Detection in Crowded Scenes: One Proposal, Multiple Predictions

TL;DR

This paper introduces a proposal-based object detection method tailored for crowded scenes, allowing each proposal to predict multiple correlated instances, significantly improving detection accuracy in highly-overlapped scenarios.

Contribution

It presents a novel detection framework with EMD Loss and Set NMS that effectively detects overlapping objects, outperforming previous methods on crowded datasets.

Findings

4.9% AP improvement on CrowdHuman dataset

1.0% MR^-2 improvement on CityPersons dataset

Moderate gains on less crowded datasets like COCO

Abstract

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9\% AP gains on challenging CrowdHuman dataset and 1.0\% $\text{MR}^{-2}$ improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at https://github.com/megvii-model/CrowdDetection.