Adaptive NMS: Refining pedestrian detection in a crowd

作     者：Liu, Songtao Huang, Di Wang, Yunhong 

作者机构：Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2019年

核心收录：

主　　题：Machine learning 

摘      要：Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum 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. Copyright © 2019, The Authors. All rights reserved.