Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment

TL;DR

This paper introduces a part-level CNN approach for pedestrian detection that leverages saliency and boundary box alignment to improve accuracy and address common detection challenges like occlusion and proposal shift.

Contribution

It proposes a novel CNN architecture with detection and alignment sub-networks using saliency and bounding box alignment to enhance pedestrian detection performance.

Findings

Significant accuracy improvement over state-of-the-art methods

Effective recall of lost body parts in detection

Outperforms existing methods in log average miss rate

Abstract

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).