Compressed Domain Real-time Action Recognition
Parvez Ahammad, Chuohao Yeo, S. Shankar Sastry and Kannan Ramchandran
We are investigating a compressed domain scheme that is able to recognize and localize actions in real time. The recognition problem is posed as performing a video query on a test video sequence. Our method is based on computing motion similarity using compressed domain features which can be extracted with low complexity. We introduce a novel motion correlation measure that takes into account differences in motion magnitudes. Our method is appearance invariant, requires no prior segmentation, alignment, or stabilization, and is able to localize actions in both space and time. We have evaluated our method on a large action video database consisting of 6 actions performed by 25 people under 3 different scenarios. Our current classification results compare favorably with existing methods at only a fraction of their computational costs .
- C. Yeo, P. Ahammad, K. Ramchandran, and S. S. Sastry, "Compressed Domain Real-time Action Recognition," MMSP, 2006.