Automatic Sensing and Detection for Subway Tunnel Pathologies
作者机构:School of Geomatics and Urban Spatial InformaticsBeijing University of Civil Engineering and ArchitectureBeijing 102616China
出 版 物:《Journal of World Architecture》 (世界建筑(百图))
年 卷 期:2024年第8卷第1期
页 面:54-62页
学科分类:08[工学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Visual detection Neural network Health monitoring Image segmentation Water leakage Subway tunnel.
摘 要:Subway tunnels often suffer from surface pathologies such as cracks,corrosion,fractures,peeling,water and sand infiltration,and sudden hazards caused by foreign object *** a mobile visual pathology sensing system at the front end of operating trains is a critical measure to ensure subway *** leakage as the typical pathology,a tunnel pathology automatic visual detection method based on Deeplabv3+(ASTPDS)was proposed to achieve automatic and high-precision detection and pixel-level morphology extraction of *** with similar methods,this approach showed significant advantages and achieved a detection accuracy of 93.12%,surpassing FCN and ***,it also exceeded the recall rates for detecting leaks of FCN and U-Net by 8.33%and 8.19%,respectively.