The accurate and efficient segmentation of large-scale urban point clouds is crucial for many higher-level tasks, such as boundary line extraction, point cloud registration, and deformation measurement. In this paper, we propose a novel supervoxel segmentation approach to address the problem of under-segmentation in local regions of point clouds at various resolutions. Our approach introduces distance constraints from boundary points to supervoxel planes in the merging stage to enhance boundary segmentation accuracy between non-coplanar supervoxels. Additionally, supervoxels with roughness above a threshold are re-segmented using random sample consensus (RANSAC) to address multi-planar coupling within local areas of the point clouds. We tested the proposed method on two publicly available large-scale point cloud datasets. The results show that the new method outperforms two classical methods in terms of boundary recall, under-segmentation error, and average entropy in urban scenes.

Focusing on the failure history of single-ring segmental lining structure, the action path and mechanism of segment joint on the segment bending moment was investigated in this study. The explicit equations of segment bending moment increment difference and segment bending moment diffusion coefficient were derived, and the causes of segment bending moment state variation in high load level were studied. In the failure history of segmental tunnel lining, the bending moment variation was mainly controlled by the bending moment increment difference per unit time (IND). IND was mainly controlled by the relative stiffness ratio of segment joints and their derivative. The action path of segment joints on segment internal force can be divided into: 1) the opening and yielding of segment joints, 2) the attenuation of rotational stiffness of segment joints, 3) the change of relative stiffness ratio and its derivative, 4) the IND value of non-zero, and 5) the drastic change of segment bending moment state. Furthermore, the rotation stiffness of the segment joint attenuated, and then the acceleration variation of segment bending moment was caused by segment joint effects because IND was not equal to 0, i.e., the segment bending moment increased or decreased sharply.