基于视觉的人体检测与跟踪
|
摘要
人体检测和跟踪是计算机视觉的重要研究课题之一,其应用已经遍及智能监控、体育运动分析、新型人机交互和虚拟现实等领域,研究基于视觉的人体检测和跟踪有着很重要的现实意义。
本文研究了在智能家居环境中人体检测与人体运动跟踪问题,主要工作和特色如下:
1.对人体运动图像分析的关键技术进行了综述。详细介绍了人体运动图像中从初始化模型、人体跟踪、姿态估计和行为识别的各个步骤,及其主要的研究方法与进展,以及存在的问题。
2.研究了一种改进的自适应混合高斯模型的人体检测算法。家居背景经常发生变化,需要采用混合高斯函数来做背景建模。已有的自适应混合高斯模型可以快速对背景进行建模,但是当人体在某个空间位置短暂停留时,就会被学习成背景。本文采用一种近似S曲线函数的分段指数函数来修正学习率和新的背景高斯成分的权重,并结合形态学、中值滤波和图像金字塔技术,有效地减除了人体阴影,降低了背景噪声的影响。
3.研究了一种融合了混合高斯模型和粒子群优化的自动人体跟踪算法利用混合高斯背景模型给出的目标前景区域,缩小跟踪的范围;利用粒子群优化方法对状态空间的随机搜索能力,寻找人体目标的最优空间位置,最后将两者的信息融合对比,实现自动的人体跟踪算法。本算法框架为每个跟踪目标维护一个历史灰度直方图信息,并在人体遮挡、人体目标离开场景等目标消失情况下,可以在稍后图像帧中自动地恢复跟踪和识别目标。
The detection and tracking of human body is an important problem in the computer vision field. Its application has spread intelligent monitoring, sports analysis, a new human computer interaction and virtual reality and other fields. Researching the technology of the human detection and tracking based on vision has very important practical significance. Body detection in the smart home environment and human motion tracking based on video have been studied in this dissertation. The main work and characteristic are as fol-lows:
1. The key technologies of human movement image analysis were reviewed.
This paper gives detail steps in the human motion image which contain the initialization model, human tracking, pose estimation and behavior recognition, the major research methods, the progress and problems.
2. Research an improved adaptive Gaussian mixture model for human detection algo-rithm.
The frequent changes in the home background need to be described by the mixed Gaussian function modeling. Existing adaptive Gaussian mixture models can quickly model the background, but when the body stays a short time at a position, they will learn it for the background. S-Curve function which is an approximate piecewise exponential function is used to modify the background learning rate and the new Gaussian component weights. After that, a combination of morphology, median filtering and image Pyramid Technology, is used to cuts off human shadow and reduces the background noise.
3. Research an automatic human tracking algorithm by the fusion of Gaussian mixture model and particle swarm optimization.
The target foreground area given by Gaussian mixture background model is used to narrow the range of human tracking. The random search capability of particle swarm op-timization method in the state space is used to find the optimal spatial location of the body. Finally, the information fusion between them can achieve automatic human tracking al-gorithm. The algorithm framework maintains a history of histogram information for each tracking object, and can automatically recover tracking and identify targets in the later image frame when self-occlusion or human target leaving the scene.
本文研究了在智能家居环境中人体检测与人体运动跟踪问题,主要工作和特色如下:
1.对人体运动图像分析的关键技术进行了综述。详细介绍了人体运动图像中从初始化模型、人体跟踪、姿态估计和行为识别的各个步骤,及其主要的研究方法与进展,以及存在的问题。
2.研究了一种改进的自适应混合高斯模型的人体检测算法。家居背景经常发生变化,需要采用混合高斯函数来做背景建模。已有的自适应混合高斯模型可以快速对背景进行建模,但是当人体在某个空间位置短暂停留时,就会被学习成背景。本文采用一种近似S曲线函数的分段指数函数来修正学习率和新的背景高斯成分的权重,并结合形态学、中值滤波和图像金字塔技术,有效地减除了人体阴影,降低了背景噪声的影响。
3.研究了一种融合了混合高斯模型和粒子群优化的自动人体跟踪算法利用混合高斯背景模型给出的目标前景区域,缩小跟踪的范围;利用粒子群优化方法对状态空间的随机搜索能力,寻找人体目标的最优空间位置,最后将两者的信息融合对比,实现自动的人体跟踪算法。本算法框架为每个跟踪目标维护一个历史灰度直方图信息,并在人体遮挡、人体目标离开场景等目标消失情况下,可以在稍后图像帧中自动地恢复跟踪和识别目标。
The detection and tracking of human body is an important problem in the computer vision field. Its application has spread intelligent monitoring, sports analysis, a new human computer interaction and virtual reality and other fields. Researching the technology of the human detection and tracking based on vision has very important practical significance. Body detection in the smart home environment and human motion tracking based on video have been studied in this dissertation. The main work and characteristic are as fol-lows:
1. The key technologies of human movement image analysis were reviewed.
This paper gives detail steps in the human motion image which contain the initialization model, human tracking, pose estimation and behavior recognition, the major research methods, the progress and problems.
2. Research an improved adaptive Gaussian mixture model for human detection algo-rithm.
The frequent changes in the home background need to be described by the mixed Gaussian function modeling. Existing adaptive Gaussian mixture models can quickly model the background, but when the body stays a short time at a position, they will learn it for the background. S-Curve function which is an approximate piecewise exponential function is used to modify the background learning rate and the new Gaussian component weights. After that, a combination of morphology, median filtering and image Pyramid Technology, is used to cuts off human shadow and reduces the background noise.
3. Research an automatic human tracking algorithm by the fusion of Gaussian mixture model and particle swarm optimization.
The target foreground area given by Gaussian mixture background model is used to narrow the range of human tracking. The random search capability of particle swarm op-timization method in the state space is used to find the optimal spatial location of the body. Finally, the information fusion between them can achieve automatic human tracking al-gorithm. The algorithm framework maintains a history of histogram information for each tracking object, and can automatically recover tracking and identify targets in the later image frame when self-occlusion or human target leaving the scene.
引文
[1] T.B. Moeslund, E. Granum. A survey of computer vision‐based human motion capture, Com‐puter Vision and Image Understanding 81 (3) (2001) 231–268.
