In this paper, a system framework has been presented to recognize a human activity recognition approach. The proposed framework is composed of three consecutive modules: (i) detecting and locating people by background subtraction, (ii) scale invariant contour-based pose features from silhouettes (iii) finally classifying activities of people by Multiclass Support vector machine (SVM) classifier. The proposed method use approximate median filter based background–foreground separation technique to extract motion information and generate object silhouettes to activity of humans present in a scene monitored by a camera. Experimental results demonstrate that the proposed method can recognize these activities accurately for standard KTH database.

1. Enficiaud, R. , Lienard, B. , Allezard, N. , Sebbe Serge Beucher, R. , Desurmont, X. , Sayd, P. , and Delaigle, J. , 2006. CLOVIS - A generic framework for general purpose visual surveillance applications.
2. Chen, P. Y. , Lin, H. M. , Chen, W. T. , and Tseng, Y. C. , 2010. Demo abstract: a multi-view visual surveillance system based on angle coverage, in Proc. in the 8th ACM Conference on Embedded Networked Sensor System.
3. Valera, M. , and Velastin, S. A. , 2005. Intelligent distributed surveillance systems: a review, Int. j. Vision, Image and Signal Processing, 152(2): 192-204.
4. Srinivasan, K. , Porkumaran, K. and Sainarayanan, G. , 2009. Intelligent human body tracking, modeling, and activity analysis of video surveillance system: A survey, Int. J. of Convergence in Engineering, Technology and Science, 1: 1-8.
5. Weinland, D. and Ronfard, R. , 2011. A survey of vision based methods for action representation, segmentation, and recognition,Computer Vision and Image Understanding, 115(2): 529–551.
6. Junejo, I. , Dexter, E. , Laptev, I. and Perez, P. View-independent action recognition from temporal self-similarities, IEEE Trans. On Pattern Analysis and Machine Intelligence, in press.
7. Laptev, I. , Caputo, B. , Schuldt, C. , and Lindeberg, T. , 2007. Local velocity adapted motion events for spatio-temporal recognition, 108: 207-229.
8. Ke, Y. , Sukthankar, R. , and Hebert, M. , 2010. Volumetric features for video event detection, Int. J. of Computer Vision.
9. Technical Report CMU-CS-08-113. , 2008. Volumetric features for video event detection.
10. Bobick, A. F. , and Davis, J. W. , 2001. The recognition of human movement using temporal templates, IEEE Trans. Pattern Analysis and Machine Intelligence, 23(3): 257-267.
11. Hu, M. , 1962. Visual pattern recognition by moment invariants, IRE Trans. Information Theory, 8(2): 179-187.
12. KTH Research Project Activity Database. Available at: http://www. nada. kth. se/cvap/actions
13. McFarlane, N. , and Schofield, C. , 1995. Segmentation and tracking of piglets in images, Machine Vision Application, 8(3): 187-193.
14. Y. Dedeog? lu, B. Töreyin, U. Güdükbay, A. Çetin, "Silhouette-based method for object classi?cation and human action recognition in video", Computer Vision in Human-Computer Interaction, Lecture Notes in Computer Science, 3979. Springer, Berlin/Heidelberg, pp. 64–77, 2006.
15. S. Suzuki, K. be, "Topological structural analysis of digitized binary images by border following", Comput. Vision Graphics Image Process, Vol. 30, pp. 32–46, 1985.
16. J. Westons and C. Wtkins, "Support Vector Machines for Multiclass Pattern Recognition," Proc. 7th European Symposium on Artificial Neural Networks, pp. 219-224, 1999.
17. V. Kulathumani, WVU Multi-View Action Recognition DatasetAvailable on: http://csee. wvu. edu/~vkkulathumani/wvu-action. html#download2

Video Surveillance Support Vector Machine Approximate Median Filter