Research On Point Cloud Data Edge Extraction And Geometric Feature Measurement Algorithm

With the development of three-dimensional scanning technology,many scholars has pay attention to the technology of 3D point cloud data processing.Edge feature extraction and size measurement has been the hot topics of this field.The purpose of this paper is to propose an accurate and robust edge feature extraction algorithm of point cloud and measure the geometric features of several workpieces.Compared with the image processing field,the 3D point cloud processing lags behind image processing,and the robustness and applicability of the edge extraction algorithm is poor.However,in the dimension measurement of some objects,the edge information plays a crucial role.Therefore,it is of great significance to propose an accurate,efficient edge extraction algorithm of point cloud.This dissertation takes the scattered point cloud data as the research object,starts with the study of two key issues of edge cloud edge feature extraction and geometric feature measurement,and proposes a dual threshold constrained point cloud edge extraction algorithm based on normal information and k-neighborhood distribution..At the same time,the problems of the establishment of point cloud topological relations,point cloud reduction,and noise removal in the process of point cloud data processing are studied,and finally a geometric feature measurement method based on edge information is formed.The main research content of this article includes the following aspects:First,the k-neighborhood method is used to establish the topological relationship between the scattered point cloud data,and the point cloud data with a large amount of data point cloud is simplified to facilitate the subsequent fast calculation.Secondly,using the radius filtering method and statistical filtering method for the point cloud data containing noise points,denoising is performed.At the same time,for the incomplete problem of edge extraction existing in traditional edge detection methods,a normal information distribution based on k-neighborhood is proposed.The dual threshold constrained point cloud edge extraction algorithm completes the accurate extraction of the edge information of the object.Finally,the three-dimensional edge data is mapped to a two-dimensional plane,and an accurate measurement of the object's geometric size isachieved by using methods such as least squares and hough transform.In order to verify the effectiveness of the proposed algorithm,several sets of experiments were performed for different types of point cloud data and compared with mainstream algorithms.The experimental results show that the edge extraction effect and measurement accuracy of this algorithm are higher than the comparison algorithms.