This paper presents a longitudinal dislocation detection method using an accurate tunnel segment joint labeling algorithm featured by deep CNNs (Convolutional Neural Networks). This method is proposed to be four steps. First, a mobile scanning system is used to acquire 3D point clouds of metro shield tunnels. Then, we use cylinder projection to generate tunnel surface depth images from 3D point clouds for segment joint labeling. Subsequently, two deep CNNs are designed to accurately label the segment joints on the depth images. The first CNN can roughly locate the segment joint positions, and the second precisely label the segment joints. Based on the labeled segment joints, two point data sets are obtained on both sides of each segment joint. By using the RANSAC algorithm, the two point sets can fit into two planes, the equation of which is then calculated to generate the dislocation value of the tunnel segment. Experiment results show that this method can label segment joints integrally and accurately without being affected by nearby tunnel equipment. Compared with traditional image edge detection algorithms (Canny and Sobel with Hough Transform), the CNNs are more powerful in labeling segment joints. When the distance measuring accuracy of scanner is 1.2 mm + 10 ppm, the internal and external accuracy of our detection method are evaluated to be 0.4 mm and 0.9 mm respectively. Compared with the scanning line method, the external accuracy of our method is higher and more reliable when there is tunnel equipment around segment joints.

本文提出了一种使用深度CNN（卷积神经网络）的精确隧道段接头标记算法的纵向错位检测方法。该方法被提议为四个步骤。首先，使用移动扫描系统来获取地铁盾构隧道的3D点云。然后，我们使用圆柱投影从3D点云生成隧道表面深度图像，以进行分段接头标记。随后，设计了两个深层的CNN，以在深层图像上准确标记分段关节。第一个CNN可以大致定位分段接头的位置，第二个CNN可以精确标记分段接头。基于标记的节段关节，在每个节段关节的两侧都获得了两个点数据集。通过使用RANSAC算法，两个点集可以适合两个平面，然后计算其方程以生成隧道段的位错值。实验结果表明，该方法可以完整，准确地标记节理，而不受附近隧道设备的影响。与传统的图像边缘检测算法（带有Hough变换的Canny和Sobel）相比，CNN在标记段关节上功能更强大。当扫描仪的测距精度为1.2 mm + 10 ppm时，我们检测方法的内部和外部精度分别为0.4 mm和0.9 mm。与扫描线法相比，当节段接头周围有隧道设备时，本方法的外部精度更高，更可靠。实验结果表明，该方法可以完整，准确地标记节理，而不受附近隧道设备的影响。与传统的图像边缘检测算法（带有Hough变换的Canny和Sobel）相比，CNN在标记段关节上功能更强大。当扫描仪的测距精度为1.2 mm + 10 ppm时，我们检测方法的内部和外部精度分别为0.4 mm和0.9 mm。与扫描线法相比，当节段接头周围有隧道设备时，本方法的外部精度更高，更可靠。实验结果表明，该方法可以完整，准确地标记节理，而不受附近隧道设备的影响。与传统的图像边缘检测算法（带有Hough变换的Canny和Sobel）相比，CNN在标记段关节上功能更强大。当扫描仪的测距精度为1.2 mm + 10 ppm时，我们检测方法的内部和外部精度分别为0.4 mm和0.9 mm。与扫描线法相比，当节段接头周围有隧道设备时，本方法的外部精度更高，更可靠。CNN在标记分段接头方面更强大。当扫描仪的测距精度为1.2 mm + 10 ppm时，我们检测方法的内部和外部精度分别为0.4 mm和0.9 mm。与扫描线法相比，当节段接头周围有隧道设备时，本方法的外部精度更高，更可靠。CNN在标记分段接头方面更强大。当扫描仪的测距精度为1.2 mm + 10 ppm时，我们检测方法的内部和外部精度分别为0.4 mm和0.9 mm。与扫描线法相比，当节段接头周围有隧道设备时，本方法的外部精度更高，更可靠。