The Community for Technology Leaders
Computer Vision, IEEE International Conference on (2007)
Rio de Janeiro, Brazil
Oct. 14, 2007 to Oct. 21, 2007
ISBN: 978-1-4244-1630-1
pp: 1-8
Zhe Lin , Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. zhelin@umiacs.umd.edu
Larry S. Davis , Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. lsd@umiacs.umd.edu
David Doermann , Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. doermann@umiacs.umd.edu
Daniel DeMenthon , Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. daniel@umiacs.umd.edu
ABSTRACT
An interactive human segmentation approach is described. Given regions of interest provided by users, the approach iteratively estimates segmentation via a generalized EM algorithm. Specifically, it encodes both spatial and color information in a nonparametric kernel density estimator, and incorporates local MRF constraints and global pose inferences to propagate beliefs over image space iteratively to determine a coherent segmentation. This ensures the segmented humans resemble the shapes of human poses. Additionally, a layered occlusion model and a probabilistic occlusion reasoning method are proposed to handle segmentation of multiple humans in occlusion. The approach is tested on a wide variety of images containing single or multiple occluded humans, and the segmentation performance is evaluated quantitatively.
INDEX TERMS
CITATION

D. Doermann, L. S. Davis, D. DeMenthon and Z. Lin, "An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans," 2007 11th IEEE International Conference on Computer Vision(ICCV), Rio de Janeiro, 2007, pp. 1-8.
doi:10.1109/ICCV.2007.4409123
97 ms
(Ver 3.3 (11022016))