摘要
本文的主要研究内容是从多个同步的视频序列中自动恢复人体的三维运动姿态。这种无标记的人体运动捕捉跟踪技术可广泛应用于体育运动分析、医学诊断、虚拟现实、计算机动画、视频监控、人机交互等领域。由于存在非刚体人体描述、人体模型的三维到二维投影多义性、人体模型的自遮挡、高维状态空间搜索、复杂条件下的图像特征提取与匹配等方面的困难,从视频图像中恢复出人体三维运动姿态存在大量的不确定性。因此三维人体运动跟踪是计算机视觉领域一项非常有挑战性的任务。
本文提出了有模型指导的三维人体运动跟踪框架,将一个多关节的圆台形状三维人体模型与多个视频图像中的外轮廓、边界、灰度和肤色特征进行匹配,使人体运动跟踪变成一个状态估计问题。并且,使用基于概率模型的粒子滤波算法来完成非线性、非高斯动态系统的状态估计。
粒子滤波算法虽然能在混乱背景及遮挡情况下很好地完成一般跟踪任务,但是对于人体运动估计仍然存在困难。因此本文提出了两种新的粒子滤波改进策略。一种是将状态空间分解和PERM(Pruned-Enriched Rosenbluth Method)采样与退火粒子滤波结合,提高了对多模式后验分布的模拟精度。另一种是确定性搜索方法与随机采样方法相结合的改进粒子滤波算法,用于跟踪复杂背景下的三维人体运动。这种新的粒子滤波算法的最大特点就是通过局部优化方法来指导重要性分布函数的生成,使得对高维空间中多峰后验分布函数的估计成为可能。
此外,在图像特征提取方面,本文提出了一种非参数的背景估计模型,用于检测视频图像中的运动人体的外轮廓。这种方法综合考虑了图像上的时间与空间信息,利用颜色和边界特征增强前景检测的可靠性;而且,通过自适应的阴影消除,进一步提高了运动目标检测的准确性。
本文算法在模拟和真实数据上进行了试验,能够完成复杂背景条件下的人体运动跟踪任务。
This thesis focuses on the automatic recovery of three-dimensional human motion from multiple synchronized video sequences. The potential applications of this kind of markerless motion capture technique are motion analysis, medical diagnosis, virtual reality, computer animation, video surveillance, human-computer interface and so on. 3D human motion tracking faces difficulties caused by non-rigid human model representation, 2D-3D projection, self occlusion, high dimensionality of state space and image features extraction under clutter. It is a challenging task in the field of computer vision.
This thesis proposes a model based 3D human motion tracking framework, where the articulated human model represented by truncated cones is matched with several image features, such as silhouette, edge, intensity and skin color. And human motion tracking is the problem of state estimation, which can be accomplished by the particle filter algorithm based on probabilistic model.
The particle filter algorithm, having the advantage of tracking under clutter and self occlusion, still suffers the pain of high computing complexity during 3D human motion estimation. This thesis proposes two improvements of standard particle filter. Firstly, for the purpose of improving the accuracy of posterior distribution, state space decomposition and PERM (Pruned-Enriched Rosenbluth Method) sampling are adopted during the annealed particle filter. Secondly, a new particle filter based sampling framework, which combines the local optimization and stochastic sampling, is proposed. The most important feature of this sampling method is that the optimization result is used to guide the importance function, which suits for estimation of multi-modal distribution in high dimensionality.
Further more, this thesis proposes a novel method based on a non-parametric background model to detect the silhouette of human body in video sequences. This background subtraction method utilizes intensity and edge features synchronously to improve robustness of the foreground detection. And an adaptive shadow detection model is used to find the accurate moving objects.
The algorithm is tested on simulative and real video sequences, which include human motion with self-occlusion, and can accomplish the 3D human motion tracking tasks.
引文
[Agarwal and Triggs’ 2004] A.Agarwal and B.Triggs. 3D Human pose from silhouettes by relevance vector regression. In Proc. of International Conference on Computer Vision and Pattern Recognition, Washington, pp.882-888, 2004.
[Aggarwal and Cai’ 1999] J.Aggarwal and Q.Cai. Human motion analysis: a review. Computer Vision and Image Understanding. Vol.73(3), pp.428-440, 1999.
[Arulampalam et al‘ 2002] S.Arulampalam, S.Maskell, N.Gordon and T.Clapp, A tutorial on particle filters for on-line nonlinear/non-gaussian bayesian tracking, IEEE Transactions on Signal Processing, Special Issue on Monte Carlo Methods; Vol.50(2), pp.174-188, 2002
[Ascensio’ 2005] Magnetic motion capture equipment http://www.ascension-tech.com
[Bharatkumar’ 1994] A.G.Bharatkumar, K.E.Daigle, M.G.Pandy, Q.Cai, and J.K.Aggarwal. Lower limb kinetics of human walking with the medial axis transfomatoin. In Workshop on Motin of Non-Rigid and Articulated Objects, Austin, Texas, USA, pp.70-76, 1994.
[Brand and Mason’ 2000] J.Brand and J.Mason. A comparative assessment of three approaches to pixellevel human skin-detection. In Proc. of the International Conference on Pattern Recognition, pp.1056-1059, 2000
[Brand’ 1999] M.Brand. Shadow puppetry. In Proc. of International Conference on Computer Vision. Corfu, Greece, pp.1237-1244, 1999
[Bray et al’ 2004] M.Bray, E.Koller-Meier, N.N.Schraudolph and L.V.Gool. Stochastic meta-descent for tracking articulated structures. In IEEE Workshop on Articulated and Nonrigid Motion, Washington, USA, pp.7-15, 2004
[Bregler and Mailik’ 1998] C.Bregler and J.Malik. Tracking people with twists and exponential maps. In Proc. of International Conference on Computer Vision and Pattern Recognition, pp.8-15, 1998.
