Low-Light Pedestrian Detection Toward Nighttime Safety Monitoring in Smart Built Environments: A Frequency-Aware RGB–Infrared Fusion Approach
Chao Zhang, Xingkun Li, Xiangyang Cao · Buildings · 2026
Reliable pedestrian perception under low illumination is important for nighttime monitoring in smart built environments. However, visible-light detectors often lose texture and edge information, whereas conventional RGB–infrared fusion may introduce cross-modal noise and discard discriminative cues during scale conversion. This study proposes Multimodal Wavelet–Spectral DETR (MWSD), a frequency-aware RGB–infrared detection framework. MWSD employs a dual-branch Multimodal Fusion Feature Sampling backbone for cross-modal interaction. The Multimodal Frequency-Domain Feature Enhancement (MFFE) module produces input-dependent Fourier modulation within shared detection features, rather than reconstructing a fused image or independently fusing modality-specific spectra. Haar wavelet upsampling and downsampling (HWU and HWD) construct a bidirectional feature pyramid by using frequency components to guide adjacent-level scale conversion, rather than performing image-level wavelet reconstruction. This coordinated design combines residual spectral enhancement with wavelet-guided multi-scale fusion in an end-to-end detector. On LLVIP, MWSD achieves 96.7% mAP50 and 63.0% mAP50:95. On M3FD, it achieves 87.1% and 59.0%, respectively. The model requires 45 ms per 640 × 640 image on an NVIDIA RTX 4090 GPU. These results support frequency-aware multimodal detection as a visual perception approach for nighttime safety monitoring.