文献类型：期刊文献

英文题名：Combining SfM and deep learning to construct 3D point cloud models of shield tunnels and Realize spatial localization of water leakages

作者：Qian, Jinhua[1];Xue, Fei[1];Wang, Tianzuo[1];Lin, Zhongqin[2];Cai, Mingcheng[3];Shou, Feifeng[3]

机构：[1]Shaoxing Univ, Coll Civil Engn, Key Lab Rock Mech & Geohazards Zhejiang Prov, Shaoxing 312000, Peoples R China;[2]Fuzhou Univ, Coll Civil Engn, Fuzhou 350108, Peoples R China;[3]Shaoxing Commun Holding Grp Co Ltd, Shaoxing 312000, Peoples R China

年份：2025

卷号：250

外文期刊名：MEASUREMENT

收录：SCI-EXPANDED(收录号：WOS:001438138000001)、、EI(收录号：20250917979421)、Scopus(收录号：2-s2.0-85218991188)、WOS

基金：The authors would like to thank Yadong Xue's team at Tongji Uni-versity for their assistance in creating a public dataset on tunnel water leakage. This work is supported by the National Natural Science Foun-dation of China (52104094) , the China Postdoctoral Science Foundation (2022M721997) and the Zhejiang Provincial Natural Science Founda-tion of China (LGJ22D020001)

语种：英文

外文关键词：3D reconstruction; Shield tunnels; Water leakage; Leakage detection; Water leakage localization; RANSAC algorithm; Deep learning

外文摘要：To address the inefficiency of traditional 3D reconstruction methods for shield tunnels and their limitations in visualization and leakage localization, this study replaces the dense reconstruction process with the generation of cylindrical point clouds using RANSAC to extract tunnel contours from SfM-based sparse point clouds. Experiments show that the structural error of the cylindrical point cloud is only 0.47%, and modeling time is reduced by 80.6%. With its uniform and controllable point density, the cylindrical point cloud enables texture mapping through camera parameters, achieving a 190.81% improvement in texture clarity and a 49.4% reduction in overall modeling time compared to traditional methods. Deep learning is further applied for pixel-level leakage segmentation, enabling spatial annotation in the 3D model. This method provides rapid, clear 3D modeling and efficient leakage detection, aiding in spatial leakage analysis.