[Bregler et al’ 2004] C.Bregler, J.Malik and K.Pullen. Twist based acquisition and tracking of animal and human kinematics. International Journal of Computer Vision. Vol.56(3), pp.179-194, 2004
[Carranza et al’ 2003] J.Carranza, C.Theobalt, M.A.Magnor and H.P.Seidel. Free-viewpoint video of human actors. ACM Trans. on Graphics. Special issue: Proceedings of ACM SIGGRAPH San Diego USA, pp.569-577, 2003
[Castleman’ 2002] K.R.Castleman 数字图像处理 电子工业出版社 2002
[Cavallaro and Ebrahimi’ 2001] A.Cavallaro, T.Ebrahimi. Video object extraction based on adaptive background and statistical change detection. In Proc. of SPIE Visual Communications and Image Processing, San Jose, CA, USA, pp.465-475, 2001
[Cavin et al’ 2003] R.D.Cavin, A.V.Nefian and N.Goel. A bayesian formulation for 3D articulated upper body segmentation and tracking from dense disparity maps. In Proc. Of International Conference of Image Processing, Barcelona, Spain, pp.97-100, 2003
[Cham and Rehg’ 1999] T.Cham and J.Rehg. A multiple hypothesis approach to figure tracking. In Proc. of International Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA, Vol.2, pp.239-245, 1999.
[Chen and Li’ 1995] R.Chen, T.Li. Blind restoration of linearly degraded discrete singals by Gibbs sampler. IEEE Trans. on Signal Proecessing, Vol.43, pp.2410-2413, 1995
[Chen et al’ 2002a] Y.Chen, Y.Rui and T.Huang. Parametric contour tracking using unscented kalman filter. In Proc. of IEEE ICIP, Rochester NY, USA, pp.613-616, 2002
[Chen et al’ 2002b] Y.Chen, T.Huang and Y.Rui. Mode-based multi-hypothesis head tracking using parametric contours. In Proc. of IEEE Automatic face and gesture recognition, Washington DC, USA, pp.119-124, 2002,
[Cheung et al’ 2003a] K.M.Cheung, S.Baker and T.Kanade. Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion captur. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin USA, pp.77-85, 2003
[Cheung et al’ 2003b] K.M.Cheung, S.Baker and T.Kanade. Visual hull alignment and refinement across time: a 3d reconstruction algorithm combining shape-from-silhouette with stereo. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin USA, pp.375-383, 2003
[Choo and Fleet’ 2001] K.Choo and D.J.Fleet. People tracking with hybrid Monte Carlo. In Proc. of IEEE International Conference on Computer Vision, Vancouver, Paris, France, Vol.2, pp.321-328, 2001
[Christof et al’ 1995] R.Christof, M.Olaf and K.Harald. Adaptive background estimation and foreground detection using kalman-filtering. In Proc. of International Conference on recent Advances in Mechatronics, UNESCO Chair on Mechatronics, Istanbul, Turkey, pp.193-199, 1995.
[Cohen and Lee’ 2002] I.Cohen and M.W.Lee. 3D Body Reconstruction for Immersive Interaction. In Second international Workshop on Articulated Motion and Deformable Objects Palma. de Mallorca, Spain, pp.21-23,2002.
[Collins and Liu’ 2003] R.T.Collins, Y.Liu. On-line selection of discriminative tracking features. In Proc. of International Conference on Computer Vision, Paris, France, pp.346-352, 2003
[Comaniciu et al’ 2000] D.Comaniciu, V.Ramesh, P.Meer. Real-time tracking of non-rigid objects using mean shift. In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA., Vol.2, pp.142-149, 2000
[Comaniciu et al’ 2003] D.Comaniciu, V.Ramesh, P.Meer. Kernel-based object tracking. In IEEE Trans. on Pattern Analysis Machine Intell., Vol.25(5), pp.564-577, 2003.
[Curio and Giese’ 2005] C.Curio, M.A.Giese. Combining view-based and model-based tracking of articulated human. In IEEE Computer Society Workshop on Motion and Vision Computing, Beckenridge, Colorado, USA, pp.261-268, 2005
[Curiouslabs’ 2005] http://www.curiouslabs.com
[Darrell et al’ 1994] T.Darrell, P.Maes, B.Blumberg and A.Pentland. A Novel Environment for Situated Vison and Behavior. In Workshop for Visual Behaviors at CVPR, Seattle, Washington, USA, pp.68-72, 1994.
[Delamarre and Faugeras’ 1999] Q.Delamarre and O.Faugeras. 3D articulated models and multi-view tracking with silhouettes. In Proc. of IEEE International Conference on Computer Vision, Corfu, Greece, pp.716-721, 1999.
[Demirdjian and Darrell’ 2002] D.Demirdjian and T.Darrell. 3D articulated pose tracking for untethered diectic reference. In Proc. of ICMI’ 02, Pittsburgh, Pennsylvania, USA, pp.267-272, 2002,
[Demirdjian’ 2003] D.Demirdjian. Enforcing Constraints for human body tracking. In WOMOT’ 03 (Worshop on Multi-Object Tracking), Madison, Wisconsin, USA, pp.102-103, 2003
[Denzler et al’ 2002] J. Denzler, M. Zobel and J. Triesch. Probabilistic integration of cues from multiple cameras. In Workshop Dynamic Perception, Bochum, Germany, pp.309-314, 2002
[Deutscher et al’ 2000] J.Deutscher, A.Blake, I.Reid. Articulated body motion capture by annealed particle filtering. In Proc. of International Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA., Vol.2, pp.126-133, 2000
[Deutscher et al’ 2001] J.Deutscher, A.Davidson, I.Reid. Articulated partitioning of high dimensional search spaces associated with articulated body motion capture. In Proc. of International Conference on Computer Vision and Pattern Recognition. Hawaii, USA., pp.669-676, 2001
[Dornaika et al’ 2004] F. Dornaika, F. Davoine, and M. Dang. 3D head tracking by particle filters. In 5th International Workshop on Image Analysis for Multimedia Interactive Services, Lisboa, Portugal, pp.113-118, 2004
[Doucet et al’ 2000] A.Doucet, S.Godsill, C.Andrien. On sequential monte carlo sampling methods for bayesian filtering. In Statistics and Computing, Vol.10(3), pp.197-208, 2000
[Drummond and Cipolla’ 2001] T.Drummond and R.Cipolla. Real-time tracking of highly articulated structures in the presence of noisy measurements. In Proc. of International Conference on Computer Vision, Vancouver, Canada, pp.315-320, 2001.
