Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied how poor lighting makes it hard to spot small defects on bridges using drone images. They created a method called DaL-MoE that improves these dark images by reducing noise, fixing colors, and bringing out details, helping detection tools find damage better. Tested on both fake and real low-light images, their method made defects easier to see and detect. They plan to build even better detection systems that work well in different bridge and lighting situations.
low-light image restorationUAV imagerybridge inspectiondegradation-aware restorationYOLO object detectionPSNRSSIMimage synthesisnoise suppressionsim-to-real transfer
Authors
Hu Wang, Hongxu Pu, Zhiqi Hu, Fangzhou Lin, Wang Wang
Abstract
Poor illumination obscures small, low-contrast defects in UAV bridge imagery, reducing the reliability and operational flexibility of automated inspection. This paper investigates whether degradation-aware image restoration can improve bridge damage detection under low-light conditions and transfer from synthetic degradations to real inspection scenes. We propose DaL- MoE, a detector-agnostic restoration front end trained with an ISP-aware low-light synthesis pipeline and equipped with degradation-aware guidance estimation and complementary experts for noise suppression, color adjustment, and structural-detail recovery. On paired synthetic data, DaL-MoE achieves 23.12 dB PSNR and 0.8482 SSIM, increasing YOLOv11m box mAP50 from 0.3097 to 0.4923 and mask mAP50 from 0.2281 to 0.3529. On real low-light UAV imagery without paired normal-light references, sim-to-real evaluation shows improved defect visibility and more complete detections than direct inference on raw low-light inputs. Future work will develop low-light-aware bridge damage detectors with stronger cross-scene generalization across bridge sites, imaging conditions, and illumination levels.