Human Action Representation Using Pyramid Correlogram of Oriented Gradients on Motion History Images

Ling Shao (1) , Xiantong Zhen (2) , Yan Liu (3) , Ling Ji (4)

1 Electronic and Electrical Engineering
2 University of Sheffield [Sheffield]
3 POLYU - The Hong Kong Polytechnic University [Hong Kong]
4 Philips

The representation of human actions in video sequences is one of the key steps in action classification and recognition, performances of which are greatly dependent on the distinctiveness and robustness of the descriptors used for representation. In this paper, a novel descriptor, named Pyramid Correlogram of Oriented Gradients (PCOG), is presented for feature representation. PCOG, combined with the motion history images, captures both shape and spatial layout of the motion and therefore gives more effective and powerful representation for human actions and can be used for detection and recognition of a variety of actions. Experiments on challenging action datasets show that PCOG performs significantly better than Histogram of Oriented Gradients (HOG) both as a global descriptor and as a local descriptor.

Mots clés: Physical Sciences

Domaines: Informatique [cs]

Ling Shao, Xiantong Zhen, Yan Liu, Ling Ji. Human Action Representation Using Pyramid Correlogram of Oriented Gradients on Motion History Images. International Journal of Computer Mathematics, 2011, pp.1. ⟨10.1080/00207160.2011.582102⟩. ⟨hal-00721221⟩