and Pattern Recognition[C],2003,234-240
[158]G. R. Bradski, S. Clara. Computer vision face tracking for use in a perceptual user interface[J]. Intelligence Technology Journal,1998,:1-15
[159]D. Comaniciu, V. Ramesh, P. Meer. The variable bandwidth mean shift and datadriven scale selection[A]. IEEE International Conference on Computer Vision[C],2001:438-445
[160]K. Nummiaro, E. Koller-Meier, L. V. Gool. An adaptive color-based particle filter[J]. Image and Vision Computing,2003,21:99-110
[161]K. Fukunaga, L. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transaction on Information Theory,1975,21(1): 32-40
[162]C. Yizong. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799
[163]D. Comaniciu, P. Meer. Mean shift:a robust approach toward feature space analysis[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2002,24(5):603-619
[164]D. Comaniciu, V. Ramesh, P. Meer. Real-Time tracking of non-rigid objects using mean shift[A]. IEEE International Proceeding on Computer Vision and Pattern Recognition[C], 2000,142-149
[165]A. Doucet, D. F. Nando, N. Gordon, sequential monte carlo methods in practice[M]. New York:Springer-Verlag,2001
[166]M. S. Arulampalam, S. Maskell, N. Gordon, T. Clapp. A tutorial on particle filters for online nonlinear non-gaussian bayesian tracking[J]. IEEE Transactions on Signal Processing, 2002,50(2):174-188
[167]王郑耀,程正兴,汤少杰.基于视觉特征的尺度空间信息量度量[J].中国图象图形学报,2005,10(7)：922-928
[168]T. Xiang, S. G. Gong. Video behaviour profiling and abnormality detection without manual labeling[A]. Internation Conference on Computer Vision[C],2005,1238-1245
[169]Y. Rui, P. Anandan. Segmenting visual actions based on spatio-temporal motion patterns[A]. IEEE Conf. on Computer Vision and Pattern Recognition[C],2000,111-118
[170]L. Zelnik-Manor, M. Irani. Event-Based analysis of video[A]. IEEE Conference on Computer Vision and Pattern Recognition[C],2001,123-130
[171]H. Li, Z. Hu, Y. Wu, F. Wu. Behavior modeling and recognition based on space-time image features[A]. International Conference on Pattern Recognition[C],2006,243-246
[172]吴晓婕,胡占义,吴毅红.基于Segmental-DTW的无监督行为序列分割[J].软件学报,2008,19(9)：2285-2292
[173]Y. Rui, P. Anandan. Segmenting visual actions based on spatio-temporal motion patterns[A]. IEEE Conference on Computer Vision and Pattern Recognition[C],2000, 111-118
[174]A. Ali, J. K. Aggarwal. Segmentation and recognition of continuous human activity [A]. IEEE Workshop on Detection and Recognition of Events in Video[C],2001,28-35
[175]D. Y. Chen, H. Y. Mark Liao, S. W. Shih. Continuous Human Action Segmentation and Recognition Using A Spatio-Temporal Probabilistic Framework[A]. IEEE International Symposium on Multimedia[C],2006,275-282
[176]D. Y. Chen, H. Y. Mark Liao, S. W. Shih. Atomic Human Action Segmentation and Recognition Using A Spatio-Temporal Probabilistic Framework[J]. International Journal of Semantic Computing,2007,1(2):205-220
[177]C. Bauckhage, J. K. Tsotsos, F. E. Bunn. Automatic detection of abnormal gait[J]. Image and Vision Computing,2009,27(1-2):108-115
[178]J. Barbic, A. Safonova, J. Y. Pan, C. Faloutsos, J. K. Hodgins, N. S. Pollard. Segmenting motion capture data into distinct behaviors[A]. Proceedings of Graphics Interface, ACM International Conference Proceeding Series[C],2004,185-194
[179]R. O. Duda, P. E. Hart, D. G. Stork.模式分类(第2版)[M].李宏东,姚天翔等,译.北京：机械工业出版社,2003
[180]K. Murphy. Hidden Markov Model Toolbox for Matlab
http://people.cs.ubc.ca/-murphyk/Software/HMM/hmm.html
[181]A. Prati, I. Mikic, M. M. Trivedi, R.Cucchiara, Detecting Moving Shadows:Algorithms and Evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(7):918-923
[182]T. Horprasert, D. Harwood, L. S. Davis. A statistical approach for real-time robust background subtraction and shadow detection[A]. ICCV FRAME-RATE Workshop[C],1999, 1-19
[183]I. Mikic, P. Cosman, G. Kogut, M. M. Trivedi. Moving shadow and object detection in traffic scenes[A]. International Conference on Pattern Recognition[C],2000,321-324
[184]M. Kilger. A shadow handler in a video-based real-time traffic monitoring system[A]. IEEE Workshop on Applications of Computer Vision[C],1992,11-18
[185]J. Stauder, R. Mech, J. Ostermann. Detection of moving cast shadows for object segmentation[J]. IEEE Transactions on Multimedia,1999,1(1):65-76
[186]R. Cucchiara, C. Grana, G Neri, M. Piccardi, A. Prati. The Sakbot system for moving object detection and tracking[J]. Video-based Surveillance Systems-Computer Vision and Distributed Processing,2001,145-157
[187]W. K. Pratt. Digital image Processing[M]. New York:John Wiley & Sons,2001
[188]R. Mukundan, K. R. Ramakrishnan. Fast computation of legendre and zernike moments[J]. Pattern Recognition,1995,28(9):1433-1442
[189]K. P. Bennett, N. Cristianini, J. Shawe-taylor, D. Wu. Enlarging the margins in perceptron decision trees [J]. Machine Learning 2000,41(3):295--313
