三維步態動作預測在現代電腦視覺中扮演著很重要的腳色。在這篇論文中，我們提出了一個可學習的架構來預測三維步態動作。首先，我們建立了一個具有各種步態姿勢的三維資料庫，接著將這些資料投影到二維平面來擷取這些步態姿勢從不同觀察角度上的資訊。藉著和相近的關節點相減以及前後張的位移，我們得到了空間和時間上人體資訊，得到了足夠的特徵當作我們的訓練的資訊。接著我們使用了決策樹結合多維梯度樹狀加速法來改善傳統上訓練過長的問題，並且得出能快速測試的決策樹。在測試階段，我們使用了一個自動起始身體部位的方法，接著使用粒子濾波器來追蹤這些身體部位在二維影像上的位置。在初略知道身體部位後，我們使用了骨架推估法來算出其他身體部位的位置。在獲取身體部位後，我們可以得到足夠的特徵來推估測試影片中三維人體步態姿勢。我們量化的實驗數據分析，顯示了我們提出的方法有著不錯的效果。

Human walking pose estimation plays an important role in modern computer vision. In this paper, we propose a method to estimate 3D human walking pose by a learning architecture. First, establishing the database by synthesize the human walking sequence. Then, projecting the 3D human model to 2D image plane obtains the 2D position from different views. By Applying the skeleton vector, which subtracts the nearest the joint position and previous orientation in image sequence to represent the direction of human body part, we obtain the spatial and temporal of human pose information. Due to the dimensionality of features are less, we use the fast training method called classification and regression trees combined with multi-gradient treeboost to improve the disadvantage of long time training and get the fast testing tree. The testing phase, we do an auto-initialization of human body part( head, chest, and lower limbs)on first image, then applying particle filter tracking on body parts obtains the following 2d position in image sequence. Then, we use skeleton approximating to get the other body part position. Finally, using the output of skeleton as the input feature of decision tree infers the 3D human walking pose. Our quantitative analysis of experimental results showed a good performance by using our proposed method.

[1] A. Agarwal, B. Triggs, “Recovering 3D human pose from monocular images” Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 28, Issue 1, Jan. 2006 Page(s):44 - 58 Digital Object Identifier 10.1109/TPAMI.2006.21

[2] A. Bissacco, Ming-Hsuan Yang, S. Soatto, “Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression” Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on 17-22 June 2007 Page(s):1 - 8 Digital Object Identifier 10.1109/CVPR.2007.383129

[3] G.. Shakhnarovich, P. Viola, T. Darrell, “Fast pose estimation with parameter-sensitive hashing” Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on13-16 Oct. 2003 Page(s):750 - 757 vol.2

[4] N. Howe, M. Leventon, and W. Freeman, “Bayesian Reconstruction of 3D Human Motion from Single-Camera Video,” Neural Information Processing Systems, 1999.

[5] C. Taylor, “Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image,” Proc. Int’l Conf. Computer Vision and Pattern Recognition, 2000.

[6] G. Mori and J. Malik, “Estimating Human Body Configurations Using Shape Context Matching,” Proc. European Conf. Computer Vision, vol. 3, pp. 666-680, 2002.

[7] W. P. Alexander and S. D. Grimshaw. “Treed regression.” Journal of Computational and Graphical Statistics, (5):156–175, 1996.

[8] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. “Classification and Regression Trees,” Wadsworth, Belmont, 1984.

[9] J. Gehrke, R. Ramakrishnan, and V. Ganti. “Rainforest– a framework for fast decision tree construction of large datasets.” In Proceedings of the 24th International Conference on Very Large Databases, pages 416–427. Morgan Kaufmann, August 1998.

[10] C. Taylor, “Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image,” Proc. Int’l Conf. Computer Vision and Pattern Recognition, 2000.

[11] V. Athitsos and S. Sclaroff, “Estimating 3D Hand Pose from a Cluttered Image,” Proc. Int’l Conf. Computer Vision, 2003.

