近年來，電腦視覺的蓬勃發展促進了視覺監控系統的發達，而步態辨識屬於視覺監控系統的一個部份。在本論文所提出的人類步態辨識方法，同時考慮了速度以及形狀的資訊來幫助判斷。我們採用速度不定矩來表示速度資訊。因為單一的frame無法呈現出速度資訊，需要數個frame的內容才能計算出速度資訊。因此將影片分成數個區段。每個區段視為一個處理單元。再以處理單元為單位，計算其速度與形狀資訊。在速度資訊方面，我們利用x，y以及x-y三個方向的速度不定矩來表示速度資訊;而在形狀資訊方面，我們用累加表來儲存形狀資訊。我們先利用Canny測邊搜集出每張frame邊點間的資訊，然後再計算邊點之間的相對關係，包含了邊點之間的距離以及角度的資訊，再將處理後的結果存入累加表，其大小可以根據需要來決定以記錄形狀資訊，這給予了很大的彈性。又辨識的步驟係採用 AdaBoost演算法，它在訓練時的收斂速度佔了很大的優勢，有助於更新資訊或是新增步態姿勢的種類。在本論文中，我們辨識走、跑、跛行三種步態，根據實驗結果顯示：同時考慮速度與形狀資訊可以有不錯的辨識率。

In recent years, the researchers in the field of computer vision have devoted considerable efforts to visual surveillance systems. Motion classification is part of a visual surveillance system. In this thesis, we propose a human motion classification method that classifies three different kinds of human motion. We divide each sequence as several segments that are regarded as a process unit. For each process unit, we collect both the velocity and shape information of a moving object. We use velocity moment to represent the velocity of moving object, and we take account of three-direction velocity: x, y, and x-y directions. As for the shape, we use an accumulation table to code such information. We first use the Canny edge detector to calculate the edge information. We then put it into the accumulation table. In addition, the accumulation table can adjust its size for the requirement. The motion classification employs an AdaBoost algorithm which is excellent in facilitating the speed of convergence during the training. Hence, it is conducive to update new information and add new kinds of motion. The experimental result reveals that our classification method has good results from using both velocity and shape information.

[1] K. Luttgens and K. F. Wells, “Kinesiology: Scientific Basis of Human Motion,” Saunders College Publishing, Philadelphia, 1982.
[2] J. Piscopo and J. A. Baley Kinesiology , “the science of movement,” John Wiley and Sons, New York, 1981.
[3] M. C. Mazzaro, M. Sznaieer, and O. Camps, “a model (in) validation approach to
gait classification,” IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 27, pp. 1820-1825, 2005.
[4] J. D. Shutler, M. S. Nison, and C. J. Harris, “Statistical gait description via
temporal moments,” in Proceedings of the 4th IEEE Southwest Symposium on
Image Analysis and Interpretation, USA, pp.291-295, 2000.
[5] M. Brand, N. Oliver, and A. Pentland, “coupled hidden Markov models for
complex action recognition,” in Proceedings of IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, San Juan, pp. 994-999,
1997
[6] Ezra Tassone, Geoff West and Svetha Venkatesh, “Temporal PDMs for Gait Classification,” in Proceedings of the 16th International Conference on Pattern Recognition, vol. 2, pp.1065-1068, Singapore, 2002.
[7] Ezra Tassone, Geoff West and Svetha Venkatesh, , “Classifying complex human motion using point distribution models,” in 5th Asian Conference on Computer Vision, pp. 148-156, 2002
[8] Hironobu Fujiyoshi, Alan J. Lipton, “Real-time Human Motion Analysis by Image Skeletonization,” in Proceedings of 4th IEEE Workshop on Applications of Computer Vision, pp.15-21, 1998.
[9] R. Das. Sandhitsu, C. Wilson Robert, T. Lazarewicz Maciej, H. Finkel Leif, “Gait Recognition by Two-Stage Principal Component Analysis,” in 7th International Conference on Automatic Face and Gesture Recognition, pp.579-584, 2006.
[10] J. E. Jackson, “A User’s Guide to Principal Components,” John Wiley and Sons Inc., 1991.
[11] J. L. Wang, B. L. Lo, G. Z. Yang, “Ubiquitous sensing for posture/behavior analysis,” in IEE proceedings of the 2nd International Workshop on Body Sensor Networks, pp.119-122, 2005.
[12] A. N. Rajaqopalan, R.Chellappa, “High-order spectral analysis of human motion,” in Proceedings of International Conference on Image Processing, vol. 3 pp.230-233, 2000.
