Adaptive NMS: Refining Pedestrian Detection in a Crowd
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
Datasets
ssd
CrowdHuman
CityPersons
Methods
1x1 Convolution •
Adaptive NMS •
Convolution •
Dense Connections •
Dropout •
Faster R-CNN •
FPN •
Max Pooling •
ReLU •
RoIPool •
RPN •
SGD with Momentum •
Softmax •
Step Decay •
VGG •
Weight Decay