[Elgammal and Lee’ 2004] A.Elgammal, C.S. Lee. Inferring 3D body pose from silhouettes using activity manifold learning. In Proc. of International Conference on Computer Vision and Pattern Recognition Washington, DC, USA, pp.681-688, 2004
[Elgammal et al’ 2000] A.Elgammal, D.Harwood, L.Davis. Non-parametric model for background subtraction. In Proc. of 6th European Conference on Computer Vision. Dublin, Ireland, pp.751-767, 2000.
[Finlayson et al’ 2002] G.Finlayson, S.Hordley, M.Drew. Removing shadows from images. In Proc. of European Conference on Computer Vision, Copenhagen, Denmark, pp.823-836, 2002
[Foley et al’ 1993] J.D.Foley, A.van Dam, S.K.Feiner, J.F.Hughes and R.L.Phillips. Introduction to Computer Graphics, Addison-Wesley Publishing Company, Reading, MA, USA., 1993
[Forsyth and Ponce’ 2002] D.Forsyth and J.Ponce. Computer vision: a modern approach. Pearson Education Publisher, 2002
[Fox’ 2002] D.Fox. KLD-sampling: Adaptive particle filters. In Advances in Neural Information Processing Systems, pp.713-720, 2002.
[Freeman et al’ 1996] W.T.Freeman, K.Tanaka, J.Ohta and K.Kyuma. Computer vision for computer games, In Proc. of IEEE International Conference on Automatic Face and Gesture Recognition, Killington, Vermont, USA, pp.100-105, 1996
[Gao and Collins’ 2004] J.Gao, R.Collins, A.Hauptmann and H.Wactler. Articulated motion modeling for activity analysis. In IEEE Workshop on Articulated and NonRigid Motion, held in conjunction with CVPR'04, Washington, DC, USA, pp.20-21, 2004.
[Gavrila and Davis’ 1996] D.Gavrila, L.Davis. 3-D model based tracking of humans in action: a multiview approach. In Proc. of International Conference on Computer Vision and Pattern Recognition. San Francisco, USA, pp.73-80, 1996.
[Gavrila’ 1999] D.Gavrila. The visual analysis of human movement: a survey. In Computer Vision and Image Understanding, Vol.73(1), pp.82-98, 1999.
[Giebel et al’ 2004] J.Giebel, D.M.Gavrila and C.Schnarr. A bayesian framework for multi-cue 3d object tracking. In Proc. of the European Conference on Computer Vision, Prague, Czech Republic, pp.241-252, 2004
[Gloyer et al’ 1995] B.Gloyer, H.K.Aghajan, K.Y.Siu, et al. Video-based freeway monitoring system using recursive vehicle tracking. In Proc. of SPIE Symposium on Electronic Imaging: Image and Video Processing, San Jose, CA, USA, pp.173-178, 1995
[Gonzalez et al’ 2003] J.J.Gonzalez, I.S.Lim, P.Fua, D.Thalmann. Robust tracking and segmentation of human motion in an image sequence. In Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, pp.29-32, 2003
[Gordon et al’ 1993] N.Gordon, D.Salmon, A.Smith. A novel approach to nonlinear/non garussian bayesian state estimatino. In IEE Proceedings on Radar and Signal Processing, pp.107-113, 1993
[Grassberger et al’ 1998] P.Grassberger and H.Frauenkron and W.Nadler. PERM: a monte carlo strategy for simulating polymers and other things. In Monte Carlo Approach to Biopolymers and Protein Folding, eds. P. Grassberger et al. World Scientific, Singapore, pp.21-27, 1998
[Grassberger’ 1997] P.Grassberger. The pruned-enriched rosenbluth method: simulations of theta polymers of chain length up to 1,000,000. In Physical Review E, Vol.56, pp.3682-3693, 1997
[Grauman et al’ 2004] K.Grauman, G.Shakhnarovich, T.Darrell. Virtual visual hulls: example-based 3d shape estimation from a single silhouette. Technical Report at MIT, 2004
[Gypsy’ 2005] Mechanic motion capture equipment http://www.metamotion.com
[Halvorsen’ 1999] A.K. Halvorsen. Model-based methods for tracking and analysis of human movement. Licentiate thesis, Uppsala University, Uppsala, Sweden.1999
[Haritaoglu et al’ 1998] I.Haritaoglu, D.Harwood, L.Davis. W4: who, when, where, what: a real time system for detecting and tracking people. In Proc. of IEEE International Conference on Face and Gesture Recognition. Nara, Japan, pp.222-227, 1998
[Hogg’ 1983] D.C.Hogg. Model-based vision: a program to see a walking person. In Image and Vision Computing, Vol.1(1), pp.5-20, 1983
[Horprasert et al’ 1999] T.Horprasert, D.Harwood, L.Davis. A statistical approach for real-time robust background subtraction and shadow detection. http://www.cse.lehigh.edu/FRAME/Horprasert/
[Hue et al’ 2002] C.Hue, J.Le Cadre and P.Pérez. Sequential Monte Carlo methods for multiple target tracking and data fusion. In IEEE Trans. Signal Processing, Vol.50(2), pp.309-325, 2002
[Humanoid’ 2005] Human Model. http://www.h-anim.org
[Huttenlocher et al’ 1993] D.Huttenlocher, D.Klanderman and A.Rucklige. Comparing images using the Hausdorff distance. In IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.15(9), pp.850-863, 1993
[Ioffe and Forsyth’ 1999] S.Ioffe and D.A.Forsyth. Finding people by sampling. In Proc. International Conference on Computer Vision, Corfu, Greece, pp.1092-1097, 1999.