[2] C. Barron, I.A. Kakadiaris. Estimating anthropometry and pose from a single image, in: Com‐puter Vision and Pattern Recognition, Hilton Head Island, South Carolina, June 13–15, 2000.
[3] C. Barron, I.A. Kakadiaris. On the improvement of anthropometry and pose estimation from a single uncalibrated image, Machine Vision and Applications 14 (4) (2003) 229–236.
[4] V. Parameswaran, R. Chellappa. View independent human body pose estimation from a single perspective image, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[5] C.J. Taylor. Reconstruction of articulated objects from point correspondences in a single im‐age, Computer Vision and Image Understanding 80 (3) (2000) 349–363.
[6] N. Krahnstoever, R. Sharma. Articulated models from video. Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[7] N. Krahnstoever, M. Yeasin, R. Sharma. Automatic acquisition and initialization of articulated models, Machine Vision and Applications 14 (4) (2003) 218–228.
[8] Y. Song, L. Goncalves, P. Perona. Unsupervised learning of human motion, IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (7) (2003) 814–827.
[9] G. Cheung, S. Baker, T. Kanade. Shape‐from‐silhouette for articulated objects and its use for human body kinematics estimation and motion capture, in: Computer Vision and Pattern Recog‐nition, Madison, Wisconsin, USA, June 16–22, 2003.
[10] C. Menier, E. Boyer, B. Raffin, 3D skeleton‐based body pose recovery, in: International Sym‐posium on 3D Data Processing, Visualisation and Transmission, 2006.
[11] G.J. Brostow, I. Essa, D. Steedly, V. Kwatra, Novel skeletal representation for articulated creatures, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[12] C.‐W. Chu, O.C. Jenkins, M.J. Mataric, Markerless kinematic model and motion capture from volume sequences, in: Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, June 16–22, 2003.
[13] T.B. Moeslund, E. Granum, Pose estimation of a human arm using kinematic constraints, in: The 12th Scandinavian Conference on Image Analysis, Bergen, Norway, 2001.
[14] T.B. Moeslund, M. Vittrup, K.S. Pedersen, M.K. Laursen, M.K.D. Soensen, H. Uhrenfeldt, E. Granum, Estimating the 3D shoulder position using monocular vision, in: International Confe‐rence on Imaging Science, Systems, and Technology, Las Vegas, Nevada, June 24–27, 2002.
[15] J. Mulligan, Upper body pose estimation from stereo and hand‐face tracking, in: Canadian Conference on Computer and Robot Vision, Victoria, British Columbia, Canada, May 9–11, 2005.
[16] L. Herda, R. Urtasun, P. Fua, Hierarchical implicit surface joint limits to constrain video‐based motion capture, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[17] L. Herda, R. Urtasun, P. Fua, Hierarchical implicit surface joint limits for human body tracking, Computer Vision and Image Understanding 99 (2) (2005) 189–209.
[18] T.B. Moeslund, C.B. Madsen, E. Granum, Modelling the 3D pose of a human arm and the shoulder complex utilising only two parameters, International Journal on Integrated Comput‐er‐Aided Engineering 12 (2) (2005) 159–177.
[19] http://www.charactermotion.com/products/powermoves/megamocap/.
[20] http://mocap.cs.cmu.edu/.
[21] http://www.ict.usc.edu/graphics/animWeb.
[22] A. Hilton, D. Beresford, T. Gentils, R. Smith, W. Sun, Virtual people: capturing human models to populate virtual worlds, in: International Conference on Computer Animation, May 1999.
[23] J. Carranza, C. Theobalt, M. Magnor, H.‐.P. Seidel, Free‐viewpoint video of human actors, in: ACM SIGGRAPH, 2003, pp. 565—577.
[24] R. Plankers, P. Fua, Articulated soft objects for multi‐view shape and motion capture, IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (9) (2003) 1182–1187.
[25] J. Starck, A. Hilton, Model‐based multiple view reconstruction of people, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[26] B. Allen, B. Curless, Z. Popovic, Articulated body deformation from range scan data, in: ACM SIGGRAPH, 2002, pp. 612—619.
[27] J. Starck, G. Collins, R. Smith, A. Hilton, J. Illingworth, Animated statues, Journal of Machine Vision and Applications 14 (4) (2003) 248–259.
[28] B. Allen, B. Curless, Z. Popovic, The space of human body shapes: reconstruction and para‐meterization from range images, in: ACM SIGGRAPH, 2003, pp. 587—594.
[29] M.N. Thalmann, H. Seo, Data‐driven approaches to digital human modeling, in: International Symposium on 3D Data Processing, Visualization, and Transmission, Thessalonica, Greece, Sep 2004.
[30] H. Sidenbladh, M.J. Black, Learning image statistics for Bayesian tracking, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[31] H. Sidenbladh, M.J. Black, Learning the statistics of people in images and video, International Journal of Computer Vision 54 (1/2/ 3) (2003) 183–209.
[32] T.J. Roberts, S.J. McKenna, I.W. Ricketts, Adaptive learning of statistical appearance models for 3D human tracking, in: British Machine Vision Conference, Cardiff, UK, 2002.
[33] A. Micilotta, E. Ong, R. Bowden, Detection and tracking of humans by probabilistic body part assembly, in: British Machine Vision Conference, Oxford, UK, Sep 2005.
[34] D. Ramanan, D.A. Forsyth, A. Zisserman, Strike a pose: tracking people by finding stylized poses, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[35] T.J. Roberts, S.J. McKenna, I.W. Ricketts, Human pose estimation using learnt probabilistic region similarities and partial configurations, in: European Conference on Computer Vision, Pra‐gue, Czech Republic, May 11–14, 2004.
[36] R. Ronfard, C. Schmid, B. Triggs, Learning to parse pictures of people, in: European Confe‐rence on Computer Vision, Copenhagen, Denmark, June 27–31, 2002.
[37] P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features, in: Computer Vision and Pattern Recognition, Kauai Marriott, Hawaii, Dec 9–14, 2001.
[38] H. Lim, V.I. Morariu, O.I. Camps, M. Sznaier, Dynamic appearance modeling for human tracking, in: Computer Vision and Pattern Recognition, New York City, New York, USA, June 17–22, 2006.
[39] C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real‐time tracking, in: Computer Vision and Pattern Recognition, Santa Barbara, CA, June 1998.
