ML Anthology

Repulsion Loss: Detecting Pedestrians in a Crowd

Xinlong Wang, Tete Xiao, Yuning Jiang, Shuai Shao, Jian Sun, Chunhua Shen
CVPR 2018
doi:10.1109/CVPR.2018.00811 /cvpr/2018/wang2018cvpr-repulsion/

Abstract

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem. Then, we propose a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss. This loss is driven by two motivations: the attraction by target, and the repulsion by other surrounding objects. The repulsion term prevents the proposal from shifting to surrounding objects thus leading to more crowd-robust localization. Our detector trained by repulsion loss outperforms the state-of-the-art methods with a significant improvement in occlusion cases.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Repulsion Loss: Detecting Pedestrians in a Crowd." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00811

Markdown

[Wang et al. "Repulsion Loss: Detecting Pedestrians in a Crowd." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/wang2018cvpr-repulsion/) doi:10.1109/CVPR.2018.00811

BibTeX

@inproceedings{wang2018cvpr-repulsion,
  title     = {{Repulsion Loss: Detecting Pedestrians in a Crowd}},
  author    = {Wang, Xinlong and Xiao, Tete and Jiang, Yuning and Shao, Shuai and Sun, Jian and Shen, Chunhua},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00811},
  url       = {https://mlanthology.org/cvpr/2018/wang2018cvpr-repulsion/}
}