[12] B. Stenger, A. Thayananthan, P. Torr, and R. Cipolla, “Filtering Using a Tree-Based Estimator,” Proc. Int’l Conf. Computer Vision, 2003.

[13] A. Agarwal and B. Triggs. “3d human pose from silhouettes by relevance vector regression,” CVPR, vol 2:pp. 882–888, 2004.

[14] R. Rosales and S. Sclaroff. Learning body pose via specialized maps. In NIPS, 2002.

[15] K. Grauman, G. Shakhnarovich, and T. Darrell. Inferring 3d structure with a statistical image-based shape model. ICCV, 2003.

[16] M. Brand, “Shadow Puppetry,” Proc. Int’l Conf. Computer Vision, pp. 1237-1244, 1999.

[17] V. Athitsos and S. Sclaroff, “Inferring Body Pose without Tracking Body Parts,” Proc. Int’l Conf. Computer Vision and Pattern Recognition, 2000.

[18] D. Ormoneit, H. Sidenbladh, M. Black, and T. Hastie, “Learning and Tracking Cyclic Human Motion,” Neural Information Processing Systems, pp. 894-900, 2000.

[19] V. Pavlovic, J. Rehg, and J. MacCormick, “Learning Switching Linear Models of Human Motion,” Neural Information Processing Systems, pp. 981-987, 2000.

[20] H. Sidenbladh, M. Black, and L. Sigal, “Implicit Probabilistic Models of Human Motion for Synthesis and Tracking,” Proc. European Conf. Computer Vision, vol. 1, 2002.

[21] K. Toyama and A. Blake, “Probabilistic Tracking in a Metric Space,” Proc. Int’l Conf. Computer Vision, pp. 50-59, 2001.

[22] J. H. Friedman. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29:1189–1232, 2001.

[25] T.B. Moeslund and E. Granum, “A Survey of Computer Vision-Based Human Motion Capture,” Computer Vision and Image Understanding, vol. 81, no. 3, pp. 231-268, 2001.

[26] D.M. Gavrila, “The Visual Analysis of Human Movement: A Survey,” Computer Vision and Image Understanding, vol. 73, no. 1, pp. 82-97, Jan. 1999.

[27] C. Barron and I.A. Kakadiaris, “On the Improvement of Anthropometry and Pose Estimation from a Single Uncalibrated Image,” Machine Vision and Applications, pp. 229-236, 2003.

[28] D. Demirdjian, “Combining Geometric- and View-Based Approaches for Articulated Pose Estimation,” Proc. European Conf. Computer Vision, pp. 183-194, 2004.

[29] P.F. Felzenszwalb and D.P. Huttenlocher, “Efficient Matching of Pictorial Structures,” Proc. Computer Vision and Pattern Recognition Conf., pp. 2066-2073, 2000.

[30] K. Grauman, G. Shaknarovich, and T. Darrell, “Inferring 3D Structure with a Statistical Image-Based Shape Model,” Proc. Int’l Conf. Computer Vision, pp. 641-648, 2003.

[31] M. Lee and I. Cohen, “Human Upper Body Pose Estimation in Static Images,” Proc. European Conf. Computer Vision, pp. 126-138, 2004

[32] A. Mohan, C. Parageogiou, and T. Poggio, “Example-Based Object Detection in Image by Components,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 4, pp. 349-361, Apr. 2001.

[33] R. Rosales, M. Siddiqui, J. Alon, and S. Sclaroff, ”Estimating 3D Body Pose Using Uncalibrated Cameras,” Proc. Computer Vision and Pattern Recognition Conf., pp. 821-827, 2001

[34] T. B. Moeslund, “Interacting with a virtual world through motion capture, in Interaction in Virtual Inhabited 3D Worlds” (L. Qvortrup, Ed.), chap. 11, Springer-Verlag, Berlin/New York, 2000.