[40] H. Sidenbladh, Detecting human motion with support vector machines, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[41] J.J. Gonzalez, I.S. Lim, P. Fua, D. Thalmann, Robust tracking and segmentation of human mo‐tion in an image sequence, in: International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, April 2003.
[42] P. Sangi, J. Heikkila, O. Silven, Extracting motion components from image sequences using particle filters, in: The 12th Scandinavian Conference on Image Analysis, Bergen, Norway, 2001.
[43] G.R. Bradski, J.W. Davis, Motion segmentation and pose recognition with motion history gradients, Machine Vision and Applications 13 (3) (2002) 174–184.
[44] J.W. Davis, A. Bobick, The representation and recognition of action using temporal templates, in: Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, June 1997.
[45] Collins,Lipton,Kanade,Fujiyoshi,Duggins,Tsin, Tolliver,Enomoto, Hasegawa, A system for video surveillance and monitoring: VSAM final report, Technical report CMU‐RI‐TR‐00‐12, Robot‐ics Institute, Carnegie Mellon University, 2000.
[46] I. Haritaoglu, D. Harwood, L.S. Davis, W4: real‐time surveillance of people and their activities, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 809–830.
[47] Y. Kameda, M. Minoh, A human motion estimation method using 3‐successive video frames, in: International Conference on Virtual Systems and Multimedia, Gifu City, Japan, Sep 1996.
[48] P. Viola, M.J. Jones, D. Snow, Detecting pedestrians using patterns of motion and appear‐ance, International Journal of Computer Vision 63 (2) (2005) 153–161.
[49] I. Haritaoglu, M. Flickner, D. Beymer, Ghost3D: detecting body posture and parts using ste‐reo, in: Workshop on Motion and Video Computing, Orlando, Florida, Nov 7, 2002.
[50] K. Hayashi, M. Hashimoto, K. Sumi, K. Sasakawa. Multiple‐person tracker with a fixed slant‐ing stereo camera, in: International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 17–19, 2004.
[51] Y.A. Ivanov, A.F. Bobick, J. Liu, Fast lighting independent background subtraction, Interna‐tional Journal of Computer Vision 37 (2) (2000) 199–207.
[52] S.N. Lim, A. Mittal, L.S. Davis, N. Paragios, Fast illumination‐invariant background subtraction using two views: error analysis, sensor placement and applications, in: Computer Vision and Pat‐tern Recognition, San Diego, CA, June 20–25, 2005.
[53] M.T. Yang, Y.C. Shih, S.C. Wang, People tracking by integrating multiple features, in: Interna‐tional Conference on Pattern Recognition, Cambridge, UK, Aug 23–26, 2004.
[54] S. Iwase, H. Saito, Parallel tracking of all soccer players by integrating detected positions in multiple view images, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[55] A. Mittal, L.S. Davis, M2Tracker: a multi‐view approach to segmenting and tracking people in a cluttered scene using regionbased stereo, in: European Conference on Computer Vision, Co‐penhagen, Denmark, 2002.
[56] A. Mittal, L.S. Davis, M2Tracker: a multi‐view approach to segmenting and tracking people in a cluttered scene, International Journal of Computer Vision 51 (3) (2003) 189–203.
[57] D.B. Yang, H.H.G. Banos, L.J. Guibas, Counting people in crowds with a real‐time network of simple image sensors, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[58] S.M. Khan, M. Shah, A multiview approach to tracking people in crowded scenes using a planar homography constraint, in: European Conference on Computer Vision, Graz, Austria, May 7–13, 2006.
[59] C.R. Wren, A. Azarbayejani, T. Darrell, A.P. Pentland, Pfinder: real‐time tracking of the hu‐man body, Transactions on Pattern Analysis and Machine Intelligence 19 (7) (1997) 780–785.
[60] M. Brand, Shadow puppetry, in: International Conference on Computer Vision, Corfu, Greece, Sep 1999.
[61] Q. Cai, A. Mitiche, J.K. Aggarwal, Tracking human motion in an indoor environment, in: In‐ternational Conference on Image Processing, Washington DC, USA, Oct 23–26, 1995.
[62] I. Haritaoglu, D. Harwood, L.S. Davis, Ghost: a human body part labeling system using sil‐houettes, in: International Conference on Pattern Recognition, Queensland, Australia, Aug 17–20, 1998.
[63] D. Hogg, Model‐based vision: a program to see a walking person, Image and Vision Compu‐ting 1 (1) (1983) 5–20.
[64] S. Wachter, H.‐H. Nagel, Tracking of persons in monocular image sequences, in: Workshop on Motion of Non‐Rigid and Articulated Objects, Puerto Rico, USA, 1997.
[65] C. Bregler, J. Malik, K. Pullen, Twist based acquisition and tracking of animal and human ki‐nematics, International Journal of Computer Vision 56 (3) (2004) 179–194.
[66] G. Loy, M. Eriksson, J. Sullivan, Monocular 3D reconstruction of human motion in long action sequences, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[67] C. Sminchisescu, B. Triggs, Estimating articulated human motion with covariance scaled sampling, International Journal of Robotics Research 22 (6) (2003) 371–391.
[68] M.W. Lee, I. Cohen, Proposal maps driven MCMC for estimating human body pose in static images, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[69] R. Navaratnam, A. Thayananthan, P.H.S. Torr, R. Cipolla, Hierarchical part‐based human body pose estimation, in: British Machine Vision Conference, Oxford, UK, Sep 2005.
[70] T.B. Moeslund, Pose Estimating the Human Arm using Kinematics and the Sequential Monte Carlo Framework, chapter 4 in part IX of Cutting Edge Robotics. Pro literatur Verlag, ISBN:3‐86611‐038‐3, 2005.
[71] A.J. Davison, J. Deutscher, I.D. Reid, Markerless motion capture of complex full‐body move‐ment for character animation, in: Eurographics Workshop on Computer Animation and Simula‐tion, Manchester, UK, Sep 2001.
[72] Q. Delamarre, O. Faugeras, 3D articulated models and multi‐view tracking with physical forces, Computer Vision and Image Understanding, 81 (3) (2001) 328–357.
[73] J. Deutscher, A. Blake, I. Reid, Articulated body motion capture by annealed particle filtering, in: Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, June 13–15, 2000.
[74] R. Kehl, M. Bray, L. VanGool, Full body tracking from multiple views using stochastic sam‐pling, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[75] J. MacCormick, M. Isard, Partitioned sampling, articulated objects, and interface‐quality hand tracking, in: European Conference on Computer Vision, Dublin, Ireland, June 2000.
