Sciweavers

Share
ISVC
2009
Springer

Motion-Based View-Invariant Articulated Motion Detection and Pose Estimation Using Sparse Point Features

8 years 9 months ago
Motion-Based View-Invariant Articulated Motion Detection and Pose Estimation Using Sparse Point Features
Abstract. We present an approach for articulated motion detection and pose estimation that uses only motion information. To estimate the pose and viewpoint we introduce a novel motion descriptor that computes the spatial relationships of motion vectors representing various parts of the person using the trajectories of a number of sparse points. A nearest neighbor search for the closest motion descriptor from the labeled training data of human walking poses in multiple views is performed. This observational probability is fed to a Hidden Markov Model defined over multiple poses and viewpoints to obtain temporally consistent pose estimates. Experimental results on various sequences of walking subjects with multiple viewpoints demonstrate the effectiveness of the approach. In particular, our purely motion-based approach is able to track people even when other visible cues are not available, such as in low-light situations. 1 Motivation for Articulated Human Motion Analysis The detection ...
Shrinivas J. Pundlik, Stanley T. Birchfield
Added 26 May 2010
Updated 26 May 2010
Type Conference
Year 2009
Where ISVC
Authors Shrinivas J. Pundlik, Stanley T. Birchfield
Comments (0)
books