Detection in Crowded Scenes: One Proposal, Multiple Predictions
This addresses the challenge of object detection in crowded environments for computer vision applications, representing a novel method for a known bottleneck.
The paper tackles the problem of detecting highly-overlapped objects in crowded scenes by proposing a detector where each proposal predicts multiple correlated instances, resulting in 4.9% AP gains on CrowdHuman and 1.0% MR^{-2} improvements on CityPersons.
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.