[Ioffe and Forsyth’ 2001] S.Ioffe and D.A.Forsyth. Probabilistic methods for finding people. In International Journal of Computer Vision , Vol.43(1), pp.45-68, 2001
[Isard and Blake’ 1998a] M.Isard, A.Blake. CONDENSATION – conditional density propagation for visual tracking. International Journal of Computer Vision, Vol.9(1), pp.5-28, 1998
[Isard and Blake’ 1998b] M.Isard and A.Blake. ICondensation: unifying low-level and high-level tracking in a stochastic framework. In Proc. 5th European Conf. Computer Vision, Freiburg, Germany, Vol.1, pp.893-908, 1998
[Isard and Blake’ 1998c] M.Isard and A.Blake. A mixed-state Condensation tracker with automatic model-switching. In Proc. 6th Int. Conf. Computer Vision, Bombay, India, pp.107-112, 1998
[Isard and MacCormick’ 2001] M.Isard and J.MacCormick. BRaMBLe: A bayesian multiple-blob tracker. In Proc. of IEEE International Conference on Computer Vision, Vancouver, Canada, pp.34-41, 2001.
[Iwasawa et al’ 1997] S.Iwasawa, K.Ebihar, J.Ohya and S.Morishma. Real-time estimation ofhuman body posture from moncular thermal images. In Proc. of International Conference on Computer Vison and Patern Recogniton, San Juan, Puerto Rico, pp.15-20, 1997.
[Izo and Grimson’ 2004] T.Izo, W.E.L.Grimson. Simultaneous pose estimation and camera calibration from multiple views. In Proc. of IEEE Worskhop on Articulated and Nonrigid Motion at CVPR, Washington, DC, USA, pp.14, 2004
[Jabri and Duric’ 2000] S.Jabri, Z.Duric, A.Rosenfeld and H.Wechsler. Detection and location of people in video images using adaptive fusion of color and edge information. In Proc. of International Conference on Pattern Recognition, Barcelona, Spain, pp.4627-4631, 2000
[Jien et al’ 2002] K.Jien, W.Toyohide, J.Sebastien, et al. An HMM-based segmentation method for traffic monitoring movies. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24(9), pp.1291-1296, 2002
[Johansson’ 1995] G.Johansson. Visual perception of biological motion and a model for its analysis. Perceptional Psychology, Zurich, pp.290-295, 1995
[Jones and Rehg’ 1999] M.J.Jones and J.Rehg. Statistical color models with application to skin detection. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA, pp.274-280, 1999
[Jordon’ 2001] M.I.Jordon. MDL Introduction and Source Coding. Technical Report, Berkeley: University of California at Berkeley, Department of Computer Science, 2001
[Ju et al’ 1996] S.Ju, M.Black and Y.Yacoob. Cardboard people: a parameterized model of articulated motion. In 2nd International Conference on Automatic Face and Gesture Recognition, Vermont, USA, pp.38-44, 1996.
[Julier and Uhlmann’ 1997] S.J.Julier and J.K.Uhlmann. A new extension of the Kalman lter to nonlinear systems. In Proc. of AeroSense: The 11th International Symposium on Aerospace/Defence Sensing, Simulation and Controls, Orlando, Florida, USA, pp.182-193, 1997
[Kakadiaris and Metaxas’ 1996] I.Kakadiaris and D.Metaxas. Model-based estimation of 3d human motion with occlusion prediction based on active multi-viewpoint selection. In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp.81-87, 1996.
[Karmann and Brand’ 1990] K.Karmann, A.Von Brand. Moving object recognition using an adaptive background memory]. In Time-Varying Image Processing and Moving Object Recognition (Cappellini V ed.), Amsterdam:Elsevier Science, Florence, Italy, pp.289-296, 1990.
[Khan et al’ 2003] Z.Khan, T.Balch, and F.Dellaert. Efficient Particle Filter-Based Tracking of Multiple Interacting Targets Using an MRF-based Motion Model. In Proc. of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, USA, pp.202-211, 2003
[Kirkpatrick et al’ 1983] S.Kirkpatrick, C.D.Gelatt, M.P.Vecchi. Optimization by simulated annealing. Science, Vol.220, pp.671-680, 1983
[Kjeldsen and Kender’ 1996] R.Kjeldsen and J.Kender. Finding skin in color images. In Proc. International Conference on Automatic Face and Gesture Recognition, Vermont, USA, pp.312-317, 1996.
[Kong et al’ 1994] A.Kong, J.S.Liu, W.Wong. Sequential imputations and bayesian missing data problems. Journal of the American Statistical Association, Vol.89, pp.278-288, 1994
[Kwok et al’ 2002] C.Kwok, D.Fox and M.Meila. Real-time particle filters.Technical Report UW-CSE-02-07-01, 2002
[Kwok et al’ 2003] C.Kwok, D.Fox and M.Meila. Adaptive real-time particle filters for robot localization. In Proc. of the IEEE International Conference on Robotics and Automation, Taipei, China, pp. 2836-2841, 2003
[Lan and Huttenlocher’ 2004] X.Lan, D.P.Huttenlocher. A unified spatio-temporal articulated model for tracking. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, Vol.1, pp.722-729, 2004
[Lee and Cohen’ 2003] M.W.Lee, I.Cohen. Human body tracking with auxiliary measurements. In IEEE International Workshop on Analysis and Modeling of Faces and Gestures, Nice, France, pp.112-119, 2003
[Lee and Cohen’ 2004] M.W.Lee, I.Cohen. Human upper body pose estimation in static images. In Proc. of European Conference on Computer Vision, Prague, Czech Republic, pp.126-138, 2004,
[Lee et al’ 2002] M.W.Lee, I.Cohen, S.K.Jung. Particle Filter with analytical inference for human body tracking. In IEEE Workshop on Motion and Video Computing, Orlando, Florida, USA, pp.159-165, 2002
[Levenberg’ 1944] K.Levenberg. A method for the solution of certain non-linear problems in least squares. Quarterly Journal of Applied Mathematics, Vol.2, pp.164-168, 1944.
