Classifying human actions using an incomplete real-time pose skeleton
Peursum, Patrick, Bui, Hung H., Venkatesh, Svetha and West, Geoff 2004, Classifying human actions using an incomplete real-time pose skeleton. In Zhang, Chengqi, Guesgen, Hans W. and Yeap, Wai K. (ed), PRICAI 2004 : trends in artificial intelligence : 8th Pacific Rim International Conference on Artificial Intelligence, Auckland, New Zealand, August 9-13, 2004 : proceedings, Springer-Verlag, Berlin, Germany, pp.971-972, doi: 10.1007/978-3-540-28633-2_119.
Attached Files
Name
Description
MIMEType
Size
Downloads
Title
Classifying human actions using an incomplete real-time pose skeleton
PRICAI 2004 : trends in artificial intelligence : 8th Pacific Rim International Conference on Artificial Intelligence, Auckland, New Zealand, August 9-13, 2004 : proceedings
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.
Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.