跳到主要导航 跳到搜索 跳到主要内容

面 向 铁 路 扣 件 的 多 尺 度 结 构 感 知 低 照 度图像增强方法

  • Siwei Ma
  • , Henan Hu
  • , Ronghua Li*
  • *此作品的通讯作者
  • Dalian Jiaotong University

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

To address insufficient image brightness,blurred edges,and poor distinguishability of key struc⁃ tures caused by inadequate tunnel illumination,uneven supplementary lighting,and local shadows in vehi⁃ cle-mounted railway fastener detection,a Multi-Scale Structure-Aware Network(MSA-Net)was pro⁃ posed for low-light image enhancement. Built upon the Self-Calibrated Illumination (SCI) network,MSA-Net employed a Multi-Scale Feature Extraction Module(MSFE)to extract illumination,texture,and edge information under different receptive fields,a Structure-Sensing Attention Module(SSA)to strengthen the responses of bolt contours,clip textures,and fastener boundaries,and an Adaptive Residu⁃ al Fusion Module(ARF)to dynamically adjust the enhancement intensity according to regional degrada⁃ tion levels. Ablation studies,algorithm comparisons,and downstream detection experiments were con⁃ ducted on a low-light railway fastener image dataset collected from the Fuzhou Binhai Express Line. The results show that MSA-Net achieves a standard deviation,average gradient,information entropy,Natural Image Quality Evaluator,and Blind/Referenceless Image Spatial Quality Evaluator of 46. 39,30. 49,4. 88,21. 36,and 26. 34,respectively. The model contains 0. 016 M parameters,requires 9. 782 GFLOPs,and achieves an enhancement speed of 302. 39 FPS. For the YOLOv8 detector trained on nor⁃ mal-light images,the Precision,Recall,mAP@0. 5,and mAP@0. 5:0. 95 obtained using MSA-Net-en⁃ hanced images reach 86. 10%,83. 60%,85. 80%,and 59. 00%,respectively,with an end-to-end pro⁃ cessing speed of 99. 02 FPS. For the detector trained on original low-light images,the corresponding four metrics reach 88. 10%,85. 40%,88. 60%,and 61. 80%,respectively. Experiments on two public low-light image datasets further demonstrate the adaptability of the proposed method to different scenes. MSA-Net improves low-light railway fastener image quality and structural distinguishability while maintaining re⁃ al-time processing efficiency,thereby providing stable image inputs for vehicle-mounted railway fastener detection.

投稿的翻译标题Multi-scale structure-aware low-light image enhancement method for railway fasteners
源语言繁体中文
页(从-至)2936-2958
页数23
期刊Guangxue Jingmi Gongcheng/Optics and Precision Engineering
卷34
期18
DOI
出版状态已出版 - 9月 2026
已对外发布是

关键词

  • adaptive residual fusion
  • low-light image enhancement
  • multi-scale feature extraction
  • railway fasteners
  • structure-sensing attention

学术指纹

探究 '面 向 铁 路 扣 件 的 多 尺 度 结 构 感 知 低 照 度图像增强方法' 的科研主题。它们共同构成独一无二的学术指纹。

引用此