[76] J. Mitchelson, A. Hilton, Hierarchical tracking of multiple people, in: British Machine Vision Conference, Norwich, UK, Sep 2003.
[77] S. Wachter, H.‐H. Nagel, Tracking persons in monocular image sequences, Computer Vision and Image Understanding 74 (3) (1999) 174–192.
[78] I. Mikic, M. Trivedi, E. Hunter, P. Cosman, Human body model acquisition and tracking using voxel data, International Journal of Computer Vision 53 (3) (2003) 199–223.
[79] G. Hua, M.‐H. Yang, Y. Wu, Learning to estimate human pose with data driven belief propa‐gation, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[80] X. Ren, A.C. Berg, J. Malik, Recovering human body configurations using pairwise constraints between parts, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[81] R. Rosales, S. Sclaroff, Learning and synthesizing human body motion and posture, in: The fourth International Conference on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
[82] G. Shakhnarovich, P. Viola, T. Darrell, Fast pose estimation with parameter‐sensitive hashing, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[83] M. Hu, W. Hu, T. Tan, Tracking people through occlusion, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[84] S. Khan, M. Shah, Tracking people in presence of occlusion, in: Asian Conference on Com‐puter Vision, Taipei, Taiwan, Jan 8–11, 2000.
[85] K. Okuma, A. Taleghani, N.D. Freitas, J.J. Little, David G. Lowe, A boosted particle filter: mul‐titarget detection and tracking, in: European Conference on Computer Vision, Prague, Czech Re‐public, May 11–14, 2004.
[86] S. Park, J.K. Aggarwal, Segmentation and tracking of interacting human body parts under occlusion and shadowing, in: Workshop on Motion and Video Computing, Orlando, Florida, Nov 7, 2002.
[87] D. Roth, P. Doubek, L.V. Gool, Bayesian pixel classification for human tracking, in: IEEE Workshop on Motion and Video Computing (MOTION’05), Breckenridge, Colorado, Jan 2005.
[88] C. Yang, R. Duraiswami, L. Davis, Fast multiple object tracking via a hierarchical particle filter, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[89] S.J. McKenna, S. Jabri, Z. Duric, H. Wechsler, Tracking Interacting People, in: International Conference on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
[90] A.E.C. Pece, From cluster tracking to people counting, in: Workshop on Performance Evalua‐tion of Tracking and Surveillance, Copenhagen, Denmark, June 1, 2002.
[91] K. Okuma, A. Taleghani, N.D. Freitas, J.J. Little, David G. Lowe, A boosted particle filter: mul‐titarget detection and tracking, in: European Conference on Computer Vision, Prague, Czech Re‐public, May 11–14, 2004.
[92] E. Polat, M. Yeasin, R. Sharma, Robust tracking of human body parts for collaborative human computer interaction, Computer Vision and Image Understanding 89 (2003) 44–69.
[93] K. Smith, D.G. Perez, J.M. Odobez, Using particles to track varying numbers of interacting people, in: Computer Vision and Pattern Recognition, San Diego, CA, June 20–25, 2005.
[94] T. Zhao, R. Nevatia, Tracking multiple humans in crowded environments, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[95] N. Atsushi, K. Hirokazu, H. Shinsaku, I. Siji, Tracking multiple people using distributed vision systems, in: International Conference on Robotics and Automation, Washington DC, USA, May 2002.
[96] J. Kang, I. Cohen, G. Medioni, Persistent objects tracking across multiple non‐overlapping cameras, in: IEEE Workshop on Motion and Video Computing (MOTION’05), Breckenridge, Col‐orado, Jan 2005.
[97] S. Khan, O. Javed, Z. Rasheed, M. Shah, Human tracking in multiple cameras, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[98] N. Ukita, T. Matsuyama, Real‐time cooperative multi‐target tracking by communicating ac‐tive vision agents, Computer Vision and Image Understanding 97 (2) (2005) 137–179.
[99] A. Agarwal, B. Triggs, Tracking articulated motion with piecewise learned dynamic models, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[100] A. Agarwal, B. Triggs, Recovering 3D human pose from monocular images, IEEE Transac‐tions on Pattern Analysis and Machine Intelligence 28 (1) (2006) 44–58.
[101] H. Sidenbladh, M.J. Black, D.J. Fleet, Stochastic tracking of 3D human figures using 2D im‐age motion, in: European Conference on Computer Vision, Dublin, Ireland, June 2000.
[102] R. Urtasun, D.J. Fleet, A. Hertzmann, P. Fua, Priors for people tracking from small training sets, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[103] R. Urtasun, P. Fua, 3D human body tracking using deterministic temporal motion models, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[104] K. Mikolajczyk, D. Schmid, A. Zisserman, Human detection based on a probabilistic assem‐bly of robust part detectors, in: European Conference on Computer Vision, Prague, Czech Repub‐lic, May 11– 14, 2004.
[105] M. Shah, Understanding human behavior from motion imagery, Machine Vision and Appli‐cations 14 (4) (2003) 210–214.
[106] Yu Huang, Thomas S. Huang, Model‐based human body tracking, in: Proceedings of the International Conference on Pattern Recognition (ICPR’02), vol. 1, Quebec, Canada, August 2002, pp. 552–555.
[107] Roland Kehl, Luc Van Gool, Markerless tracking of complex human motions from multiple views, Computer Vision and Image Understanding (CVIU) 104 (2–3) (2006) 190–209.
[108] Nicholas R. Howe, Silhouette lookup for automatic pose tracking, in: Proceedings of the Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’04), Los Alamitos, CA, June 2004, p. 15.
[109] D.A. Forsythe, M.M. Fleck, Body plans, in: Computer Vision and Pattern Recognition, Puerto Rico, June 17–19, 1997.
[110] P.F. Felzenszwalb, D.P. Huttenlocher, Efficient matching of pictorial structures, in: Comput‐er Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, June 13–15, 2000.
[111] S. Ioffe, D. Forsyth, Finding people by sampling, in: International Conference on Computer Vision, Korfu, Greece, 1999.
[112] S. Ioffe, D. Forsyth, Human tracking with mixtures of trees, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[113] A. Mohan, C. Papageorgiou, T. Poggio, Example‐based object detection in images by com‐ponents, IEEE Transactions on Pattern Analysis and Machine Intelligence 23 (4) (2001) 349–361.
