Share Email Print

Proceedings Paper

Efficient occlusion reasoning for articulated tracking in monocular views
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Pose estimation and tracking of articulated objects like humans is particularly difficult due to the complex occlusions among the articulated parts. Without the benefit of multiple views, resolution of occlusions becomes both increasingly valuable and challenging. We propose a method for articulated 3D pose estimation from monocular video which uses nonparametric belief propagation and employs a novel and efficient approach to occlusion reasoning. We present a human tracking application, and evaluate results using the HumanEva II data set.

Paper Details

Date Published: 14 February 2013
PDF: 10 pages
Proc. SPIE 8657, Computational Imaging XI, 86570L (14 February 2013); doi: 10.1117/12.2012645
Show Author Affiliations
Landis M. Huffman, The MITRE Corp. (United States)
Ilya Pollak, Purdue Univ. (United States)

Published in SPIE Proceedings Vol. 8657:
Computational Imaging XI
Charles A. Bouman; Ilya Pollak; Patrick J. Wolfe, Editor(s)

© SPIE. Terms of Use
Back to Top