Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ICCV.2007.4408975 | ICCV |
Keywords | Field | DocType |
shape articulations,image matching,video sequences,partial occlusions,hierarchical part-template matching,human segmentation,bayes methods,image segmentation,bayesian map framework,fine occlusion analysis,global shape template-based human detectors,local part-based human detectors,global likelihood re-evaluation,image sequences,background subtraction,bayesian approach,human detection,template matching | Background subtraction,Template matching,Computer vision,Market segmentation,Pattern recognition,Computer science,Segmentation,Image matching,Image segmentation,Artificial intelligence,Detector,Bayesian probability | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1550-5499 E-ISBN : 978-1-4244-1631-8 |
ISBN | Citations | PageRank |
978-1-4244-1631-8 | 94 | 3.10 |
References | Authors | |
18 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhe Lin | 1 | 3100 | 134.26 |
| Larry S. Davis | 2 | 14201 | 2690.83 |
| David Doermann | 3 | 4313 | 312.70 |
| Daniel Dementhon | 4 | 1327 | 139.94 |