[114] B. Wu, R. Nevatia, Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detection, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[115] D. Ramanan, C. Sminchisescu, Tranining deformable models for localization, in: Computer Vision and Pattern Recognition, New York City, New York, USA, June 17–22, 2006.
[116] R. Rosales, M. Siddiqui, J. Alon, S. Sclaroff, Estimating 3D Body pose using uncalibrated cameras, in: Computer Vision and Pattern Recognition, Kauai Marriott, Hawaii, Dec 9–14, 2001.
[117] E.‐J. Ong, A. Hilton, A.S. Micilotta, Viewpoint invariant exemplar‐based 3D human tracking, in: First IEEE Workshop on Modeling People and Human Interaction (PHI’05), Beijing, China, Oct 15, 2005.
[118] N.R. Howe, Silhouette lookup for automatic pose tracking, in: Workshop on Articulated and Non‐Rigid Motion, Washington DC, USA, June 2004.
[119] K. Grauman, G. Shakhnarovich, T. Darrell, Inferring 3D structure with a statistical im‐age‐based shape model, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[120] A. Elgammal, C.S. Lee, Inferring 3D body pose from silhouettes using activity manifold learning, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[121] A. Agarwal, B. Triggs, 3D human pose from silhouettes by relevance vector regression, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[122] J. Starck, A. Hilton, Spherical matching for temporal correspondence of non‐rigid surfaces, in: ICCV, Beijing, China, Oct 15–21, 2005.
[123] M. W. Lee, R. Nevatia, Human Pose Tracking in Monocular Sequence Using Multilevel Structured Models, PAMI, VOL. 31, NO. 1, Jan 2009.
[124]王永忠,梁彦,潘泉等人,基于自适应混合高斯模型的时空背景建模。
[125] J. Serra, Image Analysis and Matiematical Morphology, New York:Academic Press, 1983.
[126] J. J. Bardyn et al.,“Une architecture VLSI pour un operateur de filtrage median”, Congres reconnaissance des forms et intelligence aritificielle(vol. 1, pp. 557– 566), Paris, 25‐27 January 1984.
[127] E. H. Adelson, C. H. Anderson, J. R. Bergen, P. J. Burt, and J. M. Ogden,“Pyramid methods in image proceesing”, RCA Engineer 29 (1984): 33‐41.
[128] P. J. Burt , E. H. Adelson,“The Laplacian pyramid as a compact image code”, IEEE Transac‐tions om Communications 31 ,1983, 532‐540.
[129] P. KaewTraKulPong, R. Bowden, An improved adaptive background mixture Model for real‐time tracking with shadow detection, in: European Workshop on Advanced Video Based Surveillance Systems, Kluwer Academic, 2001.
[130] Gary Bradski, Adrian Kaebler,“Learning OpenCV”, 2009.
[2] C. Barron, I.A. Kakadiaris. Estimating anthropometry and pose from a single image, in: Com‐puter Vision and Pattern Recognition, Hilton Head Island, South Carolina, June 13–15, 2000.
[3] C. Barron, I.A. Kakadiaris. On the improvement of anthropometry and pose estimation from a single uncalibrated image, Machine Vision and Applications 14 (4) (2003) 229–236.
[4] V. Parameswaran, R. Chellappa. View independent human body pose estimation from a single perspective image, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[5] C.J. Taylor. Reconstruction of articulated objects from point correspondences in a single im‐age, Computer Vision and Image Understanding 80 (3) (2000) 349–363.
[6] N. Krahnstoever, R. Sharma. Articulated models from video. Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[7] N. Krahnstoever, M. Yeasin, R. Sharma. Automatic acquisition and initialization of articulated models, Machine Vision and Applications 14 (4) (2003) 218–228.
[8] Y. Song, L. Goncalves, P. Perona. Unsupervised learning of human motion, IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (7) (2003) 814–827.
[9] G. Cheung, S. Baker, T. Kanade. Shape‐from‐silhouette for articulated objects and its use for human body kinematics estimation and motion capture, in: Computer Vision and Pattern Recog‐nition, Madison, Wisconsin, USA, June 16–22, 2003.
[10] C. Menier, E. Boyer, B. Raffin, 3D skeleton‐based body pose recovery, in: International Sym‐posium on 3D Data Processing, Visualisation and Transmission, 2006.
[11] G.J. Brostow, I. Essa, D. Steedly, V. Kwatra, Novel skeletal representation for articulated creatures, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[12] C.‐W. Chu, O.C. Jenkins, M.J. Mataric, Markerless kinematic model and motion capture from volume sequences, in: Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, June 16–22, 2003.
[13] T.B. Moeslund, E. Granum, Pose estimation of a human arm using kinematic constraints, in: The 12th Scandinavian Conference on Image Analysis, Bergen, Norway, 2001.
[14] T.B. Moeslund, M. Vittrup, K.S. Pedersen, M.K. Laursen, M.K.D. Soensen, H. Uhrenfeldt, E. Granum, Estimating the 3D shoulder position using monocular vision, in: International Confe‐rence on Imaging Science, Systems, and Technology, Las Vegas, Nevada, June 24–27, 2002.
[15] J. Mulligan, Upper body pose estimation from stereo and hand‐face tracking, in: Canadian Conference on Computer and Robot Vision, Victoria, British Columbia, Canada, May 9–11, 2005.
[16] L. Herda, R. Urtasun, P. Fua, Hierarchical implicit surface joint limits to constrain video‐based motion capture, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[17] L. Herda, R. Urtasun, P. Fua, Hierarchical implicit surface joint limits for human body tracking, Computer Vision and Image Understanding 99 (2) (2005) 189–209.
[18] T.B. Moeslund, C.B. Madsen, E. Granum, Modelling the 3D pose of a human arm and the shoulder complex utilising only two parameters, International Journal on Integrated Comput‐er‐Aided Engineering 12 (2) (2005) 159–177.
[19] http://www.charactermotion.com/products/powermoves/megamocap/.
[20] http://mocap.cs.cmu.edu/.
[21] http://www.ict.usc.edu/graphics/animWeb.
[22] A. Hilton, D. Beresford, T. Gentils, R. Smith, W. Sun, Virtual people: capturing human models to populate virtual worlds, in: International Conference on Computer Animation, May 1999.
