Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning

TL;DR

This paper introduces a novel foreground-background contrast learning approach for nighttime pedestrian detection, enhancing channel attention mechanisms by incorporating background information to improve detection accuracy under low-light conditions.

Contribution

The paper proposes the Fore-Background Contrast Attention (FBCA), a new method that integrates background information into channel attention for better nighttime pedestrian detection.

Findings

FBCA outperforms existing methods on NightOwls and TJU-DHD datasets.

The approach improves detection performance on multispectral LLVIP dataset.

Incorporating background information enhances semantic and spatial accuracy of channel descriptors.

Abstract

The significance of background information is frequently overlooked in contemporary research concerning channel attention mechanisms. This study addresses the issue of suboptimal single-spectral nighttime pedestrian detection performance under low-light conditions by incorporating background information into the channel attention mechanism. Despite numerous studies focusing on the development of efficient channel attention mechanisms, the relevance of background information has been largely disregarded. By adopting a contrast learning approach, we reexamine channel attention with regard to pedestrian objects and background information for nighttime pedestrian detection, resulting in the proposed Fore-Background Contrast Attention (FBCA). FBCA possesses two primary attributes: (1) channel descriptors form remote dependencies with global spatial feature information; (2) the integration of background information enhances the distinction between channels concentrating on low-light pedestrian features and those focusing on background information. Consequently, the acquired channel descriptors exhibit a higher semantic level and spatial accuracy. Experimental outcomes demonstrate that FBCA significantly outperforms existing methods in single-spectral nighttime pedestrian detection, achieving state-of-the-art results on the NightOwls and TJU-DHD-pedestrian datasets. Furthermore, this methodology also yields performance improvements for the multispectral LLVIP dataset. These findings indicate that integrating background information into the channel attention mechanism effectively mitigates detector performance degradation caused by illumination factors in nighttime scenarios.