TY - CONF T1 - Hierarchical Part-Template Matching for Human Detection and Segmentation 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 - analysis;global KW - approach;background KW - articulations;video KW - Bayesian KW - detection;human KW - detectors;hierarchical KW - detectors;partial KW - framework;Bayesian KW - human KW - likelihood KW - MAP KW - matching;human KW - matching;image KW - methods;image KW - occlusion KW - occlusions;shape KW - part-based KW - part-template KW - re-evaluation;global KW - segmentation;image KW - segmentation;local KW - sequences; KW - sequences;Bayes KW - SHAPE KW - subtraction;fine KW - template-based AB - Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detectors are capable of detecting and segmenting human shapes simultaneously. We describe a Bayesian approach to human detection and segmentation combining local part-based and global template-based schemes. The approach relies on the key ideas of matching a part-template tree to images hierarchically to generate a reliable set of detection hypotheses and optimizing it under a Bayesian MAP framework through global likelihood re-evaluation and fine occlusion analysis. In addition to detection, our approach is able to obtain human shapes and poses simultaneously. We applied the approach to human detection and segmentation in crowded scenes with and without background subtraction. Experimental results show that our approach achieves good performance on images and video sequences with severe occlusion. JA - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on M3 - 10.1109/ICCV.2007.4408975 ER -