DMCA
A Discriminative Deep Model for Pedestrian Detection with Occlusion Handling (2012)
| Venue: | In Proc. CVPR |
| Citations: | 18 - 12 self |
BibTeX
@INPROCEEDINGS{Ouyang12adiscriminative,
author = {Wanli Ouyang and Xiaogang Wang},
title = {A Discriminative Deep Model for Pedestrian Detection with Occlusion Handling},
booktitle = {In Proc. CVPR},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Part-based models have demonstrated their merit in ob-ject detection. However, there is a key issue to be solved on how to integrate the inaccurate scores of part detectors when there are occlusions or large deformations. To han-dle the imperfectness of part detectors, this paper presents a probabilistic pedestrian detection framework. In this frame-work, a deformable part-based model is used to obtain the scores of part detectors and the visibilities of parts are mod-eled as hidden variables. Unlike previous occlusion han-dling approaches that assume independence among visibil-ity probabilities of parts or manually define rules for the visibility relationship, a discriminative deep model is used in this paper for learning the visibility relationship among overlapping parts at multiple layers. Experimental results on three public datasets (Caltech, ETH and Daimler) and a new CUHK occlusion dataset1 specially designed for the evaluation of occlusion handling approaches show the ef-fectiveness of the proposed approach. 1.
Keyphrases
discriminative deep model pedestrian detection part detector visibility relationship define rule key issue hidden variable new cuhk occlusion dataset1 visibil-ity probability probabilistic pedestrian detection framework deformable part-based model part-based model ob-ject detection large deformation public datasets inaccurate score experimental result multiple layer previous occlusion han-dling approach
