Occlusion-robust Detector Trained with Occluded Pedestrians

Zhixin Guo, Wenzhi Liao, Peter Veelaert, Wilfried Philips

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.

References

Download


Paper Citation


in Harvard Style

Guo Z., Liao W., Veelaert P. and Philips W. (2018). Occlusion-robust Detector Trained with Occluded Pedestrians.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 86-94. DOI: 10.5220/0006569200860094


in Bibtex Style

@conference{icpram18,
author={Zhixin Guo and Wenzhi Liao and Peter Veelaert and Wilfried Philips},
title={Occlusion-robust Detector Trained with Occluded Pedestrians},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={86-94},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006569200860094},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Occlusion-robust Detector Trained with Occluded Pedestrians
SN - 978-989-758-276-9
AU - Guo Z.
AU - Liao W.
AU - Veelaert P.
AU - Philips W.
PY - 2018
SP - 86
EP - 94
DO - 10.5220/0006569200860094