A method for human action recognition.pdf

A method for human action recognition Osama Masoud, Nikos Papanikolopoulos* Department of Computer Science and Engineering, University of Minnesota, 4-192 EE/CS Building, 200 Union Street SE, Minneapolis, MN 55455, USA Received 25 February 2002; received in revised form 4 March 2003; accepted 18 March 2003 Abstract This article deals with the problem of classification of human activities from video. Our approach uses motion features that are computed very efficiently, and subsequently projected into a lower dimensional space where matching is performed. Each action is represented as a manifold in this lower dimensional space and matching is done by comparing these manifolds. To demonstrate the effectiveness of this approach, it was used on a large data set of similar actions, each performed by many different actors. Classification results were very accurate and show that this approach is robust to challenges such as variations in performers’ physical attributes, color of clothing, and style of motion. An important result of this article is that the recovery of the three-dimensional properties of a moving person, or even the two-dimensional tracking of the person’s limbs need not precede action recognition. q 2003 Elsevier Science B.V. All rights reserved. Keywords: Motion recognition; Human tracking; Articulated motion 1. Introduction Recognition of human actions from video streams has many applications in the surveillance, entertainment, user interfaces, sports and video annotation domains. Given a number of pre-defined actions, the problem can be stated as that of classifying a new action into one of these actions. Normally, the set of actions has a meaning in a certain domain. In sign language, for example, the set of actions corresponds to the set of possible words and letters that can be produced. In ballet, the actions are the step names in one of the ballet notation languages. In psychophysics, the study of human body motion perception by the human visual sys