发表机构
School of Computer Science and Engineering, University of Electronic Science and Technology of China; Sustainability X-Lab, The University of Hong Kong; School of Architecture, Building, and Civil Engineering, Loughborough University; Department of Engineering Science, University of Oxford; Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（电子科技大学计算机科学与工程学院; 香港大学可持续发展X实验室; 拉夫堡大学建筑、建造与土木工程学院; 牛津大学工程科学系; 香港科技大学土木与环境工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低光照无人机桥梁图像缺陷模糊问题，提出DaL-MoE退化感知混合专家恢复前端，提升了YOLOv11m的桥梁损伤检测精度，实现了合成退化到真实场景的性能迁移。
AI 中文摘要
不良光照会模糊无人机桥梁图像中微小、低对比度的缺陷，降低自动检测的可靠性与操作灵活性。本文探究退化感知图像恢复是否能提升低光照条件下的桥梁损伤检测性能，并实现从合成退化到真实检测场景的迁移。我们提出DaL-MoE，一种与检测器无关的恢复前端，采用感知ISP的低光照合成流水线训练，配备退化感知引导估计及用于降噪、色彩调整和结构细节恢复的互补专家。在配对合成数据上，DaL-MoE取得23.12dB的峰值信噪比（PSNR）和0.8482的结构相似性（SSIM），使YOLOv11m的边界框平均精度（box mAP50）从0.3097提升至0.4923，掩码平均精度（mask mAP50）从0.2281提升至0.3529。在无配对正常光照参考的真实低光照无人机图像上，仿真到真实的评估显示，与直接对原始低光照输入推理相比，缺陷可见性提升，检测结果更完整。未来工作将开发低光照感知的桥梁损伤检测器，使其在桥梁站点、成像条件和光照水平间具备更强的跨场景泛化能力。
英文摘要
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.
Comments31 pages, 9 figures
