Discriminative Feature Transformation for Occluded Pedestrian Detection

Chunluan Zhou, Ming Yang, Junsong Yuan; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 9557-9566

Abstract


Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded pedes- trian examples, it is generally more difficult to distinguish occluded pedestrian examples from background in featue space due to the missing of occluded parts. In this paper, we propose a discriminative feature transformation which en- forces feature separability of pedestrian and non-pedestrian examples to handle occlusions for pedestrian detection. Specifically, in feature space it makes pedestrian exam- ples approach the centroid of easily classified non-occluded pedestrian examples and pushes non-pedestrian examples close to the centroid of easily classified non-pedestrian ex- amples. Such a feature transformation partially compen- sates the missing contribution of occluded parts in feature space, therefore improving the performance for occluded pedestrian detection. We implement our approach in the Fast R-CNN framework by adding one transformation net- work branch. We validate the proposed approach on two widely used pedestrian detection datasets: Caltech and CityPersons. Experimental results show that our approach achieves promising performance for both non-occluded and occluded pedestrian detection.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhou_2019_ICCV,
author = {Zhou, Chunluan and Yang, Ming and Yuan, Junsong},
title = {Discriminative Feature Transformation for Occluded Pedestrian Detection},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}