Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
This addresses pedestrian detection for video surveillance or autonomous driving, but it appears incremental as it builds on existing CNNs with specific enhancements.
The paper tackles pedestrian detection challenges like varied appearances and proposal shift by proposing part-level CNNs with saliency and boundary box alignment, achieving improved accuracy and outperforming state-of-the-art methods in log average miss rate.
Pedestrians in videos have a wide range of appearances such as body poses, occlusions, and complex backgrounds, and there exists the proposal shift problem in pedestrian detection that causes the loss of body parts such as head and legs. To address it, we propose part-level convolutional neural networks (CNN) for pedestrian detection using saliency and boundary box alignment in this paper. The proposed network consists of two sub-networks: detection and alignment. We use saliency in the detection sub-network to remove false positives such as lamp posts and trees. We adopt bounding box alignment on detection proposals in the alignment sub-network to address the proposal shift problem. First, we combine FCN and CAM to extract deep features for pedestrian detection. Then, we perform part-level CNN to recall the lost body parts. Experimental results on various datasets demonstrate that the proposed method remarkably improves accuracy in pedestrian detection and outperforms existing state-of-the-arts in terms of log average miss rate at false position per image (FPPI).