[Li and Zhang’ 2002] P.Li, T.Zhang. Visual contour tracking based on particle filters. In Proc. of Workshop on Generative-Model Based Vision, Copenhagen, Denmark, pp.111-123, 2002
[Liu and Chen’ 1995] J.S.Liu, R.Chen. Blind deconvolution via sequential imputations. Annals of Statistics Vol.24(3), pf.911-930, 1995
[Liu and Chen’ 1999] J.S.Liu, R.Chen. Sequential monte carlo methods for dynamical systems. Journal of the American Statistical Association, Vol.93, pp.1032-1044, 1999
[Lucas and Kanade’ 1981] B.Lucas and T.Kanade. An iterative image registration technique with an application to stereo vision. In. Proc. of 7th International Joint Conference on Artificial Intelligence, pp.674-679, 1981
[MacCormick and Isard’ 2000] J.MacCormick and M.Isard. Partitioned sampling, articulated objects, and interface-quality hand tracker. In European Conference on Computer Vision, Dublin, Ireland, Vol.2, pp.3-19, 2000.
[Mackay’ 1998] D.J.Mackay. Introduction to monte carlo methods. In Learning In Graphical Models. Jordan M I ed. Cambridge, MA: MIT Press, pp.175-204, 1999.
[Marquardt’ 1963] D.W.Marquardt. An algorithm for least-squares estimation of non-linear parameters. In Journal Of The Society Of Industrial And Applied Mathematics, Vol.11(2), pp.431-441, 1963.
[Maskell et al’ 2002] S.Maskell, N.Gordon, M.Rollason and D.Salmond. Efficient multitarget tracking using particle filters, In SPIE Proceedings, Vol.21(10), pp.931-939, 2002
[McKenna et al’ 1999] S.McKenna, Y.Raja and S.Gong.Tracking color objects using adaptive mixture models. Image Vision Computing, pp.225-231, 1999
[Menache’ 1999] A.Menache. Understanding motion capture for computer animation and video games. Morgan Kaufmann.1999
[Mikic et al’ 2002] I.Mikic, M.Trivedi, E.Hunter, P.Cosman. Human body model acquisition and tracking using voxel data. In International Journal of Computer Vision, Vol.53(3), pp.199-223, 2002
[Mittal and Davis’ 2002] A.Mittal and L.S.Davis. M2Tracker: a multi-view approach to segmenting and tracking people in a cluttered scene using region-based stereo. In 7th European Conference on Computer Vision (ECCV), Copenhagen, Denmark, pp.121-130, 2002
[Mittal and Davis’ 2003] A.Mittal and L.S.Davis. M2Tracker: a multi-view approach to segmenting and tracking people in a cluttered scene. In International Journal of Computer Vision. Vol.51(3), pp.189-203, 2003
[Moeslund and Granum’ 2000] T.B.Moeslund and E.Granum. 3D human pose estimation using 2d-data and an alternative phase shpe representation. In Workshop on Human Modeling,Analysi and Synthesis at CVPR,Hilton Head Island,South Carolina,USA, pp.237-247, 2000
[Moeslund and Granum’ 2001] T.Moeslund and E.Granum. A survey of computer vision-based human motion capture. Computer Vision and Image Understanding, pp.231-268, 2001.
[Moeslund and Granum’ 2002] T.Moeslund and E.Granum. Bootstrapping the Condensation Algorithm. In The 11th Danish Conference On Pattern Recognition And Image Analysis, www.vision.auc.dk/~tbm/Publications/ dankomb2002.pdf 2002
[Moeslund and Granum’ 2003] T.Moeslund and E.Granum. Sequential monte carlo tracking of body parameters in a sub-space. The International Workshop on Analysis and Modeling of Faces and Gestures (AMFG), Nice, France, pp.84-91, 2003
[Moeslund and Granum’ 2004] T.Moeslund and E.Granum. Motion capture of articulated chains by applying auxiliary information to the sequential monte carlo algortihm. In 4th IASTED International Conference on Visualization, Imaging, And Image Processing, Marbella, Spain, www.cvmt.dk/~tbm/Publications/ 2004
[Montemerlo et al’ 2002] M.Montemerlo, S.Thrun, W.Wh. Conditional particle filters for simultaneous mobile robot localization and people-tracking. In Proc. of IEEE International Conference on Robotics and Automation Washington, DC, USA, pp.695-701, 2002
[Moon et al’ 2001a] H.Moon, R.Chellappa and A.Rosenfeld. 3D object tracking using shape-encoded particle propagation. In Proc. of International Conference on Computer Vision, Vancouver, Canada, pp.307-314, 2001
[Moon et al’ 2001b] H.Moon, R.Chellappa and A.Rosenfeld. Tracking of human activities using shape-encoded particle propagation. In Proc. of International Conference on Image Processing, Thrace, Greece, pp.357-360, 2001
[Mori and Malik’ 2002] G.Mori and J.Malik. Estimating human body configurations using shape context matching. In Proc. of European Conference on Computer Vision, Dublin, Ireland, pp.666-680, 2002
[Morris and Rehg’ 1998] D.Morris and J.Rehg. Singularity analysis for articulated object tracking. In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, pp.289-296, 1998
[MotionAnalysis’ 2005] Optical motion capture equipment http://www.motionanalysis.com
[Nummiaro et al’ 2002] K.Nummiaro, E.Koller-Meier, L.Van Gool. A color-based particle filter. In Proc. of the 1st International Workshop on Generative-Model-Based Vision, in conjunction with ECCV02, Denmark, pp.53-60, 2002
[Nummiaro et al’ 2003] K.Nummiaro, E.B.Koller-Meier and L.Van Gool. Color features for tracking non-rigid objects. Special Issue on Visual Surveillance, ACTA Automatica Sinica (Chinese Journal of Automation), pp.345-355, 2003.
