A Fast Statistical Approach for Human Activity Recognition

Samy Sadek, Ayoub Al-Hamadi, Bernd Michaelis, Usama Sayed

.

DOI: 10.4236/ijis.2012.21002                

Abstract

An essential part of any activity recognition system claiming be truly real-time is the ability to perform feature extraction in real-time. We present, in this paper, a quite simple and computationally tractable approach for real-time human activity recognition that is based on simple statistical features. These features are simple and relatively small, accordingly they are easy and fast to be calculated, and further form a relatively low-dimensional feature space in which classification can be carried out robustly. On the Weizmann publicly benchmark dataset, promising results (i.e. 97.8%) have been achieved, showing the effectiveness of the proposed approach compared to the-state-of-the-art. Furthermore, the approach is quite fast and thus can provide timing guarantees to real-time applications.

Keywords

Activity Recognition; Motion Analysis; Statistical Moments; Video Interpretation

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “Human Actionrecognition: A Novel Scheme Using Fuzzy Log-Polar Histogram and Temporal Self-Similarity,” EURASIP Journal on Advances in Signal Processing, 2011.
[2]	Y. G. Jiang, C. W. Ngo and J. Yang, “Towards Optimal bag-Offeatures for Object Categorization and Semantic Video Retrieval,” ACM International Conferences on Image and Video Retrieval, Vol. 8, 2007, pp. 494-501.
[3]	R. Cutler and L. S. Davis, “Robust Real-Time Periodic Motion Detection, Analysis, and Applications,” IEEE Transactions on PAMI, Vol. 22, 2000, pp. 781-796. doi:10.1109/34.868681
[4]	S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “An Efficient Method for Real-Time Activity Recognition,” Proceedings of the International Conference on Soft Computing and Pattern Recognition, Paris, 2010, pp. 7- 10. doi:10.1109/SOCPAR.2010.5686433
[5]	C. Thuran and V. Hlavaˇc, “Pose Primitive Based Human Action Recognition in Videos or Still Images,” Conference on Computer Vision and Pattern Recognition, 2008.
[6]	S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “Human Activity Recognition: A Scheme Using Multiple cues,” Proceedings of the International Symposium on Visual Computing, Las Vegas, 2010, pp. 574-583.
[7]	W.-L. Lu, K. Okuma and J. J. Little, “Tracking and Recognizing Actions of Multiple Hockey Players Using the Boosted Particle Filter,” Image and Vision Computing, Vol. 27, 2009, pp. 189-205. doi:10.1016/j.imavis.2008.02.008
[8]	S. Sadek, A. Al-Hamadi, M. Elmezain, B. Michaelis and U. Sayed, “Human Activity Recognition Using Temporal Shape Moments,” IEEE International Symposium on Signal Processing and Information Technology, Luxor, 2010, pp. 79-84. doi:10.1109/ISSPIT.2010.5711729
[9]	S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “Towards Robust Human Action Retrieval in Video,” Proceedings of the British Machine Vision Conference, Aberystwyth, 2010.
[10]	P. Doll’ar, V. Rabaud, G. Cottrell and S. Belongie, “Behavior Recognition via Sparse Spatio-Temporal Featu- Res,” IEEE International Workshop on VS-PETS, 2005.
[11]	J. Liu and M. Shah, “Learning Human Actions via Information Maximization,” Conference on Computer Vision and Pattern Recognition, Alaska, 2008.
[12]	A. F. Bobick and J. W. Davis, “The Recognition of Human Movement Using Temporal Templates,” IEEE Transactions on PAMI, Vol. 23, No. 3, 2001, pp. 257-267. doi:10.1109/34.910878
[13]	E. Shechtman and M. Irani, “Space-Time Behavior Based Correlation,” Conference on Computer Vision and Pattern Recognition, Vol. 1, 2005, pp. 405-412.
[14]	M. D. Rodriguez, J. Ahmed and M. Shah, “Action MACH: A Spatio-Temporal Maximum Average Correlation Height Filter for Action Recognition,” Conference on Computer Vision and Pattern Recognition, Alaska, 2008. doi:10.1109/CVPR.2008.4587727
[15]	H. Jhuang, T. Serre, L. Wolf, and T. Poggio, “A biologically inspired system for action recognition,” International Conference on Computer Vision, Sophia Antipolis, 2007, pp. 257-267.
[16]	K. Schindler and L. V. Gool, “Action Snippets: How Many Frames Does Action Recognition Require?” Conference on Computer Vision and Pattern Recognition, Alaska, 2008.
[17]	B. Laxton, J. Lim and D. Kriegman, “Leveraging Temporal, Contextual and Ordering Constraints for Recognizing Complex Activities in Video,” Conference on Computer Vision and Pattern Recognition, Alaska, 2007, pp. 1-8. doi:10.1109/CVPR.2007.383074
[18]	N. Olivera, A. Garg and E. Horvitz, “Layered Representations for Learning and Inferring Office Activity from Multiple Sensory Channels,” Computer Vision and Image Understanding, Vol. 96, No. 2, 2004, pp. 163-180. doi:10.1016/j.cviu.2004.02.004
[19]	D. M. Blei and J. D. Lafferty, “Correlated Topic Models,” Advances in Neural Information Processing Systems, Vol. 18, 2006, pp. 147-154.
[20]	V. N. Vapnik, “The Nature of Statistical Learning Theory,” Springer-Verlag, New York, 1995.
[21]	M. Blank, L. Gorelick, E. Shechtman, M. Irani and R. Basri, “Actions as Space-Time Shapes,” International Conference on Computer Vision, Sophia Antipolis, 2005, pp. 1395-1402.
[22]	M. Bregonzio, S. Gong and T. Xiang, “Recognising Action as Clouds of Space-Time Interest Points,” Conference on Computer Vision and Pattern Recognition, Alaska, 2009.
[23]	Z. Zhang, Y. Hu, S. Chan and L.-T. Chia, “Motion Context: A New Representation for Human Action Recognition,” European Conference on Computer Vision, Crete, 2008, pp. 817-829.
[24]	J. Niebles, H. Wang and L. Fei-Fei, “Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words,” International Journal of Computer Vision, Vol. 79, No. 3, 2008, pp. 299-318. doi:10.1007/s11263-007-0122-4
[25]	A. Fathi and G. Mori, “Action Recognition by Learning Midlevel Motion Features,” Conference on Computer Vision and Pattern Recognition, Alaska, 2008.