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.
@article{arxiv.1904.03629,
title = {Adaptive NMS: Refining Pedestrian Detection in a Crowd},
author = {Songtao Liu and Di Huang and Yunhong Wang},
journal= {arXiv preprint arXiv:1904.03629},
year = {2019}
}