本篇論文包含了兩部份的研究主題：人體姿勢的重建與人體動作的辨識。在人體姿勢重建的部份，我們提出了一個新的以模型為基礎的方法，從單張影像中來重建3D人體姿勢。此方法是由一個姿勢資料庫與一組限制條件所引導。給定一張2D圖像，使用者標記出圖像中人體的各肢幹位置與估計其身體朝向，則系統首先會在姿勢資料庫中擷取出投影後最相似於2D人體影像的姿勢。為了加速擷取過程，我們提出了一種以查表為基礎的索引結構來建立姿勢資料庫。接下來系統會自動套用一組身體上與環境上的限制條件來重建出3D的人體姿勢。實驗結果進一步顯示了所提方法的有效性。在人體動作辨識的部份，我們利用動作捕捉資料來產生出許多不同的模擬動作軌跡，並利用不同的辨識演算法，包含動態時間校正法、支援向量機、隱藏的馬可夫模型與動態貝氏網路，來嘗試辨識出不同動作的軌跡。我們對於辨識的實驗結果進行討論，並且比較不同演算法之間的優缺點與適於使用的場合。

The thesis comprises two part of research: human posture reconstruction and human motion recognition. In the part of human posture reconstruction, we propose a novel model-based approach to reconstruct 3D human posture from a single image. The approach is guided by a posture library and a set of constraints. Given a 2D image and the users label body segments of human figure and estimate root orientation in the image, a 3D pivotal posture whose projection is similar to the 2D human figure will first retrieved from posture library. To facilitate the retrieval process, a table-lookup technique is proposed to build an index structure of posture library. Next, constraints including physical and environmental constraints are automatically applied to reconstruct the 3D posture. Experimental results show the effectiveness of the proposed approach. In the part of human motion recognition, we use motion capture data to generate simulated 2D motion trajectory. Next, four recognition algorithms including Dynamic Time Warping, Support Vector Machine, Hidden Markov Model, and Dynamic Bayesian Network are exploited to recognize different motion. We will discuss the experimental results in depth and compare different recognition algorithms.

[1] 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, pp. 809-830.

[2] N. M. Oliver, B. Rosario, A. P. Pentland, A Bayesian computer vision system for modeling human interactions, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 2000, pp. 831-843.

[3] M. Kőhle, D. Merkl, J. Kastner, Clinical gait analysis by neural networks: issues and experiences, IEEE Symposium on Computer-Based Medical Systems, 1997, pp. 138-143.

[4] D. Meyer, J. Denzler, H. Niemann, Model based extraction of articulated objects in image sequences for gait analysis, IEEE International Conference on Image Processing, 1997, pp. 78-81.

[5] J. W. Davis, A. F. Bobick, Virtual PAT: a virtual personal aerobics trainer, Workshop on Perceptual User Interfaces, San Francisco, CA, Nov. 5-6, 1998, pp. 13-18.

[6] P. T. Chua, R. Crivella, B. Daly, N. Hu, R. Schaaf, D Ventura, T. Camill, J. Hodgins, R. Pausch, Training for physical tasks in virtual environments: Tai Chi, IEEE International Conference on Virtual Reality, Los Angeles, CA, Mar. 22-26, 2003.

[7] C. BenAbelkader, R. Cutler, L. Davis, Person identification using automatic height and stride estimation, IEEE International Conference on Pattern Recognition, Quebec City, Canada, Aug. 11-15, 2002.

[8] A. F. Bobick, A. Johnson, Gait recognition using static activity-specific parameters, IEEE Computer Vision and Pattern Recognition, Kauai, Hawaii, Dec. 8-14, 2001.

[9] F. Multon, L. France, M.-P. Cani-Gascuel, G. Debunne, Computer animation of human walking: a survey, The Journal of Visualization and Computer Animation, 10(1), 1999, pp. 39-54.

[10] O. Arikan, D. A. Forsyth, J. F. O’Brien, Motion synthesis from annotations, ACM Transactions on Graphics, 22(3), 2003, pp. 402-408.

[11] W. T. Freeman, P. A. Beardsley, H. Kage, K.-I. Tanaka, K. Kyuma, C. D. Weissman, Computer vision for computer interaction, ACM SIGGRAPH Computer Graphics, 33(4), 1999, pp. 65-68.

[12] J. Lee, J. Chai, J. K. Hodgins, P. S. A. Reitsma, N. S. Pollard, Interactive control of avatars animated with human motion data, ACM Transactions on Graphics, 21(3), 2002, pp. 491-500.

[13] Lee, H. J. and Chen, Z. Determination of 3D human body postures from a single view, Computer Vision, Graphics, and Image Processing, 30, 1985, pp. 148-168.

[14] Bregler, C. and Malik, J. Tracking people with twists and exponential maps, IEEE Computer Vision and Pattern Recognition, Santa Barbara, California, 1998, pp. 8-15.

[15] Difranco, D. E., Cham, T. J., and Rehg, J. M. Recovery of 3D articulated motion from 2D correspondences, Compaq Cambridge Research Laboratory Technical Report Series, CRL 99/7, Dec. 1999.

