隨著科技的進步，不論是在居家照顧或醫療看護的領域，安全議題已經變成得越來越重要。為了預防危險動作的發生及降低人為事故，因此，如何利用監控系統達到辨識危險行為變成一個很重要的研究議題。在本論文當中，我們提出一個基於光流法和傅利葉轉換的演算法去進行各種不同的行為分析 。

在演算法中，首先我們將影像序列利用光流法和背景減法來得到單張影像的光流圖和前景圖，並將序列中影像的光流圖和前景圖根據取樣區間相疊起來，藉此可以得到影像序列的光流軌跡圖及前景軌跡圖。接下來為了克服攝影機焦距大小及物體偏移的問題，我們將光流軌跡圖及前景軌跡圖的水平和垂直投影量進行傅利葉轉換，並取出低頻的部分進行分析。最後透過階層式最近鄰演算法來做出正確的分類。

根據實驗及測試後，我們證實本論文提出的演算法是有效率及高準確度的。

With the advancement of technology, the security issue has become more important. In order to prevent illegal behavior and to lower down the accident ratio in home care or medical care, it is an important topic for using surveillance systems to recognize illegal actions. In this thesis, the method which is based on the Discrete Fourier Transform (DFT) and optical flow was proposed.

In the proposed method, first of all, the optical flow image of sequences is captured, and the foreground image is extracted by background subtraction. Moreover, the overlapping image of optical flow and background subtraction are taken as the important features. Second, the DFT is used to overcome the problem of focal distance and object offsets. Finally, Hierarchical k-Nearest Neighbors (H-kNN) is used to classify correctly.

According to experiment results, it shows that proposed method is robust and efficient.

[1] M. Ahmad and S. Lee, "Human action recognition using shape and clg-motion flow from multi-view image sequences," Pattern Recognit, vol. 41, Issue 7, pp. Pages 2237-2252, July 2008.
[2] A. Aminian Modarres and M. Soryani, "Body posture graph: a new graph-based posture descriptor for human behaviour recognition," Computer Vision, IET, vol. 7, no. 6, pp. 488-499, December 2013.
[3] S. Belongie and J. Malik, "Matching with shape contexts," in Content-based Access of Image and Video Libraries, 2000. Proceedings. IEEE Workshop on, 2000, pp. 20-26.
[4] T. W. Chua, K. Leman, and N. T. Pham, "Human action recognition via sum-rule fusion of fuzzy k-nearest neighbor classi ers," in Fuzzy Systems (FUZZ), 2011 IEEE International Conference on, June 2011, pp. 484-489.
[5] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, June 2005, pp. 886-893 vol. 1.
[6] M.-A. Dragan and I. Mocanu, "Human activity recognition in smart environments," in Control Systems and Computer Science (CSCS), 2013 19th International Conference on, May 2013, pp. 495-502.
[7] H. Fujiyoshi and A. Lipton, "Real-time human motion analysis by image skeletonization," in Applications of Computer Vision, 1998. WACV '98. Proceedings., Fourth IEEE Workshop on, Oct 1998, pp. 15-21.
[8] U. Halici and O. Gokce, "Mixture of poses for human behavior understanding," in Image and Signal Processing (CISP), 2013 6th International Congress on, vol. 01, Dec 2013, pp. 112-116.
[9] B. Herbert, T. Tinne, and G. Luc Van, "Surf: Speeded up robust features," Computer Vision and Image Understanding, vol. 110 Issue 3, June, 2008, pp. 346-359.
[10] C.-W. Hsu and C.-J. Lin, "A comparison of methods for multiclass support vector machines," Neural Networks, IEEE Transactions on, vol. 13, no. 2, pp. 415-425, Mar 2002.
[11] H. Jhuang, T. Serre, L. Wolf, and T. Poggio, "A biologically inspired system for action recognition," in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, Oct 2007, pp. 1-8.
[12] K. Lertniphonphan, S. Aramvith, and T. Chalidabhongse, "Human action recognition using direction histograms of optical flow," in Communications and Information Technologies (ISCIT), 2011 11th International Symposium on, Oct 2011, pp. 574-579.
[13] C. Li, B. Su, Y. Liu, H. Wang, and J. Wang, "Human action recognition using spatio-temoporal descriptor," in Image and Signal Processing (CISP), 2013 6th International Congress on, vol. 01, Dec 2013, pp. 107-111.
[14] N. Li, X. Cheng, S. Zhang, and Z. Wu, "Recognizing human actions by bp-adaboost algorithm under a hierarchical recognition framework," in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, May 2013, pp. 3407-3411.
[15] X. Li, Hmm based action recognition using oriented histograms of optical flow field," Electronics Letters, vol. 43, no. 10, pp. 560{561, May 2007.
[16] Z. Lin, Z. Jiang, and L. Davis, "Recognizing actions by shape-motion prototype trees," in Computer Vision, 2009 IEEE 12th International Conference on, Sept 2009, pp. 444-451.
[17] D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol. 60, Issue 2, pp. 91-110, 2004.
[18] H. Ng, W.-H. Tan, H.-L. Tong, J. Abdullah, and R. Komiya, "Extraction of human gait features from enhanced human silhouette images," in Signal and Image Processing Applications (ICSIPA), 2009 IEEE International Conference on, Nov 2009, pp. 425-430.
[19] S. Rahman, S.-Y. Cho, and M. Leung, "Recognising human actions by analysing negative spaces," Computer Vision, IET, vol. 6, no. 3, pp. 197-213, May 2012.
[20] N. S. Ryosuke Kubota, Eiji Uchino, "Hierarchical k-nearest neighbor classi cation using feature and observation space information, "IEICE Electronics Express, vol.5 (2008) No. 3, pp. P.114{119, 2008.
[21] K. Schindler and L. Van Gool, Action snippets: How many frames does human action recognition require?" in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, June 2008, pp. 1-8.
[22] B. Sharma, K. S. Venkatesh, and A. Mukerjee, "Fourier shape-frequency words for actions," in Image Information Processing (ICIIP), 2011 International Conference on, Nov 2011, pp. 1-6.
[23] K. F. Sim and K. Sundaraj, "Human motion tracking of athlete using optical flow amp; arti cial markers," in Intelligent and Advanced Systems (ICIAS), 2010 International Conference on, June 2010, pp. 1-4.
[24] N. Thome, S. Miguet, and S. Ambellouis, "A real-time, multiview fall detection system: A lhmm-based approach," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 18, no. 11, pp. 1522-1532, Nov 2008.