[35] K. S. Huang ; “3D Shape Context Based Gesture Analysis Integrated with Tracking using Omni Video Array” Computer Vision and Pattern Recognition, 2005 IEEE Computer Society Conference on Volume 3, 20-26 June 2005 Page(s):80 – 80

[36] Cheng-Yu Chang, Chun-Rong Huang, Chen-Yi Hsu and Pau-Choo Chung, "Tracking Human Body Parts via Joint Probabilistic Data Association with Kinematic Constraints", 2008 Symposium on Digital Life Technologies: Human- Centric Smart Living Technology, June, 2008

[37] S. Belongie, J. Malik, and J. Puzicha, “Shape matching and object recognition using shape contexts,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 24, no. 4, pp. 509–522, 2002.

[38] M. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking,” Signal Processing, IEEE Transactions on [see also Acoustics, Speech, and Signal Processing, IEEE Transactions on], vol. 50, no. 2, pp. 174–188, 2002.

[39] L. Sigal and M.J. Black, “HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion.” Technical Report CS-06-08, 2006.

[40] M. Krinidis, N. Nikolaidis, I. Pitas, “3D head pose estimation using support vector machines and physics-based deformable surfaces” Signal Processing and Its Applications, 2007. ISSPA 2007. 9th International Symposium on 12-15 Feb. 2007 Page(s):1 – 4

[41] G.K.M Cheung, S. Baker, T. Kanade “Visual hull alignment and refinement across time: a 3D reconstruction algorithm combining shape-from-silhouette with stereo” Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on Volume 2, 18-20 June 2003 Page(s):II - 375-82 vol.2

[42] I. Mikic, M. Trivedi, E. Hunter, P. Cosman,“Articulated body posture estimation from multi-camera voxel data” Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
Volume 1, 2001 Page(s):I-455 - I-460 vol.1

[43] F. Dellaert and S. Tariq, “A Multi-Camera Pose Tracker for Assisting the Visually Impaired”
Computer Vision and Pattern Recognition, 2005 IEEE Computer Society Conference on Volume 3, 20-26 June 2005 Page(s):31 – 31 Digital Object Identifier 10.1109/CVPR.2005.391

[44] De Xu; You Fu Li ,“A new pose estimation method based on inertial and visual sensors for autonomous robots”, Robotics and Biomimetics, 2007. ROBIO 2007. IEEE International Conference on 15-18 Dec. 2007 Page(s):405 – 410

[45] P. F. Felzenszwalb and D. P. Huttenlocher, “Pictorial Structures for Object Recognition”, International Journal of Computer Vision, 2005. Volume 61, Number 1 / January

[46] G. Mori and J. Malik, “Recovering 3D Human Body Configurations Using Shape Contexts” Transaction on Pattern analysis and Machine intelligence, 2006.

[47] C. Sminchisescu and B. Triggs, “Kinematic Jump Processes for Monocular 3D Human Tracking,” Proc. Int’l Conf. Computer Visionand Pattern Recognition, June 2003

[48] B. Stenger, A. Thayananthan, P. Torr, and R. Cipolla, “Filtering Using a Tree-Based Estimator,” Proc. Int’l Conf. Computer Vision, 2003.

[49] K. An, “Kinematic analysis of human movement,” Annals of Biomedical Engineering, vol. 12, no. 6, pp. 585–597, Nov. 1984. [Online]. Available: http://dx.doi.org/10.1007/BF02371451

[50] N. Klopˇcar and J. Lenarˇciˇc, “Kinematic model for determination of human arm reachable workspace,” Meccanica, vol. 40, no. 2, pp. 203–219, Apr. 2005. [Online]. Available: http://dx.doi.org/10.1007/s11012-005-3067-0

[51] F. Bashir and F. Porikli, “Performance evaluation of object detection and tracking systems,” in IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), June 2006. [Online]. Available: http://www.merl.com/publications/TR2006-041/

[52] A. Bissacco. “Modeling and learning contact dynamics in human motion.” CVPR, v. 1, pp. 421–428, 2005.

[53] M. A. Brubaker, D. J. Fleet, and A. Hertzmann. “Physicsbased person tracking using simplified lower-body dynamics.” CVPR, pp. 1–8, 2007.