Hierarchical Part-Template Matching for Human Detection and Segmentation

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Lin, Davis, L.S., Doermann, D., DeMenthon, D.
Format: Conference Proceeding
Language:eng ; jpn
Subjects:
Assembly
Bayesian methods
Detectors
Humans
Image edge detection
Image generation
Image segmentation
Object detection
Robustness
Shape
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2007.4408975