Adaptive NMS: Refining Pedestrian Detection in a Crowd

Songtao Liu, Di Huang, Yunhong Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 6459-6468

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.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Liu_2019_CVPR,
author = {Liu, Songtao and Huang, Di and Wang, Yunhong},
title = {Adaptive NMS: Refining Pedestrian Detection in a Crowd},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}