Three-dimensional point cloud automatic registration method based on characteristic information change degree

Abstract

The invention discloses a three-dimensional point cloud automatic registration method based on the characteristic information change degree, which is used for processing two or more than two pieces ofthree-dimensional point cloud data with overlapped parts, and comprises the following processing steps of: (1) selecting feature points according to the change degree of a local normal vector of point cloud; (2) designing three feature metrics to perform feature description on each obtained feature point; (3) comparing the feature description of each feature point through threshold constraint toobtain an initial matching point pair; (4) acquiring an accurate matching point pair by using a rigid distance constraint condition, and performing calculating by using a four-element method to obtainan initial registration parameter; and (5) carrying out accurate registration on the point cloud by adopting an improved ICP (iterative closest point) algorithm. According to the steps, the point cloud can be automatically registered, the feature description is simple, the identification degree is high, the robustness is high, and the registration precision and speed are improved to a certain extent.

Description

technical field [0001] The invention relates to a three-dimensional point cloud automatic registration method based on the change degree of feature information, belonging to the field of three-dimensional information reconstruction. Background technique [0002] The 3D reconstruction of object surface has always been an important topic in the field of machine vision. The point cloud data on the surface of the measured object can be quickly obtained by an optical scanner, but due to the linear propagation characteristics of light, the complete data on the surface of the measured object needs to be measured multiple times under multiple viewing angles, so that the obtained data are not in the same coordinates Therefore, in order to obtain a complete model of the object, it is necessary to transform the coordinates of the data obtained from each perspective, and finally merge them into a unified coordinate system, which is point cloud registration. Point cloud registration tec...

AI Technical Summary

Problems solved by technology

However, this approximate position transformation makes it difficult to accurately fit the overlapping areas of the depth map, and there are often some interlacing and layering phenomena, which is not conducive to the fusion of subsequent depth map data, so the position of the depth map needs to be further adjusted. To improve the registration accuracy of the depth map, this process is called fine registration

Images