Authors:
Zhixin Guo
;
Wenzhi Liao
;
Peter Veelaert
and
Wilfried Philips
Affiliation:
Ghent University-IMEC, Belgium
Keyword(s):
Pedestrian Detection, Occlusion Handling, Adaboost, Integral Channel Features.
Related
Ontology
Subjects/Areas/Topics:
Feature Selection and Extraction
;
Pattern Recognition
;
Theory and Methods
Abstract:
Pedestrian detection has achieved a remarkable progress in recent years, but challenges remain especially when
occlusion happens. Intuitively, occluded pedestrian samples contain some characteristic occlusion appearance
features that can help to improve detection. However, we have observed that most existing approaches intentionally
avoid using samples of occluded pedestrians during the training stage. This is because such samples
will introduce unreliable information, which affects the learning of model parameters and thus results in dramatic
performance decline. In this paper, we propose a new framework for pedestrian detection. The proposed
method exploits the use of occluded pedestrian samples to learn more robust features for discriminating pedestrians,
and enables better performances on pedestrian detection, especially for the occluded pedestrians (which
always happens in many real applications). Compared to some recent detectors on Caltech Pedestrian dataset,
with our
proposed method, detection miss rate for occluded pedestrians are significantly reduced.
(More)