An unstructured point cloud feature point detection method and its extraction method

Abstract

The present invention provides a detection method of an unstructured point cloud feature point and an extraction method thereof. The extraction method includes (1) calculating the Harris response value of a sampling point in different scale space; (2) selecting the Harris response value of the optimal scale space as the Harris response value of the sampling point to obtain a feature point set Q; (3) selecting one maximum point of the Harris response values possessing maximality in both of the scale space neighborhood and a geometric neighborhood as a candidate feature point, at last, selecting the optimizing strategy to draw the final feature point. A tangent plane of the gained feature point is subjected to network segmentation under a polar coordinate system, and then a neighborhood point of the feature point is projected to the tangent plane, a feature information statistical matrix is generated by voting projected length corresponding to projective points from each grid to four peaks of the grid, then both of a row vector and a column vector are respectively subjected to the DCT transform and the DFT transform, the elements of the upper left corner after transform is a character description vector.

Description

technical field [0001] The invention belongs to the field of three-dimensional space object recognition, and relates to a method for detecting feature points of unstructured point clouds and an extraction method thereof. It specifically involves a multi-scale feature point detection algorithm for unstructured 3D point cloud data and a feature point description algorithm based on shape information statistics and space transformation ideas. Background technique [0002] With the popularization of 3D modeling technology, 3D point cloud data is widely used in many fields such as cultural relics protection and space object recognition. Facing the 3D point cloud with a huge amount of information, how to extract meaningful information that meets the requirements of practical applications is a problem that must be solved when processing 3D point cloud data. [0003] Feature point extraction of point cloud data, as a key technology in 3D point cloud data processing, is a research ho...

AI Technical Summary

Problems solved by technology

Existing 3D model feature extraction algorithms are mainly aimed at grid data, which cannot meet the requirements for unstructured point cloud feature extraction

Compared with gridded point cloud data, unstructured point cloud data has a large amount of data, no point cloud topology information, and feature point detection is easily affected by noise, so feature point detection and description are difficult

Images