An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans

TitleAn Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans
Publication TypeConference Papers
Year of Publication2007
AuthorsLin Z, Davis LS, Doermann D, DeMenthon D
Conference NameComputer Vision, 2007. ICCV 2007. IEEE 11th International Conference on
Date Published2007/10//
Keywordsalgorithm;appearance-based, algorithm;hidden, approach;layered, density, EM, Estimation, estimation;, estimator;pose-assisted, feature, human, Kernel, mechanisms;pose, method;expectation-maximisation, model;nonparametric, occlusion, reasoning, removal;image, segmentation;inference, segmentation;interactive, segmentation;probabilistic

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.