Currently, most human action recognition systems are trained with feature sets that have no missing data. Unfortunately, the use of human pose estimation models to provide more descriptive features also entails an increased sensitivity to occlusions, meaning that incomplete feature information will be unavoidable for realistic scenarios. To address this, our approach is to shift the responsibility for dealing with occluded pose data away from the pose estimator and onto the action classifier. This allows the use of a simple, real-time pose estimation (stick-figure) that does not estimate the positions of limbs it cannot find quickly. The system tracks people via background subtraction and extracts the (possibly incomplete) pose skeleton from their silhouette. Hidden Markov Models modified to handle missing data are then used to successfully classify several human actions using the incomplete pose features.
History
Chapter number
119
Pagination
971-972
ISSN
0302-9743
ISBN-13
9783540228172
ISBN-10
3540228179
Language
eng
Publication classification
B1.1 Book chapter
Copyright notice
2004, Springer-Verlag Berlin Heidelberg
Extent
142
Editor/Contributor(s)
Zhang C, Guesgen H, Yeap W
Publisher
Springer-Verlag
Place of publication
Berlin, Germany
Title of book
PRICAI 2004 : trends in artificial intelligence : 8th Pacific Rim International Conference on Artificial Intelligence, Auckland, New Zealand, August 9-13, 2004 : proceedings