A Denoising Method for Point Cloud of Aviation Parts Based on Deep Learning

Abstract

The invention discloses a method for denoising a point cloud of aviation parts based on deep learning, which includes: artificially increasing different degrees of Gaussian noise based on a theoretical data model of aviation parts, and generating a height map for each point in the model , to construct a deep learning training set; based on the constructed deep learning training set, train the deep learning network to obtain a deep learning network model, which is used to predict the normal information of each point in the point cloud data; The parts are scanned to obtain the measured point cloud data, and based on the trained deep learning network model, the normal information of the measured point cloud is predicted; based on the predicted normal information, each The position of the point is updated, so as to realize the denoising of the measured point cloud. The invention solves the problem in the prior art that the noise of the scanning point cloud of the aviation parts cannot be accurately and efficiently removed, and further improves the efficiency and accuracy of the detection and analysis of the aviation parts.

Description

technical field [0001] The invention belongs to the technical field of aviation detection, and in particular relates to a method for denoising point clouds of aviation parts based on deep learning. Background technique [0002] In recent years, with the continuous improvement of domestic aviation research projects in technical combat indicators such as flight speed, stealth, and maneuverability, the structure of the aircraft itself has shown a clear trend of integration, lightweight, compactness, and precision. Aviation structural parts with complex structures and surface features have been widely used. The precision requirements of aviation structural parts are also increasing, and the requirements for assembly are gradually increasing, which makes the control and inspection of the manufacturing and processing quality of aviation parts particularly important. At the same time, as the use time of the aircraft increases, the wear and deformation of various parts will greatly ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for denoising the point cloud of aviation parts based on deep learning to solve the problem that the point cloud of aviation parts cannot be accurately and efficiently denoised in the prior art

Images