[16] Taylor, C. J. Reconstruction of articulated objects from point correspondences in a single uncalibrated image, Computer Vision and Image Understanding, 80(3), 2000, pp. 349-363.

[17] Barron, C. and Kakadiaris, I. A. Estimating anthropometry and posture from a single image, IEEE Computer Vision and Pattern Recognition, South Carolina, USA, 2000.

[18] Park, M. J., Choi, M. G., and Shin, S. Y. Human motion reconstruction from inter-frame feature correspondences of a single video stream using a motion library, ACM SIGGRAPH Symposium on Computer Animation, San Antonio, Texas, USA, 2002.

[19] J. Davis, M. Agrawala, E. Chuang, Z. Popović, D. Salesin, A sketching interface for articulated figure animation, ACM SIGGRAPH/Eurographics Symposium on Computer Animation, San Diego, California, USA, Jul. 26-27, 2003.

[20] Pavlović, V., Rehg, J. M., Cham, T. J., and Murphy, K. P. A dynamic Bayesian network approach to figure tracking using learned dynamic models, IEEE International Conference on Computer Vision, Kerkyra, Corfu, Greece, 1999, pp. 94-101.

[21] Brand, M. Shadow puppetry, IEEE International Conference on Computer Vision, Kerkyra, Corfu, Greece, 1999, pp. 1237-1244.

[22] Howe, N. R., Leventon, M. E., and Freeman, W. T. Bayesian reconstruction of 3D human motion from single-camera video, Neural Information Processing Systems, Denver, Colorado, USA, Nov. 29-Dec. 4, 1999.

[23] Rosales, R. and Sclaroff, S. Learning body pose via specialized maps, Neural Information Processing Systems, Vancouver, British Columbia, Canada, 2001.

[24] T. B. Moeslund, E. Granum, A survey of computer vision-based human motion capture, Computer Vision and Image Understanding, 81(3), 2001, pp. 231-268.

[25] L. Wang, W. Hu, T. Tan, Recent developments in human motion analysis, Pattern Recognition, 36(3), 2003, pp. 585-601.

[26] Matthew Brand, Nuria Oliver, and Alex Pentland, Coupled hidden markov models for complex action recognition, Computer Vision and Pattern Recognition, 1997.

[27] Y. Luo, T.-D. Wu, J.-N. Hwang, Object-based analysis and interpretation of human motion in sports video sequences by Dynamic Bayesian Networks, IEEE Computer Vision and Image Understanding, 92 (2) (2003) 196-216.

[28] Deva Ramanan, David A. Forsyth, Automatic annotation of everyday movements, Neural Information Processing Systems , 2003.

[29] Cheung, G. K. M., Baker, S., and Kanade, T. Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture, IEEE Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, 2003.

[30] Davis, J., Agrawala, M., Chuang, E., Popović, Z., and Salesin, D. A sketching interface for articulated figure animation, ACM SIGGRAPH/Eurographics Symposium on Computer Animation, San Diego, CA, USA, 2003.

[31] Tolani, D., Goswami, A., and Badler, N. Real-time inverse kinematics techniques for anthropomorphic limbs, Graphical Models, 62(5), 2000, pp. 353-388.

[32] McFarlane, S. The Complete Book of T’ai Chi, Dorling Kindersley Limited, London, 1999.

[33] Gleicher, M. Retargetting motion to new characters, ACM SIGGRAPH, Orlando, Florida, Jul. 19-24, 1998.

[34] T. W. Parsons, Voice and Speech Processing, McGraw-Hill, 1986.

[35] O. Arikan, D. Forsyth, and J. O’Brien. Motion synthesis from annotations. In Proc. ACM SIGGRAPH, 2003.

[36] C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2):955–974, 1998.

[37] B. Scholkopf, C.J.C. Burges, and A.J. Smola. Advances in Kernel Methods. MIT Press, 1998.

[38] X.D. Huang, Y. Ariki, and M.A. Jack, Hidden Markov Models for Speech Recognition. Edinburgh: Edinburgh Univ. Press, 1990.

[39] L.R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Proc. IEEE, vol.77, pp. 257-285, 1989.

[40] R.G. Cowell, A.P. Dawid, S.L. Lauritzen, D.J. Spiegelhalter, Probabilistic Networks and Expert Systems, Spring-Verlag, Berlin-Heidelberg-New York, 1999.

[41] K. Murphy, Dyanamic Bayesian Networks: Representation, Inference and Learning, PH.D. dissertation, UC Berkeley 2002.

[42] D. Ramanan and D.A. Forsyth. Finding and tracking people from the bottom up. IEEE Computer Vision and Pattern Recognition, 2003.

[43] H. Sidenbladh, M.J. Black, L. Sigal, Implicit probabilistic models of human motion for synthesis and tracking. European Conference on Computer Vision, 2002.

[44] C.C. Chang and C.J. Lin. Libsvm: Introduction and benchmarks. Technical report, Department of Computer Science and Information Engineering, National Taiwan University, 2000.

[45] K. Murphy, The Bayes net toolbox for matlab, Computer Science and Statistics 33, 2001.