Research On Hole Recognition And Feature Hole Recognition Method Based On Scattered Point Cloud In Reverse Engineering

For the point cloud model with a large number of holes,there are some problems such as low efficiency and poor accuracy when using reverse software to hole identify.This paper mainly focuses on the detection of hole boundary feature points in discrete point cloud data and the identification of cylindrical feature hole boundary points:(1)The fundamental reason for the low computational efficiency of the traditional tensor voting algorithm for saliency structural feature reasoning is that the voting process and voting mechanism are too complicated.Especially when calculating the voting domain,it is necessary to rotate and align the standard stick voting domain and use the set step size to perform A large number of single and double integral operations.The three-dimensional analytical tensor voting algorithm after modifying the voting mechanism can effectively solve this problem,and the first-order analytical rod tensor voting algorithm is applied to the hole boundary point detection,and the threedimensional analytical first-order rod tensor voting algorithm is realized.Recognition and extraction of the hole boundary of the point cloud model.(2)In view of the fact that there are pseudo boundary points close to the real hole boundary points in the model,the large hole recognition algorithm cannot extract the complete boundary point set and is prone to misrecognition of boundary points.A fusion of first-order tensor and second-order tensor is proposed.Hole boundary feature point detection method based on voting algorithm.First,establish a new attenuation function to achieve the preliminary extraction of the boundary points of the first-order rod tensor voting in the neighborhood;then perform the eigenvalue and saliency of the semi-definite matrix obtained by the addition of the second-order rod,board,and ball tensors Correspondence analysis,further extract the boundary points of the hole;finally,the boundary point set extracted twice is combined,and the noise is removed at the same time to achieve the purpose of detecting the boundary point of the hole.Experimental results show that this method can effectively eliminate the influence of false boundary points on the extraction of hole boundary features,can achieve a more ideal detection effect,is more robust to noise,and has a low algorithm complexity.(3)For point cloud models with a large number of holes,current reverse software and repair algorithms both have low efficiency when single holes are repaired one by one,and there are too many human-computer interactions;while multiple holes are repaired at the same time,the accuracy is not high,and features are lost.Therefore,it is necessary to realize an efficient and high-precision point cloud hole classification automatic repair method based on the classification and recognition of holes and the goal of feature preservation.Based on the above ideas,a method for classifying cylindrical characteristic holes and general types of holes on the basis of hole recognition is proposed.First,extract the hole boundary point set with the aid of the maximum angle recognition criterion,segment and count the total number of holes by the European clustering algorithm,and then use the RANSAC algorithm and the set distance threshold to extract the cylindrical characteristic holes in the model.Experimental results show that this method can not only extract multiple cylindrical characteristic holes with different diameters in the model,but also estimate more accurate cylindrical geometric parameters,and realize the recognition of a class of characteristic holes oriented to automatic repair technology.