Quasi-Invariants for Human Action Representation and Recognition

11 years 5 months ago
Quasi-Invariants for Human Action Representation and Recognition
Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an approach to detect human action with a high tolerance to viewpoint change. Canonical body poses are modeled in a view invariant manner to enable detection from a general viewpoint. While there exist no invariants for 3D to 2D projection, there exists a wealth of techniques in 2D invariance that can be used to advantage in 3D to 2D projection. We employ 2D invariants to recognize canonical poses of the human body leading to an effective way to represent and recognize human action which we evaluate theoretically and experimentally on 2D projections of publicly available human motion capture data.
Vasu Parameswaran, Rama Chellappa
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2002
Where ICPR
Authors Vasu Parameswaran, Rama Chellappa
Comments (0)