On-site manual inspection of metro tunnel leakages has been faced with the problems of low efficiency and poor accuracy. An automated, high-precision, and robust water leakage inspection method is vital to improve the manual approach. Existing approaches cannot provide the leakage location due to the lack of spatial information. Therefore, an integrated deep learning method of water leakage inspection using tunnel lining point cloud data from mobile laser scanning is presented in this paper. It is composed of three parts as follows: (1) establishment of the water leakage dataset using the acquired point clouds of tunnel linings; (2) automated leakage detection via a mask-region-based convolutional neural network; and (3) visualization and quantitative evaluation of the water leakage in 3D space via a novel triangle mesh method. The testing result reveals that the proposed method achieves automated detection and evaluation of tunnel lining water leakages in 3D space, which provides the inspectors with an intuitive overall 3D view of the detected water leakages and the leakage information (area, location, lining segments, etc.).

中文翻译：

---

owards 使用移动激光扫描数据对盾构隧道衬砌中的漏水进行自动 3D 检查


地铁隧道渗漏现场人工检测一直面临着效率低、精度差的问题。自动化、高精度、稳健的漏水检测方法对于改进手动方法至关重要。由于缺乏空间信息，现有方法无法提供泄漏位置。因此，本文提出了一种利用移动激光扫描隧道衬砌点云数据进行漏水检测的集成深度学习方法。它由以下三部分组成：（1）利用获取的隧道衬砌点云建立漏水数据集； (2) 通过基于掩模区域的卷积神经网络进行自动泄漏检测； (3)通过一种新颖的三角网格方法对3D空间中的漏水情况进行可视化和定量评估。测试结果表明，该方法实现了3D空间中隧道衬砌漏水的自动化检测和评估，为检查人员提供了检测到的漏水的直观整体3D视图以及渗漏信息（面积、位置、衬砌段等） .)。