[190]M. R. Azimi-Sadjadi, S. A. Zekavat. Cloud classification using support vector machines[A]. International Geoscience and Remote Sensing Symposium[C],2000,669-671
[191]J. C. Platt, N. Cristianini, J. Shawe-Taylor. Large margin dags for multiclass classification[J]. Advances in Neural Information Processing Systems,2000,12:547-553
[192]A. Gammerman. Machine Learning:Progress and Prospects[D]. Royal Holloway, Egham, UK:University of London,1996
[193]J. Nilsson. Introduction to machine learning[D]. Stanford University,1996
[194]罗瑜.支持向量机在机器学习中的应用研究[D].西南交通大学,2007
[195]F. Rosenblatt. The perceptron:a probabilistic model for information storage and organization in the brain[J]. Psychological Revies,1958,65:386-408
[196]V. N. Vapnik. The Nature of Statistical Learning Theory[M]. New York.: Springer-Verlag,1995
[197]V. N.Vapnik. Statistical Learning Theory[M]. New York:John Wiley and Sons Inc., 1998:
[198]J. Weston, C. Watkins. Multi-class support vector machines[A]. ESANN[C],1999:1-2
[199]黄良力.多分类支持向量机综述[J].中国水运(学术版),2006,6(5)：72-74
[200]U. H. G. KreBel. Pairwise classification and support vector machines, Advances in kernel methods:support vector learning[M]. Cambridge, MA:USA MIT Press,1999, 255-268
[201]T. G. Dietterich, G. Bakiri. Solving multiclass learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research,1995,2:263-286
[202]夏建涛,何明一.支持向量机与纠错编码相结合的多类分类算法[J].西北工业大学学报,2003,21(4)：443-446
[203]S. Cheong, S. H. Oh, S. Y. Lee. Support vector machines with binary tree architecture for multi-class classification[J]. Neural Information Processing:Letters and Reviews,2004, 2(3):47-51
[204]Y. Yang, J. O. Pedersen. A comparative study on feature selection in text categorization[A]. Proceedings of the Fourteenth International Conference on Machine Learning[C],1997:412-420
[205]Y. Yeo, P. Ahammad, K. Ramchandran, S. S. Sastry. Compressed domain real-time action recognition[A]. IEEE International workshop in multimedia signal processing[C],2006: 33-36
[206]K. Yan, R. Sukthankar, M. Hebert. Efficient visual event detection using volumetric features[A]. IEEE International Conference on Computer Vision[C],2005:166-173
[207]J. C. Niebles, H. Wang, F. Li. Unsupervised learning of human action categories using spatial-temporal words.[J]. International Journal of Computer Vision,2008,79:299-318
[208]S. J. Lu, J. Zhang, D. D. Feng. Detecting Unattended packages through human activity recognition and object association[J]. Pattern Recognition,2007,40(8):2173-2184
[209]李和平,胡占义,吴毅红,吴福朝.基于半监督学习的行为建模与异常检测[J].软件学报,2007,18(3)：527-537
[210]D. Zhang, D. Gatica-Perez, S. Bengio, I. McCowan. Semi-supervised adapted HMMs for unusual event detection[A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],2005:611-618
[211]C. Doukas, I. Maglogiannis, P. Tragas, D. Liapis, G. Yovanof. Patient Fall Detection using Support Vector Machines [A]. IFIP International Federation for Information Processing, Artificial Intelligence and Innovations:From Theory to Applications[C],2007:147-156
[212]N. Noury, T. Herve, V. Rialle, G. Virone, E. Mercier, G. Morey, A. Moro, T. Porcheron. Monitoring behavior in home using a smart fall sensor and positionsensors[A].1st Annual International Conference on Microtechnologies in Medicine and Biology[C],2000:607-610
[213]T. Tamura, T. Yoshimura, F. Horiuchi, Y. Higashi, T. Fujimoto. An ambulatory fall monitor for the elderly[A].22nd Annual International Conference of the IEEE EMBS[C], 2000:2608-2610
[214]S. Liihr, S. Venkatesh, G. West, H. H. Bui. Explicit State Duration HMM for Abnormality Detection in Sequences of Human Activity [A]. Pacific Rim International Conference on Artificial Intelligence[C],2004:983-984
[215]李冠德.应用于居家看护系统之人体动作辨识模糊规则设计[D].电机工程学研究所,台湾：国立台湾大学,2005
[216]B. Toreyin, Y. Dedeoglu, A. Cetin. HMM based falling person detection using both audio and video[A]. IEEE International Workshop on Human-Computer Interaction[C],2005: 211-220
[217]C. Rougier, J. Meunier, A. St-Arnaud, J. Rousseau. Fall Detection from Human Shape and Motion History Using Video Surveillance [A].21st International Conference on AINAW 2007[C],2007:875-880
[218]T. Ji, M. Turjo, M. F. Wong, M. D. Wang, Y. P. Tan. Fall Incidents Detection for Intelligent Video Surveillance [A]. Fifth International Conference on Information, Communications and Signal Processing[C],2005:1590-1594
[219]D. A. Winter. The Biomechanics and Motor Control of Human Movement[M]. John Wiley & Sons,1990
[220]J. Kittler. Combining classifiers:A theoretical framework[J]. Pattern Analysis and Applications,1998,1(1):18-27
[221]J. Kittler, M. Hatef, R. P. W. Duin, J. Matas. On combining classifiers [J]. IEEE Transactions on Pattern Analysis and Applications,1998,20(3):226-239
[222]潘翔.基于多分类器集成的模式识别研究[D].杭州：浙江工业大学,2001
[223]C. J. Lin. http://www.csie.ntu.edu.tw/-cjlin/