TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection

TL;DR

TFDet introduces a target-aware fusion method for RGB-T pedestrian detection, significantly reducing false positives and improving detection accuracy in low-light conditions, with state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a novel target-aware fusion strategy, TFDet, that enhances feature contrast to reduce false positives and achieves superior performance in multispectral pedestrian detection.

Findings

Achieves state-of-the-art results on KAIST and LLVIP benchmarks.

Outperforms previous methods on FLIR and M3FD datasets.

Maintains comparable inference efficiency to existing approaches.

Abstract

Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches have combined thermal images to provide complementary information and have obtained enhanced performances. Nevertheless, few approaches focus on the negative effects of false positives caused by noisy fused feature maps. Different from them, we comprehensively analyze the impacts of false positives on the detection performance and find that enhancing feature contrast can significantly reduce these false positives. In this paper, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet. TFDet achieves state-of-the-art performance on two multispectral pedestrian benchmarks, KAIST and LLVIP. TFDet can easily extend to multi-class object detection scenarios. It outperforms the previous best approaches on two multispectral object detection benchmarks, FLIR and M3FD. Importantly, TFDet has comparable inference efficiency to the previous approaches, and has remarkably good detection performance even under low-light conditions, which is a significant advancement for ensuring road safety.