29 January 2007 Bayesian distributed articulated object tracking using multiple collaborative trackers
Author Affiliations +
Proceedings Volume 6508, Visual Communications and Image Processing 2007; 65080K (2007); doi: 10.1117/12.701983
Event: Electronic Imaging 2007, 2007, San Jose, CA, United States
Abstract
In this paper, we propose two novel articulated object tracking approaches. The Decentralized Articulated Object Tracking approach avoids the common practice of using a high-dimensional joint state representation for articulated object tracking. Instead, it introduces a decentralized scheme and models the inter-part interaction within an innovative Bayesian framework. To handle severe self-occlusions, we further extend the first approach by modeling high-level inter-unit interactions and develop the Hierarchical Articulated Object Tracking algorithm within a consistent hierarchical framework. Preliminary experimental results have demonstrated the superior performance of the proposed approaches for real-world videos sequences.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Qu, Dan Schonfeld, "Bayesian distributed articulated object tracking using multiple collaborative trackers", Proc. SPIE 6508, Visual Communications and Image Processing 2007, 65080K (29 January 2007); doi: 10.1117/12.701983; https://doi.org/10.1117/12.701983
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Motion models

Detection and tracking algorithms

3D modeling

Video

Algorithm development

Expectation maximization algorithms

Systems modeling

Back to Top