Beta R-CNN: Looking into Pedestrian Detection from Another Perspective

TL;DR

Beta R-CNN introduces a novel 2D beta distribution-based representation and a new NMS strategy to improve pedestrian detection in occluded and crowded scenes, outperforming traditional bounding box methods.

Contribution

The paper proposes Beta Representation and BetaNMS, along with a new pipeline Beta R-CNN, to enhance detection accuracy in challenging crowded and occluded environments.

Findings

Significantly improves detection in occluded scenes

Better distinguishes overlapping pedestrians

Achieves higher detection accuracy than existing methods

Abstract

Recently significant progress has been made in pedestrian detection, but it remains challenging to achieve high performance in occluded and crowded scenes. It could be attributed mostly to the widely used representation of pedestrians, i.e., 2D axis-aligned bounding box, which just describes the approximate location and size of the object. Bounding box models the object as a uniform distribution within the boundary, making pedestrians indistinguishable in occluded and crowded scenes due to much noise. To eliminate the problem, we propose a novel representation based on 2D beta distribution, named Beta Representation. It pictures a pedestrian by explicitly constructing the relationship between full-body and visible boxes, and emphasizes the center of visual mass by assigning different probability values to pixels. As a result, Beta Representation is much better for distinguishing highly-overlapped instances in crowded scenes with a new NMS strategy named BetaNMS. What's more, to fully exploit Beta Representation, a novel pipeline Beta R-CNN equipped with BetaHead and BetaMask is proposed, leading to high detection performance in occluded and crowded scenes.