Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild
This work addresses critical challenges in pedestrian detection for applications like surveillance and autonomous driving, representing an incremental improvement over existing methods.
The paper tackles crowd occlusion and hard negatives in pedestrian detection by introducing a coulomb loss for bounding box regression and a semantic-driven anchor selection strategy, achieving consistently high performance on Caltech-USA and CityPersons benchmarks.
Pedestrian detection has been heavily studied in the last decade due to its wide application. Despite incremental progress, crowd occlusion and hard negatives are still challenging current state-of-the-art pedestrian detectors. In this paper, we offer two approaches based on the general region-based detection framework to tackle these challenges. Specifically, to address the occlusion, we design a novel coulomb loss as a regulator on bounding box regression, in which proposals are attracted by their target instance and repelled by the adjacent non-target instances. For hard negatives, we propose an efficient semantic-driven strategy for selecting anchor locations, which can sample informative negative examples at training phase for classification refinement. It is worth noting that these methods can also be applied to general object detection domain, and trainable in an end-to-end manner. We achieves consistently high performance on the Caltech-USA and CityPersons benchmarks.