[13] L. Li, W. Huang, I. Y. H. Gu, Q. Tian, “Statistical Modeling of Complex Backgrounds for Foreground Object Detection,” IEEE Transactions on Image Processing, vol. 13, Nov. 2004.
[14] C. Stauffer and W. Grimson, “Learning Patterns of Activity Using Real-Time Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp.747-757, Aug. 2000.
[15] I. Haritaoglu, D. Harwood, and L. Davis, “W4: Real-time Surveillance of People and Their Activity,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 809-830, Aug. 2000.
[16] L. Li and M. Leung, “Integrating Intensity and Texture differences for robust change detection,” IEEE Transactions on Image Processing, Vol. 11, pp. 105-112, Feb. 2002.
[17] O. Javed, K. Shafique, M. Shah, “A Hierarchical Approach to Robust Background Subtraction Using Color and Gradient Information,” in Proceedings of 2002 Workshop on Motion and Video Computing, pp.22-27, Dec. 2002.
[18] L. Li, W. Huang, I. Y. H. Gu, Q.Tian, “Foreground Object detection in changing background based on color co-occurrence statistics,” in Proceedings of 6th IEEE Workshop on Applications of Computer Vision, pp. 269-274, Dec. 2002.
[19] J. Heikkila and O. Silven, “A Real-Time System for Monitoring of Cyclists and Pedestrians,” Second IEEE Workshop on Visual Surveillance, pp. 74-81, Jun. 1999.
[20] X. Q. Song, Real-Time Visual Detection and Tracking of Multiple Moving Objects Based on Particle Filtering Techniques, Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 2005.
[21] 王俊明，陳世旺，「漸進式背景影像建構」，師大學報：數理與科技類，民國91年。
[22] Y. Kuno, T. Watanabe, Y. Shimosakoda, and S. Nakagawa, “Automated Detection of Human for Visual Surveillance System,” in Proceedings of International Conference on Pattern Recognition, pp. 865-869, 1996.
[23] R. Cucchiara, C. Grana, G. Neri, M. Piccardi, and A. Prati, “The Sakbot System for Moving Object Detection and Tracking,” Video-based Surveillance Systems-Computer Vision and Distributed Processing, pp.145-157, 2001.
[24] T. Horprasert, D. Harwood, and L.S. Davis, “A Statistical Approach for Real-Time Robust Background Subtraction and Shadow Detection,” in Proceedings of IEEE International Conference on Computer Vision FRAME-RATE Workshop, 1999.
[25] I. Mikic, P. Cosman, G. Kogut, and M.M. Trivedi, “Moving Shadow and Object Detection in Traffic Scenes,” in Proceedings of 15th International Conference on Pattern Recognition, vol. 1, pp.321-324, Sept. 2000.
[26] N. Fridman and S. Russell, “Image Segmentation in Video Sequence: A Probabilistic Approach,” in Proceedings of 13th Conference on Uncertainty in Artificial Intelligence, 1997.
[27] M. R. Teague, “Image analysis via the general theory of moments,” Journal of the Optical Society of America, vol. 70, pp.920-930, 1979.
[28] F. Zernike,“ Beugungstheorie des Schneidenverfahrens und seiner verbesserten Form, ” der Phasenkontrastmethode,” Physica, pp. 689–704, 1934.
[29] J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, pp. 679-698, 1986.
[30] I. R. Vega, S. Sarkar, “Statistical Motion Model Based on the Change of Feature Relationships: Human Gait-Based Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1323-1328, 2003.
[31] Y. Freund and R. E. Schapire, “Experiments with a new boosting algorithm,” in Proceedings of the 13th International Conference on Machine Learning, pp. 148-156, 1996.
[32] J. Friedman, T. Hastie, and R. Tibshirani, “Additive logistic regression: a statistical view of boosting,” The Annals of Statistics, vol. 28, no. 2, pp. 337-407, 2000.
[33] R. E. Schapire and Y. Singer, “Improved boosting algorithms using confidence-rated predictions,” Machine Learning, vol. 37, no. 3, pp. 297-336, 1999.
[34] L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees, Chapman and Hall, New York, 1984.
[35] C. Bauckhage, J. K. Tsotsos, and F. E. Bunn, “Detecting abnormal gait,” in Proceedings of the 2th Canadianl Conference on Computer and Robot Vision, pp. 282-288, 2005.
[36] A. Vezhnevets, “GML Adaboost Matlab Toolbox,” Graphics and Media laboratory, Computer Science Department, Moscow State University, Moscow Russian Federation, http://research.graphicon.ru/