近年來，監視系統的使用日趨廣泛，如：社區大樓的保全系統、數位醫療照護系統…等。不論是數位醫療照護系統或是保全監視系統，其大部分的事件皆與人類的行為有關，例如：老人的跌倒、竊賊偷偷摸摸與左顧右盼的行為等。若能藉由分析影像中人類的行為，判斷是否有可疑或不正常的事件發生，並即時做出適當的回應，便能阻止悲劇的發生。
為了進行人類的行為分析，本研究提出了一套行為辨識系統，其主要結合了Delaunay triangulation特徵與區域線性內嵌法(locally linear embedding, LLE)來進行人類行為辨識。經過實驗結果顯示，此系統在行為辨識上可以獲得不錯的辨識率。

In recent year, surveillance systems are used in many areas, such as the security system for community buildings, the digital health care system and so on. No matter what surveillance systems the digital health care system or the security system are, both involve human actions. For example, older people fell over, shop-lifting, quick glimpse at left and right and so on. If we can analyze human postures from a video sequence and recognize these suspicious events we can send messages and start an alarm immediately.
To realize human action analysis, we propose a human action recognition system. It uses the Delaunay triangulation method to extract features from the contour of a human body and recognize human action by the locally linear embedding method. According to the experiments, the recognition rates of the system can be as high as 92%.

[1] S. Huwer and H. Niemann, "Adaptive change detection for real-time surveillance applications," Proceedings of the Third IEEE International Workshop on Visual Surveillance, pp. 37-46, 2000.
[2] F. E. Alsaqre and B. Yuan, "Multiple moving objects tracking for video surveillance systems," 2004 7th International Conference on Signal Processing, vol.2, pp. 1301-1305, 2004.
[3] E. Herrero-Jaraba, C. Orrite-Urunuela and J. Senar, “Detected motion classification with a double-background and a Neighborhood-based difference,” Proceedings of the Pattern Recognition Letters, Vol.24, No.12, pp.2079-2092, August 2003.
[4] B.P.L. Lo, S.A. Velastin, “Automatic congestion detection system for underground platforms,” Proceedings of the Intelligent Multimedia, Video, and Speech Processing, pp.158–161, May 2001.
[5] R. Cucchiara, M. Piccardi and A. Prati, “Detecting moving objects, ghosts, and shadows in video streams,” Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25, No10, pp.1337-1342, October 2003.
[6] Q. Zhou, J. Aggarwal, “Tracking and classifying moving objects from videos,” Proceedings of the IEEE Workshop on Performance Evaluation of Tracking and Surveillance, 2001.
[7] E. L. Dagless, A. T. Ali, J. B. Cruz, ”Visual road traffic monitoring and data collection,” Proceedings of the IEEE Vehicle Navigation and Information Systems Conference, pp.146-149, October 1993

[8] N. Friedman and S. Russell, “Image segmentation in video sequences: A probabilistic approach,” Proceedings of the Thirteenth Annual Conference on Uncertainty in Artificial Intelligence, pp.175-181, 1997
[9] B. Shoushtarian, and H. E. Bez, “A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking,” Proceedings of the Pattern Recognition Letters, Vol.26, No.1 pp. 5-26, January 2005.
[10] J. C. S. J. Jr, C. R. Jung and S.R. Musse, ”A background subtraction model adapted to illumination changes,” Proceedings of the IEEE International Conference on Image Processing, pp.1817-1820, October 2006.
[11] C. Stauffer, and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol.2, pp.252, June 1999.
[12] Y. Yuan, Z. Miao, and S. Hu, “Real-Time Human Behavior Recognition in Intelligent Environment,” IEEE 8th International Conference on Signal Processing, Vol. 3, pp. 16-20, 2006.
[13] H. Fujiyoshi and A. J. Lipton. “Real-Time Human Motion Analysis by Image Skeletonization.” Proceedings of the Fourth IEEE Workshop on Applications of Computer Vision, pp. 15-21, 1998
[14] 陳宣勝，使用星狀骨架作人類動作自動辨識，國立交通大學資訊科學與工程研究所碩士論文，2006
[15] S. Belongie, J. Malik, and J. Puzicha, “Shape matching and object recognition using shape contexts,” Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 24, pp. 509- 522, 2002.
[16] 梁祐銘，利用Isomap學習及VLMM技術來分析人類之動作，國立交通大學資訊工程學系博士論文，2009
[17] J. W. Hsieh, Y. T. Hsu, H. Y. Liao and C. C. Chen, “Video-based human movement analysis and its application to surveillance systems.” IEEE Transactions on Multimedia, pp. 372-384, 2008
[18] D. Chetverikov and Z. Szabo, “A simple and efficient algorithm for detection of high curvature points in planar curves,” Proceedings of the 23rd Workshop Austrian Pattern Recognition Group, pp. 175–184, 1999.
[19] E. Horowitz, S. Sahni, and S. A. Freed, Fundamentals of Data Structure in C. New York: W. H. Freeman
[20] M. J. Swain and D. H. Ballard, “Color indexing,” International Journal of Computer Vision, vol. 7, no. 1, pp. 11–32, 1991.
[21] Sam Roweis, Lawrence Saul, “Nonlinear dimensionality reduction by Locally Linear Embedding“, Science, pp.2323-2326, 2000.
[22] Abdenour. H and Matti. Pietikainen, “Manifold Learning for Gender Classification from Face Sequences", Lecture Notes in Computer Science, pp. 82-91, 2009.
[23] Lena. G, Moshe. B, Eli. S, Michal. I and Ronen. B, Human Action Video, http://www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html
[24] Ivan Laptev, Human Action Video, http://www.nada.kth.se/cvap/actions/
[25] Ping. G and Zhenjiang. M, “Projection Histogram Based Human Posture Recognition”, Proceedings of the International Conference on Signal Processing, 2007