• CSCD核心中文核心科技核心
  • RCCSE(A+)公路运输高质量期刊T1
  • Ei CompendexScopusWJCI
  • EBSCOPж(AJ)JST
二维码

隧道建设（中英文） ›› 2024, Vol. 44 ›› Issue (10): 1971-1981.DOI: 10.3973/j.issn.2096-4498.2024.10.006

• 结构病害诊治与韧性提升专题 • 上一篇    下一篇

基于全景展开图像的水工隧洞渗水侵蚀病害快速检测方法研究

傅金阳1， 2， 王浩宇1， 谢纪辰1， 祝志恒1， 张聪3， 伍军4   

  1. （1. 中南大学土木工程学院， 湖南 长沙 410075； 2. 高速铁路建造技术国家工程研究中心， 湖南 长沙 410075； 3. 中南林业科技大学土木工程学院， 湖南 长沙 410075； 4. 中国中铁股份有限公司， 北京 100036）
  • 出版日期:2024-10-20 发布日期:2024-11-12
  • 作者简介:傅金阳（1985—），男，湖南湘潭人，2014年毕业于德国弗莱贝格工业大学，岩土工程专业，博士，副教授，主要从事基础设施灾变机制及智能检测技术研究工作。E-mail： jy.fu@csu.edu.cn。

Rapid Detection Methods for Seepage and Erosion Diseases in Hydraulic Tunnels Using Panoramic Image

FU Jinyang1, 2, WANG Haoyu1, XIE Jichen1, ZHU Zhiheng1, ZHANG Cong3, WU Jun4   

  1. (1. School of Civil Engineering, Central South University, Changsha 410075, Hunan, China; 2. National Engineering Research Center of High-speed Railway Construction Technology, Changsha 410075, Hunan, China; 3. School of Civil Engineering, Central South University of Forest and Technology, Changsha 410075, Hunan, China; 4. China Railway Group Limited, Beijing 100036, China)
  • Online:2024-10-20 Published:2024-11-12

PDF

87

摘要： 为解决水工隧洞尺寸较小、断面形式多变、洞内环境复杂、无信号覆盖给检测图像快速采集带来的难题，研制出一种无信号覆盖下图像实时传输以及适用于不同断面、尺寸下隧洞全断面采集的水工隧洞检测系统，采集重叠率和精度满足三维重建及对自主研发的衬砌展开影像生成器的要求；针对隧洞表观病害传统算法速度慢、精度低等问题，引入DenseNet主干网络和ECA注意力机制对YOLOv5检测算法进行改进，优化特征提取能力；针对单张图像识别难以反映病害整体分布、全景展开图尺寸过大网络难以捕获有效特征等问题，以全景展开图底层图像为种子点，利用方向搜索结合目标检测算法提出一种“段-环-点”的隧洞常见表观病害快速识别算法。现场应用表明： 1）相比YOLOv7-tiny、YOLOv8、YOLOv9等模型，改进的YOLOv5模型在mAP和F1上均有明显提高，可有效提升复杂背景下病害识别与边界定位精度，显著减少误检和漏检现象； 2）所提技术适用于圆涵、箱涵等不同类型、尺寸的水工隧洞表观图像快速获取与全景识别，能够用于隧洞表观病害的展示和快速定位，可为病害整治措施的及时制定提供依据。

关键词: 水工隧洞, 图像采集, 全景展开图拼接, 快速检测, 精确定位, YOLOv5检测算法, DenseNet主干网络

Abstract: Challenges posed by hydraulic tunnels, such as confined space, varying cross-sections, complex environments, and lack of signal, hinder rapid image acquisition. To address these challenges, a rapid image acquisition system that can capture cross-sectional images of the tunnel while traveling in a short period is presented. This system can capture images under different cross-sectional shapes and sizes and meets the acquisition overlap rate and accuracy requirements of three-dimensional reconstruction and image generator for lining expansion. To enhance the speed and accuracy of the traditional algorithms, the YOLOv5 detection algorithm is improved using a DenseNet network and an efficient channel attention module, thereby enhancing the effectiveness of feature extraction. In addition, a "segment-ring-point" method is proposed for the efficient identification of common surface defects on tunnel linings using panoramic images, with the bottom image of the panorama serving as the seed point. This approach addresses the limitations of single images that fail to reflect the overall distribution of the damage and large images that do not capture the effective features of the network. Field applications demonstrate the following: (1) The improved YOLOv5 model significantly improves the mean average precision and F1 performances compared with YOLOv7-tiny, YOLOv8, and YOLOv9 models, effectively improving the accuracy of defect identification and boundary positioning in complex environments and substantially reducing the occurrence of false positives and missed detections. (2) This approach is suitable for rapid acquisition and panoramic image stitching in hydraulic tunnels with diverse cross-sectional shapes and sizes. It can also be used for identifying and locating surface diseases promptly in tunnels to provide defect treatment measures.

Key words: hydraulic tunnels, image acquisition, panorama image, rapid detection, accurate localization, YOLOv5, DenseNet

主办单位：中铁隧道勘察设计研究院有限公司    主管单位：中铁隧道局集团有限公司

本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn

粤ICP备19038941号