Feature Calibration Network for Occluded Pedestrian Detection
This addresses the problem of occluded pedestrian detection for autonomous driving and surveillance systems, presenting an incremental improvement with a novel feature learning method.
The paper tackled pedestrian detection under occlusion by proposing a Feature Calibration Network (FC-Net), which improved detection performance on occluded pedestrians by up to 10% on CityPersons and Caltech datasets while maintaining performance on non-occluded instances.
Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions. FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module. In a new self-activated manner, FC-Net learns features which highlight the visible parts and suppress the occluded parts of pedestrians. The SA module estimates pedestrian activation maps by reusing classifier weights, without any additional parameter involved, therefore resulting in an extremely parsimony model to reinforce the semantics of features, while the FC module calibrates the convolutional features for adaptive pedestrian representation in both pixel-wise and region-based ways. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10% while maintaining excellent performance on non-occluded instances.