Open Access

Viewpoint Manifolds for Action Recognition

EURASIP Journal on Image and Video Processing20092009:738702

https://doi.org/10.1155/2009/738702

Received: 1 February 2009

Accepted: 30 June 2009

Published: 22 September 2009

Abstract

Action recognition from video is a problem that has many important applications to human motion analysis. In real-world settings, the viewpoint of the camera cannot always be fixed relative to the subject, so view-invariant action recognition methods are needed. Previous view-invariant methods use multiple cameras in both the training and testing phases of action recognition or require storing many examples of a single action from multiple viewpoints. In this paper, we present a framework for learning a compact representation of primitive actions (e.g., walk, punch, kick, sit) that can be used for video obtained from a single camera for simultaneous action recognition and viewpoint estimation. Using our method, which models the low-dimensional structure of these actions relative to viewpoint, we show recognition rates on a publicly available dataset previously only achieved using multiple simultaneous views.

Publisher note

To access the full article, please see PDF.

Authors’ Affiliations

(1)
Department of Computer Science, University of North Carolina at Charlotte

Copyright

© R. Souvenir and K. Parrigan. 2009

This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.