[23] J. Carranza, C. Theobalt, M. Magnor, H.‐.P. Seidel, Free‐viewpoint video of human actors, in: ACM SIGGRAPH, 2003, pp. 565—577.
[24] R. Plankers, P. Fua, Articulated soft objects for multi‐view shape and motion capture, IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (9) (2003) 1182–1187.
[25] J. Starck, A. Hilton, Model‐based multiple view reconstruction of people, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[26] B. Allen, B. Curless, Z. Popovic, Articulated body deformation from range scan data, in: ACM SIGGRAPH, 2002, pp. 612—619.
[27] J. Starck, G. Collins, R. Smith, A. Hilton, J. Illingworth, Animated statues, Journal of Machine Vision and Applications 14 (4) (2003) 248–259.
[28] B. Allen, B. Curless, Z. Popovic, The space of human body shapes: reconstruction and para‐meterization from range images, in: ACM SIGGRAPH, 2003, pp. 587—594.
[29] M.N. Thalmann, H. Seo, Data‐driven approaches to digital human modeling, in: International Symposium on 3D Data Processing, Visualization, and Transmission, Thessalonica, Greece, Sep 2004.
[30] H. Sidenbladh, M.J. Black, Learning image statistics for Bayesian tracking, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[31] H. Sidenbladh, M.J. Black, Learning the statistics of people in images and video, International Journal of Computer Vision 54 (1/2/ 3) (2003) 183–209.
[32] T.J. Roberts, S.J. McKenna, I.W. Ricketts, Adaptive learning of statistical appearance models for 3D human tracking, in: British Machine Vision Conference, Cardiff, UK, 2002.
[33] A. Micilotta, E. Ong, R. Bowden, Detection and tracking of humans by probabilistic body part assembly, in: British Machine Vision Conference, Oxford, UK, Sep 2005.
[34] D. Ramanan, D.A. Forsyth, A. Zisserman, Strike a pose: tracking people by finding stylized poses, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[35] T.J. Roberts, S.J. McKenna, I.W. Ricketts, Human pose estimation using learnt probabilistic region similarities and partial configurations, in: European Conference on Computer Vision, Pra‐gue, Czech Republic, May 11–14, 2004.
[36] R. Ronfard, C. Schmid, B. Triggs, Learning to parse pictures of people, in: European Confe‐rence on Computer Vision, Copenhagen, Denmark, June 27–31, 2002.
[37] P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features, in: Computer Vision and Pattern Recognition, Kauai Marriott, Hawaii, Dec 9–14, 2001.
[38] H. Lim, V.I. Morariu, O.I. Camps, M. Sznaier, Dynamic appearance modeling for human tracking, in: Computer Vision and Pattern Recognition, New York City, New York, USA, June 17–22, 2006.
[39] C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real‐time tracking, in: Computer Vision and Pattern Recognition, Santa Barbara, CA, June 1998.
[40] H. Sidenbladh, Detecting human motion with support vector machines, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[41] J.J. Gonzalez, I.S. Lim, P. Fua, D. Thalmann, Robust tracking and segmentation of human mo‐tion in an image sequence, in: International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, April 2003.
[42] P. Sangi, J. Heikkila, O. Silven, Extracting motion components from image sequences using particle filters, in: The 12th Scandinavian Conference on Image Analysis, Bergen, Norway, 2001.
[43] G.R. Bradski, J.W. Davis, Motion segmentation and pose recognition with motion history gradients, Machine Vision and Applications 13 (3) (2002) 174–184.
[44] J.W. Davis, A. Bobick, The representation and recognition of action using temporal templates, in: Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, June 1997.
[45] Collins,Lipton,Kanade,Fujiyoshi,Duggins,Tsin, Tolliver,Enomoto, Hasegawa, A system for video surveillance and monitoring: VSAM final report, Technical report CMU‐RI‐TR‐00‐12, Robot‐ics Institute, Carnegie Mellon University, 2000.
[46] I. Haritaoglu, D. Harwood, L.S. Davis, W4: real‐time surveillance of people and their activities, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 809–830.
[47] Y. Kameda, M. Minoh, A human motion estimation method using 3‐successive video frames, in: International Conference on Virtual Systems and Multimedia, Gifu City, Japan, Sep 1996.
[48] P. Viola, M.J. Jones, D. Snow, Detecting pedestrians using patterns of motion and appear‐ance, International Journal of Computer Vision 63 (2) (2005) 153–161.
[49] I. Haritaoglu, M. Flickner, D. Beymer, Ghost3D: detecting body posture and parts using ste‐reo, in: Workshop on Motion and Video Computing, Orlando, Florida, Nov 7, 2002.
[50] K. Hayashi, M. Hashimoto, K. Sumi, K. Sasakawa. Multiple‐person tracker with a fixed slant‐ing stereo camera, in: International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 17–19, 2004.
[51] Y.A. Ivanov, A.F. Bobick, J. Liu, Fast lighting independent background subtraction, Interna‐tional Journal of Computer Vision 37 (2) (2000) 199–207.
[52] S.N. Lim, A. Mittal, L.S. Davis, N. Paragios, Fast illumination‐invariant background subtraction using two views: error analysis, sensor placement and applications, in: Computer Vision and Pat‐tern Recognition, San Diego, CA, June 20–25, 2005.
[53] M.T. Yang, Y.C. Shih, S.C. Wang, People tracking by integrating multiple features, in: Interna‐tional Conference on Pattern Recognition, Cambridge, UK, Aug 23–26, 2004.
[54] S. Iwase, H. Saito, Parallel tracking of all soccer players by integrating detected positions in multiple view images, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[55] A. Mittal, L.S. Davis, M2Tracker: a multi‐view approach to segmenting and tracking people in a cluttered scene using regionbased stereo, in: European Conference on Computer Vision, Co‐penhagen, Denmark, 2002.
[56] A. Mittal, L.S. Davis, M2Tracker: a multi‐view approach to segmenting and tracking people in a cluttered scene, International Journal of Computer Vision 51 (3) (2003) 189–203.
[57] D.B. Yang, H.H.G. Banos, L.J. Guibas, Counting people in crowds with a real‐time network of simple image sensors, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[58] S.M. Khan, M. Shah, A multiview approach to tracking people in crowded scenes using a planar homography constraint, in: European Conference on Computer Vision, Graz, Austria, May 7–13, 2006.
