基于遗传算法的阈值图像分割方法在隧道渗漏检测中的应用与分析  

Application and analysis of image segmentation threshold method based on genetic algorithm in tunnel leakage detection

作　　者：凌雅婷 姚连璧[1,2] 孙海丽 Ling Yating;Yao Lianbi;Sun Haili(Urban Mobility Institute,Tongji University,Shanghai 200092,China;College of Surveying and Geo-Informatics,Tongji University,Shanghai 200092,China;College of Resource Environment and Tourism,Capital Normal University,Beijing 100048,China)

机构地区：[1]同济大学城市交通研究院,上海200092 [2]同济大学测绘与地理信息学院,上海200092 [3]首都师范大学资源环境与旅游学院,北京100048

出　　处：《工程勘察》2025年第2期55-60,共6页Geotechnical Investigation & Surveying

基　　金：国家自然科学基金资助(42474053).

摘　　要：本文提出一种结合遗传算法的图像阈值分割方法,用于检测与分析隧道中的渗漏水病害。首先对隧道的激光扫描强度图像进行灰度分布特征分析处理,并根据图像特征对图像进行去噪以及灰度统一处理;其次设置适应度指标,并结合遗传算法对隧道图像进行阈值分割;最后使用西南某大城市地铁隧道的激光扫描图像进行渗漏水病害的检测与分割方法验证。实验结果表明,本文所提出的图像分割算法能够较为准确地进行隧道渗漏病害检测与分析,可为隧道结构安全分析提供支撑。In this paper,an image threshold segmentation method combined with a genetic algorithm is proposed to detect and analyze the water leakage in a tunnel.Firstly,the laser scanning intensity image of the tunnel is analyzed and processed according to the gray distribution characteristics,and then the image is denoised and processed uniformly according to the gray distribution characteristics of the tunnel image.Secondly,the corresponding fitness index is set according to the distribution characteristics of the processed image,and the threshold segmentation of the tunnel strength image obtained through the study is performed by using genetic algorithm.Finally,the laser scanning image data of a subway tunnel in a large city in southwest China is used to verify and analyze the proposed method of leakage disease segmentation.The experimental results show that the proposed image segmentation algorithm can detect and analyze tunnel leakage more accurately,which provides support for the safety analysis of tunnel structure.

关 键 词：图像分割 数字图像处理 遗传算法 移动激光扫描图像 

分 类 号：U456[建筑科学—桥梁与隧道工程]