Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
This work addresses pedestrian detection for autonomous driving and surveillance, but it is incremental as it builds on existing deep learning methods with specific architectural improvements.
The paper tackled robust pedestrian detection under size variation and occlusion by proposing a gated multi-layer convolutional feature extraction network, achieving effectiveness on the CityPersons dataset, particularly for small and occluded pedestrians.
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging problem. In this paper, we propose a gated multi-layer convolutional feature extraction method which can adaptively generate discriminative features for candidate pedestrian regions. The proposed gated feature extraction framework consists of squeeze units, gate units and a concatenation layer which perform feature dimension squeezing, feature elements manipulation and convolutional features combination from multiple CNN layers, respectively. We proposed two different gate models which can manipulate the regional feature maps in a channel-wise selection manner and a spatial-wise selection manner, respectively. Experiments on the challenging CityPersons dataset demonstrate the effectiveness of the proposed method, especially on detecting those small-size and occluded pedestrians.