Repulsion Loss: Detecting Pedestrians in a Crowd

11/21/2017
by   Xinlong Wang, et al.
0

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem. Then, we propose a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss. This loss is driven by two motivations: the attraction by target, and the repulsion by other surrounding objects. The repulsion term prevents the proposal from shifting to surrounding objects thus leading to more crowd-robust localization. Our detector trained by repulsion loss outperforms all the state-of-the-art methods with a significant improvement in occlusion cases.

READ FULL TEXT

page 4

page 8

page 12

page 13

research
07/23/2018

Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd

Pedestrian detection in crowded scenes is a challenging problem since th...
research
09/15/2019

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Pedestrian detection in crowded scenes is a challenging problem, because...
research
06/04/2021

NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection

Non-Maximum Suppression (NMS) is essential for object detection and affe...
research
01/04/2018

Microscopic Travel Time Analysis of Bottleneck Experiments

This contribution provides a microscopic experimental study of pedestria...
research
12/12/2020

DETR for Pedestrian Detection

Pedestrian detection in crowd scenes poses a challenging problem due to ...
research
08/23/2020

Visible Feature Guidance for Crowd Pedestrian Detection

Heavy occlusion and dense gathering in crowd scene make pedestrian detec...
research
04/16/2023

Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads

With the rapid development of deep learning, object detection and tracki...

Please sign up or login with your details

Forgot password? Click here to reset