Adaptive NMS: Refining Pedestrian Detection in a Crowd

CVPR 2019  ·  Songtao Liu, Di Huang, Yunhong Wang ·

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 Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection CrowdHuman (full body) Adaptive NMS (Faster RCNN, ResNet50) AP 84.71 # 18
mMR 49.73 # 15

Methods