PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection
This work improves road safety by enhancing pedestrian detection in complex scenarios, though it is incremental as it builds on existing multispectral methods.
The paper tackled pedestrian detection in intelligent transportation systems by addressing insufficient fusion of visible and infrared spectra and sensitivity to illumination changes, resulting in a state-of-the-art performance with a 6.6% improvement in mAP on datasets like LLVIP and MSDS.
Pedestrian detection in intelligent transportation systems has made significant progress but faces two critical challenges: (1) insufficient fusion of complementary information between visible and infrared spectra, particularly in complex scenarios, and (2) sensitivity to illumination changes, such as low-light or overexposed conditions, leading to degraded performance. To address these issues, we propose PedDet, an adaptive spectral optimization complementarity framework specifically enhanced and optimized for multispectral pedestrian detection. PedDet introduces the Multi-scale Spectral Feature Perception Module (MSFPM) to adaptively fuse visible and infrared features, enhancing robustness and flexibility in feature extraction. Additionally, the Illumination Robustness Feature Decoupling Module (IRFDM) improves detection stability under varying lighting by decoupling pedestrian and background features. We further design a contrastive alignment to enhance intermodal feature discrimination. Experiments on LLVIP and MSDS datasets demonstrate that PedDet achieves state-of-the-art performance, improving the mAP by 6.6% with superior detection accuracy even in low-light conditions, marking a significant step forward for road safety. Code will be available at https://github.com/AIGeeksGroup/PedDet.