Point cloud registration strategy in flatness measurement of laser contourgraph

Abstract

The invention discloses a point cloud registration strategy in flatness measurement of a laser contourgraph, and solves the problem of rapid and accurate estimation of a point cloud pose of an object to be measured in the flatness measurement of the laser contourgraph. The method comprises the following steps: firstly, extracting a boundary of a point cloud through an algorithm to obtain a more effective key point SHOT feature descriptor, and eliminating invalid key points through key point neighborhood evaluation to obtain a preliminary matching point pair; secondly, clustering the feature matching point pairs in combination with geometric consistency of the feature matching point pairs so as to realize coarse registration of the point clouds; and finally, completing fine registration of the point clouds by using an ICP algorithm based on the boundary point clouds. In comparison experiments with classical point cloud registration algorithms such as SHOT + ICP, 4PCS + ICP, NDT and the like, the speed and the precision of the method are improved to a certain extent.

Description

technical field [0001] The invention relates to the technical field of flatness measurement, in particular to a point cloud registration strategy in the flatness measurement of a laser profiler. Background technique [0002] With the development of machine vision technology worldwide, this technology is widely used in various aspects of industrial production inspection. As one of the important components of geometric tolerance, flatness has a wide range of testing requirements in many fields such as machinery, military industry and electronics. Traditional flatness measurement solutions are limited by various factors such as accuracy, detection speed, or equipment cost, and cannot meet the increasingly stringent detection requirements in actual production lines. In recent years, machine vision has been widely used in flatness detection. Among them, the laser profiler is very suitable for fast and high-precision flatness measurement because it can quickly and accurately obta...

AI Technical Summary

Problems solved by technology

[0003] The main problem faced in the point cloud registration of flatness measurement is: due to the large number of point clouds obtained by the laser profiler, the classic Iterative Closest Point (ICP) algorithm cannot meet the actual requirements due to its long calculation time. needs

On the other hand, in order to ensure that the point cloud registration does not fall into the local optimal solution, the point cloud registration method of first coarse registration and then fine registration is often used. In the rough registration based on feature descriptors, due to the lack of planar point cloud Texture makes it difficult to obtain effective local features, resulting in low accuracy of coarse registration, which has an adverse effect on subsequent fine registration

Images