[Ong and Gong’ 1999] E.J.Ong and S.Gong. Tracking hybrid 2d-3d human models from multiple views. In International Workshop on Modeling People at ICCV'99, Corfu, Greece, pp.11-18, 1999.
[OpenCV’ 2004] http://www.intel.com/research/mrl/research/opencv
[Oren et al’ 1997] M.Oren, C.Papageorgiou, P.Sinha, E.Osuna and T.Poggio. Pedestrian detection using wavelet templates. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, pp.193-199, 1997
[Papageorgiu and Poggio’ 1999] C.Papageorgiu and T.Poggio. Trainable pedestrian detection. In Proc. of IEEE International Conference on Image Processing, Kobe, Japa, pp.241-246, 1999.
[Park et al’ 2003] J.Park, S.Park, J.K.Aggarwal. Human motion tracking by combining view-based and model-based methods for monocular video sequences. International Conference on Computational Science and Its Applications, Montreal, Canada, pp.650-659, 2003,
[Pavlovic et al’ 1999] V.Pavlovic, J.Rehg, T.Cham, et al. A dynamic bayesian approach to figure tracking using learned dynamical models. In Proc. of IEEE International Conference on Computer Vision. Corfu, Greece, pp.94-102, 1999
[Perales and Tores’ 1994] F.J.Perales and J.Tores. A system for human motion matching between synthetic and real images based on a biomechanic graphical model. In Workshop on Motion of Non-rigid and Articulated Objects, Austin, TX, USA, pp.83-88, 1994
[Pitt and Shephard’ 1999] M.Pitt, N.Shephard. Filtering via simulation: auxiliary particle filtering. Journal of the American Statistical Association, Vol.94(446), pp.590-599, 1999
[Plaenkers and Fua’ 2001] R.Plaenkers, P.Fua. Articulated soft objects for video-based body modeling. In Proc. of International Conference on Computer Vision. Vancouver, Canada, pp.394-402, 2001
[Polhemus’ 2005] Magnetic motion capture equipment http://www.polhemus.com
[Press’ 1988] W.H.Press, B.P.Flannery, S.A.Teukolsky, W.T. Vetterling. Numerical recipes in C. Cambridge University Press 1988.
[Qualisys’ 2005] Optical motion capture equipment http://www.qualisys.com
[Rabiner’ 1989] A.Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, ,Vol.7(2), pp.257-286, 1989
[Ramanan and Forsyth’ 2003] D.Ramanan, and D.Forsyth. Finding and tracking people from the bottom up. In Proc. of Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, pp.467-474, 2003
[Rehg and Kanade’ 1995] J.Rehg and T.Kanade. Model-based tracking of self occluding articulated objects. In Proc. of IEEE International Conference on Computer Vision, Cambridge, Massachusetts, USA, pp.612-617, 1995.
[Rehg et al’ 2003] J.Rehg, D.D.Morris, and T.Kanade. Ambiguities in visual tracking of articulated objects using two- and three-dimensional models. International Journal of Robotics Research, Vol.22(6), pp.393-418, 2003
[Rittscher et al’ 2000] J.Rittscher, J.Kato, S.Joga, et al. A probabilistic background model for tracking. In Proc. of European Conference on Computer Vision, Dublin, Ireland, pp.336-350, 2000.
[Roberts et al’ 2004] T.Roberts, S.J.McKenna, I.W.Ricketts. Human pose estimation using learnt robabilistic region similarities and partial configurations, In Proc. of European Conference on Computer Vision, Prague, pp.291-303, 2004
[Rohr’ 1994] K.Rohr. Towards model-based recognition of human movements in image sequences. Computer Vision, Graphics and Image Processing, Vol.59(1), pp.94-115, 1994.
[Rosales and Sclaroff’ 2000] R.Rosales and S.Sclaroff. Inferring body pose without tracking body parts, In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, pp.721-727, 2000
[Safonova et al’ 2004] A.Safonova, J.Hodgins and N.Pollard. Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces. ACM Transactions on Graphics. Vol.23(3), pp.514-521, 2004
[Saxe and Foulds’ 1996] D.Saxe and R.Foulds. Toward robust skin identification in video images. In Proc. of 2nd International Conference on Automatic Face and Gesture Recognition, Killington, Vermont, USA, pp.379-384, 1996
[Senior’ 2003] A.W.Senior. Real-time articulated human body tracking using silhouette information. In Proc. of IEEE Workshop on Visual Surveillance/PETS, Nice, France, www.research.ibm.com/ peoplevision/ Senior-vspets.pdf, 2003.
[Sidenbladh and Black’ 2001] H.Sidenbladh and M.Black. Learning image statistics for bayesian tracking. In Proc. of IEEE International Conference on Computer Vision, Vancouver, Canada, pp.709-716, 2001
[Sidenbladh and Wirkander’ 2003] H.Sidenbladh and S.Wirkander. Particle filtering for random sets. IEEE Transactions on Aerospace and Electronic Systems, www.irisa.fr/sigma2/campillo/ site-pf/bib/sidenbladh2000Xx.pdf, 2003
[Sidenbladh et al’ 2000] H.Sidenbladh, M.Black and D.Fleet. Stochastic tracking of 3d human figures using 2d image motion. In Proc. of European Conference on Computer Vision, Dublin, Ireland, pp.702-718, 2000
[Sidenbladh et al’ 2002] H.Sidenbladh, M.Black and L.Sigal. Implicit probabilistic models of human motion for synthesis and tracking. In Proc. of European Conference on Computer Vision, Copenhagen, Danmark, pp.784-800, 2002.
[Sminchisescu and Telea’ 2001a] C.Sminchisescu and A.Telea. A framework for generic state estimation in computer vision applications. In International Conference for Computer Vision, InternationalWorkshop on Computer Vision Systems, Vancouver, Canada, pp.21-34, 2001.
