TY - CONF T1 - An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans T2 - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on Y1 - 2007 A1 - Zhe Lin A1 - Davis, Larry S. A1 - David Doermann A1 - DeMenthon,D. KW - algorithm;appearance-based KW - algorithm;hidden KW - approach;layered KW - density KW - EM KW - Estimation KW - estimation; KW - estimator;pose-assisted KW - feature KW - human KW - Kernel KW - mechanisms;pose KW - method;expectation-maximisation KW - model;nonparametric KW - occlusion KW - reasoning KW - removal;image KW - segmentation;inference KW - segmentation;interactive KW - segmentation;probabilistic AB - 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. JA - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on M3 - 10.1109/ICCV.2007.4409123 ER -