Voronoi density classification reverse reconstruction method for concrete beam point cloud

Abstract

The invention discloses a Voronoi density classification reverse reconstruction method for a concrete beam point cloud. The method comprises the following steps: preliminarily extracting a potential feature point set Pc in an actual point cloud Pr of a concrete beam by utilizing iterative weighted PCA (Principal Component Analysis); a beam body design feature point set Pd is formed according to a design drawing, Pd and Pc are matched by using an ICP algorithm to identify a design size and a spatial pose corresponding to Pr, and then Pr is translated and rotated to a standard axis position to form a standardized point cloud Ps; classifying Ps to each preset structural plane calculated by Pd to form a structural plane classification point set; extracting neighbor regions in a structural plane classification point set corresponding to the intersection surface of each reconstruction feature point in the Pd, judging the point cloud density quality of each neighbor region by using a Voronoi graph, marking reverse reconstruction reference regions, and calculating the number of the reverse reconstruction reference regions of each reconstruction feature point; and determining different design reconstruction point calculation methods according to the number of reverse reconstruction reference regions of each reconstruction feature point, and calculating coordinates of each reconstruction feature point.

Description

technical field [0001] The invention belongs to the technical field of bridge structures, and in particular relates to a Voronoi sparse density classification reverse reconstruction method of point clouds of concrete beams. Background technique [0002] With the development of 3D laser point cloud technology, its application in various fields has gradually matured. Reverse reconstruction of the shape of the model based on point cloud data is one of the key application directions. Although researchers in various fields currently have many mature algorithms for some key technical points of reverse reconstruction, such as calculating feature points, matching, and giving semantic information. However, most of these algorithms cannot be directly applied to sparse point clouds, or cannot provide the large test sets required for their big data learning algorithms in the field of bridge engineering. In the field of reverse reconstruction of bridge components, how to use the unique...

AI Technical Summary

Problems solved by technology

However, most of these algorithms cannot be directly applied to sparse point clouds, or cannot provide a large number of test sets required by their big data learning algorithms in the field of bridge engineering.

Images