[59] C.R. Wren, A. Azarbayejani, T. Darrell, A.P. Pentland, Pfinder: real‐time tracking of the hu‐man body, Transactions on Pattern Analysis and Machine Intelligence 19 (7) (1997) 780–785.
[60] M. Brand, Shadow puppetry, in: International Conference on Computer Vision, Corfu, Greece, Sep 1999.
[61] Q. Cai, A. Mitiche, J.K. Aggarwal, Tracking human motion in an indoor environment, in: In‐ternational Conference on Image Processing, Washington DC, USA, Oct 23–26, 1995.
[62] I. Haritaoglu, D. Harwood, L.S. Davis, Ghost: a human body part labeling system using sil‐houettes, in: International Conference on Pattern Recognition, Queensland, Australia, Aug 17–20, 1998.
[63] D. Hogg, Model‐based vision: a program to see a walking person, Image and Vision Compu‐ting 1 (1) (1983) 5–20.
[64] S. Wachter, H.‐H. Nagel, Tracking of persons in monocular image sequences, in: Workshop on Motion of Non‐Rigid and Articulated Objects, Puerto Rico, USA, 1997.
[65] C. Bregler, J. Malik, K. Pullen, Twist based acquisition and tracking of animal and human ki‐nematics, International Journal of Computer Vision 56 (3) (2004) 179–194.
[66] G. Loy, M. Eriksson, J. Sullivan, Monocular 3D reconstruction of human motion in long action sequences, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[67] C. Sminchisescu, B. Triggs, Estimating articulated human motion with covariance scaled sampling, International Journal of Robotics Research 22 (6) (2003) 371–391.
[68] M.W. Lee, I. Cohen, Proposal maps driven MCMC for estimating human body pose in static images, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[69] R. Navaratnam, A. Thayananthan, P.H.S. Torr, R. Cipolla, Hierarchical part‐based human body pose estimation, in: British Machine Vision Conference, Oxford, UK, Sep 2005.
[70] T.B. Moeslund, Pose Estimating the Human Arm using Kinematics and the Sequential Monte Carlo Framework, chapter 4 in part IX of Cutting Edge Robotics. Pro literatur Verlag, ISBN:3‐86611‐038‐3, 2005.
[71] A.J. Davison, J. Deutscher, I.D. Reid, Markerless motion capture of complex full‐body move‐ment for character animation, in: Eurographics Workshop on Computer Animation and Simula‐tion, Manchester, UK, Sep 2001.
[72] Q. Delamarre, O. Faugeras, 3D articulated models and multi‐view tracking with physical forces, Computer Vision and Image Understanding, 81 (3) (2001) 328–357.
[73] J. Deutscher, A. Blake, I. Reid, Articulated body motion capture by annealed particle filtering, in: Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, June 13–15, 2000.
[74] R. Kehl, M. Bray, L. VanGool, Full body tracking from multiple views using stochastic sam‐pling, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[75] J. MacCormick, M. Isard, Partitioned sampling, articulated objects, and interface‐quality hand tracking, in: European Conference on Computer Vision, Dublin, Ireland, June 2000.
[76] J. Mitchelson, A. Hilton, Hierarchical tracking of multiple people, in: British Machine Vision Conference, Norwich, UK, Sep 2003.
[77] S. Wachter, H.‐H. Nagel, Tracking persons in monocular image sequences, Computer Vision and Image Understanding 74 (3) (1999) 174–192.
[78] I. Mikic, M. Trivedi, E. Hunter, P. Cosman, Human body model acquisition and tracking using voxel data, International Journal of Computer Vision 53 (3) (2003) 199–223.
[79] G. Hua, M.‐H. Yang, Y. Wu, Learning to estimate human pose with data driven belief propa‐gation, in: Computer Vision and Pattern Recognition, San Diego, California, USA, June 20–25, 2005.
[80] X. Ren, A.C. Berg, J. Malik, Recovering human body configurations using pairwise constraints between parts, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[81] R. Rosales, S. Sclaroff, Learning and synthesizing human body motion and posture, in: The fourth International Conference on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
[82] G. Shakhnarovich, P. Viola, T. Darrell, Fast pose estimation with parameter‐sensitive hashing, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[83] M. Hu, W. Hu, T. Tan, Tracking people through occlusion, in: International Conference on Pattern Recognition, Cambridge, UK, Aug 2004.
[84] S. Khan, M. Shah, Tracking people in presence of occlusion, in: Asian Conference on Com‐puter Vision, Taipei, Taiwan, Jan 8–11, 2000.
[85] K. Okuma, A. Taleghani, N.D. Freitas, J.J. Little, David G. Lowe, A boosted particle filter: mul‐titarget detection and tracking, in: European Conference on Computer Vision, Prague, Czech Re‐public, May 11–14, 2004.
[86] S. Park, J.K. Aggarwal, Segmentation and tracking of interacting human body parts under occlusion and shadowing, in: Workshop on Motion and Video Computing, Orlando, Florida, Nov 7, 2002.
[87] D. Roth, P. Doubek, L.V. Gool, Bayesian pixel classification for human tracking, in: IEEE Workshop on Motion and Video Computing (MOTION’05), Breckenridge, Colorado, Jan 2005.
[88] C. Yang, R. Duraiswami, L. Davis, Fast multiple object tracking via a hierarchical particle filter, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[89] S.J. McKenna, S. Jabri, Z. Duric, H. Wechsler, Tracking Interacting People, in: International Conference on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
[90] A.E.C. Pece, From cluster tracking to people counting, in: Workshop on Performance Evalua‐tion of Tracking and Surveillance, Copenhagen, Denmark, June 1, 2002.
[91] K. Okuma, A. Taleghani, N.D. Freitas, J.J. Little, David G. Lowe, A boosted particle filter: mul‐titarget detection and tracking, in: European Conference on Computer Vision, Prague, Czech Re‐public, May 11–14, 2004.
[92] E. Polat, M. Yeasin, R. Sharma, Robust tracking of human body parts for collaborative human computer interaction, Computer Vision and Image Understanding 89 (2003) 44–69.
[93] K. Smith, D.G. Perez, J.M. Odobez, Using particles to track varying numbers of interacting people, in: Computer Vision and Pattern Recognition, San Diego, CA, June 20–25, 2005.
