Hand Tracking by Fusion of Color and a Range Sensor
Loading...
Date
Author
Institution
http://id.loc.gov/authorities/names/n79058482
Degree Level
Master's
Degree
Master of Science
Department
Department of Computing Science
Supervisor / Co-Supervisor and Their Department(s)
Examining Committee Member(s) and Their Department(s)
Citation for Previous Publication
Link to Related Item
Abstract
In this work we have developed a decentralized algorithm for efficient localization and tracking of hands from a sequence of depth and colour images. We deduce the location of key-points using a Bayesian framework. We use anthropomorphic constraints for modelling the interaction between body-parts.Furthermore, we incorporate an occlusion reasoning and data association preservation procedure for dealing with ambiguities. Our work is adaptive to illumination changes despite utilizing the skin-color information for tracking. Experimental results demonstrate that our system produces more accurate tracking of the head and hands in video, compared to prior research.
Item Type
http://purl.org/coar/resource_type/c_46ec
Alternative
License
Other License Text / Link
This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
Subject/Keywords
Language
en