[Sminchisescu and Telea’ 2002] C.Sminchisescu and A.Telea. Human pose estimation from silhouettes: a consistent approach using distance level sets. In WSCG International Conference for Computer Graphics, Visualization and Computer Vision, Czech Republic, pp.201-212, 2002
[Sminchisescu and Triggs’ 2001b] C.Sminchisescu and B.Triggs. A robust multiple hypothesis approach to monocular human motion tracking. Technical Report RR-4208, INRIA 2001.
[Sminchisescu Sminchisescu and Triggs’ 2001c] C.Sminchisescu and B.Triggs. Covariance-scaled sampling for monocular 3d body tracking. In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, Hawaii, USA, pp.447-454, 2001.
[Song et al’ 2000] Y.Song, X.Feng and P.Perona. Towards detection of human motion. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, pp.810-817, 2000
[Soto and Khosla’ 2001] A.Soto and P.Khosla. Probabilistic adaptive agent based system for dynamic state estimation using multiple visual cues. In 10th International Symposium of Robotics Research. Lorne, Victoria, Australia., pp.35-42, 2001
[Soto’ 2002] A.Soto. A probabilistic approach for the adaptive integration of multiple visual cues using an agent framework. Doctoral dissertation, Robotics Institute, Carnegie Mellon University, October, 2002
[Stauder et al’ 1999] J.Stauder, R.Mech, J.Ostermann. Detection of moving cast shadows for object segmentation. IEEE Transactions on Multimedia, Vol.1(1), pp.65-76, 1999
[Stauffer and Grimson’ 1999] C.Stauffer, W.Grimson. Adaptive background mixture models for real-time tracking. In Proc. of International Conference on Computer Vision and Pattern Recognition, Fort Colins, Colombia, USA, pp.246-252, 1999
[Stauffer and Grimson’ 2000] C.Stauffer, E.L.Grimson. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22(8), pp.747-757, 2000
[Stenger et al’ 2001] B.Stenger, V.Ramesh, N.Paragios, et al. Topology free hidden markov models: application to background modeling. In Proc. of International Conference on Computer Vision, Vancouver, Canada, pp.294-301, 2001
[Stenger et al’ 2003] B.Stenger, A.Thayananthan, P.H.S.Torr and R.Cipolla. Filtering using a tree-based estimator. In Proc. 9th International Conference on Computer Vision, Nice, France, pp.1063-1070, 2003
[Sullivan et al’ 1999] J.Sullivan, A.Blake, M.Isard and J.MacCormick. Object localization by bayesian correlation. In Proc. of IEEE International Conference on Computer Vision, Corfu, Greece, pp.1068-7075, 1999.
[Taycher et al’ 2004] L.Taycher, J.W.Fisher and T.Darrell. Combining simple models to approximate complex dynamics. In Workshop of Statistical Methods in Video Processing at ECCV, Prague, Czech Republic, pp.94-104, May 16, 2004
[Thayananthan et al’ 2003] A.Thayananthan, B.Stenger, P.H.S.Torr and R.Cipolla. Tracking articulated hand motion using a kinematic prior. In Proc. British Machine Vision Conference, Norwich, UK, pp.598-598, 2003
[Triesch and von der Malsburg’ 2001] J.Triesch and C.von der Malsburg. Democratic integration: self-organized integration of adaptive cues. Neural Computation, Vol.13(9), pp.2049-2074, 2001
[Triesch et al’ 2002] J.Triesch, D.H.Ballard and R.A.Jacobs. Fast temporal dynamics of visual cue integration. Perception, pp.421-434. 2002
[Triesch’ 2000] J. Triesch. Self-organized integration of adaptive visual cues for face tracking. In Sensor Fusion: Architectures, Algorithms, and Applications IV, Belur V. Dasarathy, Editor, Proceedings of SPIE Vol.4051, pp.397-406, 2000
[Tsai’ 1987] R.T.Tsai. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-shelf TV camera and lens. IEEE Journal of Robotics and Automation, Vol.3(4), pp.323-344, 1987
[Urtasun and Fua’ 2004] R.Urtasun, P.Fua. 3D human body tracking using deterministic temporal motion models. In European Conference on Computer Vision, Prague, Czech Republic, pp.92-107, 2004
[Van der Merwe et al’ 2000] R.van der Merwe, N.de Freitas, A.Doucet and E.Wan. The unscented particle filter. Technical Report, CUED/F-INFENG/TR 380, Cambridge University Engineering Department, Cambridge, England, 2000
[Vermaak et al’ 2001] J.Vermaak, A.Blake, M.Gangnet and P.Pérez. Sequential Monte Carlo fusion of sound and vision for speaker tracking. In Proc. of International Conference on Computer Vision, Vancouver, Canada, pp.741-746, 2001
[Vermaak et al’ 2002] J.Vermaak, P.Prez, M.Gangnet and A.Blake. Towards improved observation models for visual tracking: selective adaptation. In Proc. of Europe Conference on Computer Vision, Copenhague, Danemark, pp.645-660, 2002
[Vermaak et al’ 2003] J.Vermaak, A.Doucet and P.Pérez. Maintaining multi-modality through mixture tracking. In Proc. of International Conference on Computer Vision, Nice, France, pp.1110-1116, 2003
[Vicon’ 2005] Optical motion capture equipment http://www.vicon.com
[Wachter and Nagel’ 1999] S.Wachter and H.Nagel. Tracking of persons in monocular image sequences, Computer Vision and Image Understanding Vol.74(3), pp.174-192, 1999
[Wang and Tan’ 2002] Y.Wang, T.Tan. Adaptive foreground and shadow detection in image sequences. In Proc. of Uncertainty in Artificial Intelligence, Alberta, Canada, pp.552-559, 2002