[94] T. Zhao, R. Nevatia, Tracking multiple humans in crowded environments, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[95] N. Atsushi, K. Hirokazu, H. Shinsaku, I. Siji, Tracking multiple people using distributed vision systems, in: International Conference on Robotics and Automation, Washington DC, USA, May 2002.
[96] J. Kang, I. Cohen, G. Medioni, Persistent objects tracking across multiple non‐overlapping cameras, in: IEEE Workshop on Motion and Video Computing (MOTION’05), Breckenridge, Col‐orado, Jan 2005.
[97] S. Khan, O. Javed, Z. Rasheed, M. Shah, Human tracking in multiple cameras, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[98] N. Ukita, T. Matsuyama, Real‐time cooperative multi‐target tracking by communicating ac‐tive vision agents, Computer Vision and Image Understanding 97 (2) (2005) 137–179.
[99] A. Agarwal, B. Triggs, Tracking articulated motion with piecewise learned dynamic models, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[100] A. Agarwal, B. Triggs, Recovering 3D human pose from monocular images, IEEE Transac‐tions on Pattern Analysis and Machine Intelligence 28 (1) (2006) 44–58.
[101] H. Sidenbladh, M.J. Black, D.J. Fleet, Stochastic tracking of 3D human figures using 2D im‐age motion, in: European Conference on Computer Vision, Dublin, Ireland, June 2000.
[102] R. Urtasun, D.J. Fleet, A. Hertzmann, P. Fua, Priors for people tracking from small training sets, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[103] R. Urtasun, P. Fua, 3D human body tracking using deterministic temporal motion models, in: European Conference on Computer Vision, Prague, Czech Republic, May 11–14, 2004.
[104] K. Mikolajczyk, D. Schmid, A. Zisserman, Human detection based on a probabilistic assem‐bly of robust part detectors, in: European Conference on Computer Vision, Prague, Czech Repub‐lic, May 11– 14, 2004.
[105] M. Shah, Understanding human behavior from motion imagery, Machine Vision and Appli‐cations 14 (4) (2003) 210–214.
[106] Yu Huang, Thomas S. Huang, Model‐based human body tracking, in: Proceedings of the International Conference on Pattern Recognition (ICPR’02), vol. 1, Quebec, Canada, August 2002, pp. 552–555.
[107] Roland Kehl, Luc Van Gool, Markerless tracking of complex human motions from multiple views, Computer Vision and Image Understanding (CVIU) 104 (2–3) (2006) 190–209.
[108] Nicholas R. Howe, Silhouette lookup for automatic pose tracking, in: Proceedings of the Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’04), Los Alamitos, CA, June 2004, p. 15.
[109] D.A. Forsythe, M.M. Fleck, Body plans, in: Computer Vision and Pattern Recognition, Puerto Rico, June 17–19, 1997.
[110] P.F. Felzenszwalb, D.P. Huttenlocher, Efficient matching of pictorial structures, in: Comput‐er Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, June 13–15, 2000.
[111] S. Ioffe, D. Forsyth, Finding people by sampling, in: International Conference on Computer Vision, Korfu, Greece, 1999.
[112] S. Ioffe, D. Forsyth, Human tracking with mixtures of trees, in: International Conference on Computer Vision, Vancouver, Canada, July 9–12, 2001.
[113] A. Mohan, C. Papageorgiou, T. Poggio, Example‐based object detection in images by com‐ponents, IEEE Transactions on Pattern Analysis and Machine Intelligence 23 (4) (2001) 349–361.
[114] B. Wu, R. Nevatia, Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detection, in: International Conference on Computer Vision, Beijing, China, Oct 15–21, 2005.
[115] D. Ramanan, C. Sminchisescu, Tranining deformable models for localization, in: Computer Vision and Pattern Recognition, New York City, New York, USA, June 17–22, 2006.
[116] R. Rosales, M. Siddiqui, J. Alon, S. Sclaroff, Estimating 3D Body pose using uncalibrated cameras, in: Computer Vision and Pattern Recognition, Kauai Marriott, Hawaii, Dec 9–14, 2001.
[117] E.‐J. Ong, A. Hilton, A.S. Micilotta, Viewpoint invariant exemplar‐based 3D human tracking, in: First IEEE Workshop on Modeling People and Human Interaction (PHI’05), Beijing, China, Oct 15, 2005.
[118] N.R. Howe, Silhouette lookup for automatic pose tracking, in: Workshop on Articulated and Non‐Rigid Motion, Washington DC, USA, June 2004.
[119] K. Grauman, G. Shakhnarovich, T. Darrell, Inferring 3D structure with a statistical im‐age‐based shape model, in: International Conference on Computer Vision, Nice, France, Oct 13–16, 2003.
[120] A. Elgammal, C.S. Lee, Inferring 3D body pose from silhouettes using activity manifold learning, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[121] A. Agarwal, B. Triggs, 3D human pose from silhouettes by relevance vector regression, in: Computer Vision and Pattern Recognition, Washington DC, USA, June 2004.
[122] J. Starck, A. Hilton, Spherical matching for temporal correspondence of non‐rigid surfaces, in: ICCV, Beijing, China, Oct 15–21, 2005.
[123] M. W. Lee, R. Nevatia, Human Pose Tracking in Monocular Sequence Using Multilevel Structured Models, PAMI, VOL. 31, NO. 1, Jan 2009.
[124]王永忠,梁彦,潘泉等人,基于自适应混合高斯模型的时空背景建模。
[125] J. Serra, Image Analysis and Matiematical Morphology, New York:Academic Press, 1983.
[126] J. J. Bardyn et al.,“Une architecture VLSI pour un operateur de filtrage median”, Congres reconnaissance des forms et intelligence aritificielle(vol. 1, pp. 557– 566), Paris, 25‐27 January 1984.
[127] E. H. Adelson, C. H. Anderson, J. R. Bergen, P. J. Burt, and J. M. Ogden,“Pyramid methods in image proceesing”, RCA Engineer 29 (1984): 33‐41.
[128] P. J. Burt , E. H. Adelson,“The Laplacian pyramid as a compact image code”, IEEE Transac‐tions om Communications 31 ,1983, 532‐540.
[129] P. KaewTraKulPong, R. Bowden, An improved adaptive background mixture Model for real‐time tracking with shadow detection, in: European Workshop on Advanced Video Based Surveillance Systems, Kluwer Academic, 2001.
[130] Gary Bradski, Adrian Kaebler,“Learning OpenCV”, 2009.