Abstract
Point cloud registration is one of the basic research hotspots in the field of 3D reconstruction. Although many previous studies have made great progress, the registration of rock point clouds remains an ongoing challenge, due to the complex surface, arbitrary shape, and high resolution of rock masses. To overcome these challenges, a novel registration method for rock point clouds, based on local invariants, is proposed in this paper. First, to handle the massive point clouds, a point of interest filtering method based on a sum vector is adopted to reduce the number of points. Second, the remaining points of interest are divided into several cluster point sets and the centroid of each cluster is calculated. Then, we determine the correspondence between the original point cloud and the target point cloud by proving the inherent similarity (using the trace of the covariance matrix) of the remaining point sets. Finally, the rotation matrix and translation vector are calculated, according to the corresponding centroids, and a correction method is used to adjust the positions of the centroids. To illustrate the superiority of our method, in terms of accuracy and efficiency, we conducted experiments on multiple datasets. The experimental results show that the method has higher accuracy (about ten times) and efficiency than similar existing methods.
Highlights
Based on the above considerations, we propose a new registration method, which is mainly divided into the following steps: First, to efficiently and accurately extract the above feature area points, a new interesting point detection method, called sum vector filtration (SVF), is proposed
The normal distribution transform (NDT) method, proposed by Magnusson et al [36], solves the transformation matrix based on statistical information after voxelizing the point cloud, which was provided with the PCL library
The N-point Complete Graphs (NCG) method, proposed by Wang et al [15], uses the Gaussian curvature to select feature points and N-point complete graphs to calculate the transformation matrix, which was executed using the code provided by Wang et al [15]
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. With the continuous advancement of laser scanning technology, the use of laser scanners as tools to generate 3D point clouds of complex scenes for structural engineering applications has been greatly promoted. Due to technical limitations, when scanning large scenes, single-site scanning usually only obtains partial angle data of the scene and cannot obtain complete scene data. When affected by object occlusion, even small scenes require multi-station scanning coverage of the whole scene [1]. To obtain complete scene data, the fusion of multi-station scanning data is one of the fundamental and important approaches in the field of 3D point cloud research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