[Wang et al’ 2002] X.Wang, R.Chen, J.S.Liu. Monte carlo bayesian signal processing for wireless communications. Journal of VLSI Signal Processing. Vol.30, pp.89-105, 2002
[Wang et al’ 2003a] Y.Wang, T.Tan and K.F.Loe. Video segmentation based on graphical models. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin USA, pp.335-342, 2003
[Wang et al’ 2003b] Y.Wang, T.Tan, and K.F.Loe. Joint region tracking with switching hypothesized measurements. In Proc. International Conference on Computer Vision, Parisp. France, pp.75-82, 2003
[Welch and Bishop’ 1995] G.Welch, G.Bishop. An introduction to the kalman filter. Technicial Report, Chapel Hill: University of North Carolina, 1995
[Withagen et al’ 2002] P.J.Withagen, K.Schutte, F.Groen. Likelihood-based object tracking using color histograms and EM. In Proc. of the IEEE International Conference on Image Processing, Rochester, NY, USA, pp.589-592, 2002
[Wong and Wong’ 2003] S.F.Wong and K.Y.K.Wong. Reliable and fast human body tracking under information deficiency. In Proc. of IEEE Intelligent Automation Conference, Hong Kong, China, pp.491-498, 2003
[Wong and Wong’ 2004] S.F.Wong and K.Y.K.Wong. Real time human body tracking using wavenet. In Proc. of Asian Conference on Computer Vision (ACCV2004), Jeju Island, Korea, pp.91-96, 2004
[Wren et al’ 1997] R.C.Wren, A.Azarbayejani, T.Darrel, et al. Pfinder: real-time tracking of human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.19(7), pp.780-785, 1997
[Wren et al’ 2000] C.R.Wren, B.P.Clarkson and A.P.Pentland. Understanding purposeful human motion. In the 4th Internation Conference on Automatic Face and Gesture Recognition, Grenoble, France, pp.378-383, 2000
[Wu et al’ 2003] Y.Wu, G.Hua, T.Yu. Tracking articulated body by dynamic markov network. In 9th IEEE International Conference on Computer Vision, Nice, France, pp.1094-1101, 2003
[Yacoob and Black’ 1999] Y.Yacoob and M.J.Black. Parameterized modeling and recognition of activities in temporal surfaces, Computer Vision and Image Understanding Vol.73(2), pp.232-247, 1999
[Yang and Ahuja’ 1998] M.H.Yang and N.Ahuja. Detecting human faces in color images. In Proc. of the IEEE International Conference on Image Processing Piscataway, NJ. USA, pp.127-130, 1998
[Yilmaz et al’ 2004] A.Yilmaz, X.Li and M.Shah. Contour-based object tracking with occlusion handling in video acquired using mobile cameras. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.26, (11), pp.1531-1536, 2004.
[Zaritskii et al’ 1975] V.S.Zaritskii, V.B.Svetnik and L.I.Shimelevich. Monte carlo technique in problems of optimal data processing. Automation and Remote Control, Vol.12, pp.95-103, 1975
[Zhang and Liu’ 2002] J.L.Zhang, J.S.Liu. A new sequential importance sampling method with its application to the 2d hydrophobic-hydrophilic model. Journal of Chemical Physics, Vol.117, pp.3492-98, 2002
[Zhang et al’ 2004] J.Zhang, R.T. Collins and Y.Liu. Representation and matching of articulated shapes. In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,pp.342-349, 2004
[Zhang’ 2000] Z.Zhang. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22(11), pp.1330-1334, 2000
[Zhao and Nevatia’ 2002a] T.Zhao, R.Nevatia. Stochastic human segmentation from a static camera In IEEE Workshop on Motion and Video Computing, Orlando, FL. USA, pp.8-15, 2002
[Zhao and Nevatia’ 2002b] T.Zhao, R.Nevatia. Tracking human locomotion: a tracking as recognition approach, In Proc. of International Conference on Pattern Recognition, Quebec, Canada, pp.546-551, 2002
[Zhao and Nevatia’ 2003] T.Zhao, R.Nevatia. Bayesian human segmentation in crowded situations, In Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin USA, pp.459-466, 2003
[Zheng and Uezaki’ 1998] J.Y.Zheng and S.Uezaki. A model based aproach in extrating and generating human motion. In Proc. of International Confernce on Patern Recogniton, Brisbane, Australia, pp.1201-1205, 1998
[Zhou and Huang’ 2003] H. Zhou, T.S.Huang. Tracking articulated hand motion with eigen dynamics analysis. In Proc. of International Conference on Computer Vision, Paris, France, pp.1102-1109, 2003
[Zotkin et al’ 2001a] D.Zotkin, R.Duraiswami, L.Davis. Multimodal 3-D tracking and event detection via the particle filter. In Proc. of the IEEE Workshop on Detection and Recognition of Events in Video (in association with ICCV2001), Vancouver, Canada, pp. 20-27, 2001
[Zotkin et al’ 2001b] D.Zotkin, R.Duraiswami, L.Davis. Joint audio-visual tracking using particle filters. In EURASIP Journal on Applied Signal Processing, pp.1154-1164, 2001
[胡长勃’2001] 胡长勃 基于视觉的人体运动跟踪和识别研究 博士论文,中科院自动化所,2001
[卢德明 等’ 2001] 卢德明 运动生物力学测量方法 北京体育大学出版社 2001
[彭群生 等’ 1999] 彭群生,鲍虎军,金小刚,计算机真实感图形的算法基础,北京:科学出版社,1999
[王天树 等’ 2002] 王天树,郑南宁,李岩,徐迎庆,沈向洋 用于人体运动合成的运动纹理模型.第四届中国计算机图形学大会,北京,中国,pp.40-50, 2002
[徐钟济’ 1982] 徐钟济, 蒙特卡罗方法, 上海科技出版社, 1982
[向世明 等’2005] 向世明,陈睿,邓宇,李华 在线高斯混合模型和纹理支持的运动分割 计算机辅助设计与图形学学报,2005 (已录用)
[庄越挺 等’2000] 庄越挺,刘小明,潘云鹤,杨骏 运动图像序列的人体三维运动骨架重建, 计算机辅助设计与图形学学报,Vol.12(4), pp.245-250, 2000