An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans
| Title | An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans |
| Publication Type | Conference Papers |
| Year of Publication | 2007 |
| Authors | Lin Z, Davis LS, Doermann D, DeMenthon D |
| Conference Name | Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on |
| Date Published | 2007/10// |
| Keywords | algorithm;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 |
| 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. |
| DOI | 10.1109/ICCV.2007.4409123 |