ML Anthology

Adaptive NMS: Refining Pedestrian Detection in a Crowd

Songtao Liu, Di Huang, Yunhong Wang
CVPR 2019
doi:10.1109/CVPR.2019.00662 /cvpr/2019/liu2019cvpr-adaptive/

Abstract

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

PDF CVPR Semantic Scholar

Cite

Text

Liu et al. "Adaptive NMS: Refining Pedestrian Detection in a Crowd." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00662

Markdown

[Liu et al. "Adaptive NMS: Refining Pedestrian Detection in a Crowd." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/liu2019cvpr-adaptive/) doi:10.1109/CVPR.2019.00662

BibTeX

@inproceedings{liu2019cvpr-adaptive,
  title     = {{Adaptive NMS: Refining Pedestrian Detection in a Crowd}},
  author    = {Liu, Songtao and Huang, Di and Wang, Yunhong},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00662},
  url       = {https://mlanthology.org/cvpr/2019/liu2019cvpr-adaptive/}
}