The human action image and its application to motion recognition

Ricky J. Sethi, Amit K. Roy-Chowdhury
2010 Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP '10  
Recognizing a person's motion is intuitive for humans but represents a challenging problem in machine vision. In this paper, we present a multi-disciplinary framework for recognizing human actions. We develop a novel descriptor, the Human Action Image (HAI), a physically-significant, compact representation for the motion of a person, which we derive from Hamilton's Action. 1 We prove the additivity of Hamilton's Action in order to formulate the HAI and then embed the HAI as the Motion Energy
more » ... hway of the Neurobiological model of motion recognition. The Form Pathway is modelled using existing low-level feature descriptors based on shape and appearance. Finally, we propose a Weighted Integration (WI) methodology to combine the two pathways via statistical Hypothesis Testing using the bootstrap to do the final recognition. Experimental validation of the theory is provided on the well-known Weizmann and USF Gait datasets.
doi:10.1145/1924559.1924560 dblp:conf/icvgip/SethiC10 fatcat:fduyxt6sinh4pikka7j2x5bfku