Optimization-based scattered point cloud data global feature extraction method

A technology of global features and extraction methods, applied in 3D object recognition, instrument, character and pattern recognition, etc., can solve the problem of long extraction time and so on

Pending Publication Date: 2020-07-28
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide a method for extracting global features of scattered point clouds based on optimization algorith

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Optimization-based scattered point cloud data global feature extraction method
  • Optimization-based scattered point cloud data global feature extraction method
  • Optimization-based scattered point cloud data global feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] Such as figure 1 Shown flow chart of the present invention, a kind of global feature extraction method of scattered point cloud based on optimization algorithm comprises the following steps:

[0078] Step 1: Initialize the scattered point cloud labels, the process is as follows:

[0079] Step 1.1: Input the 3D scattered model P={p 1 ,p 2 ,...,p N},p i ∈ R 3 , i=1,2,...,N, N is the number of points, p i represents the point labeled i;

[0080] Step 1.2: For each point p i The m neighbor points of (in this paper, m is taken as 10) conduct covariance analysis, estimate the curvature, and set the eigenvalue of the covariance matrix to λ 1 ,λ 2 ,λ 3 , and λ 1 ≤λ 2 ≤λ 3 , then point p i The curvature c i The calculation formula is:

[0081]

[0082] Step 1.3, set the threshold θ for the curvature estimation, and its calculation formula is as follows:

[0083]

[0084] Initialize the point cloud labels according to the threshold l = {l 1 , l 2 ,...,l ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an optimization-based scattered point cloud data global feature extraction method. The method comprises the following steps of initializing a scattered point cloud label, and dividing feature points and non-feature points according to a threshold value; judging the local uniformity of each point, dividing unified points and non-unified points according to labels, and marking the unified points with the labels of 1 as a feature point set; fitting attribute information of non-uniform points in the point cloud data of the three-dimensional scattered model through Gaussiandistribution; solving a state distribution function of a Markov random field of the non-uniform point label l; solving and optimizing a target optimization function of the non-uniform point label l toobtain optimal label distribution of the non-uniform points, and further obtaining a non-uniform point feature point set. The point cloud data is directly processed, a feature extraction problem is converted into a Markov random field energy minimization problem, the optimal label of each point is solved by using a simulated annealing algorithm, and an optimal solution is obtained in a global range.

Description

technical field [0001] The invention relates to the fields of three-dimensional reconstruction and reverse engineering, in particular to an optimization-based global feature extraction method for scattered point cloud data. Background technique [0002] The 3D model expression of the object is realized through the sharp features of the object. The feature is the smallest element describing the appearance of the model, and it is also a necessary condition for the accurate expression of the appearance of the model. Therefore, feature extraction technology has become a hot topic that has attracted increasing attention in the geometric processing of 3D models, and is an unavoidable key issue in the fields of 3D reconstruction and reverse engineering. [0003] In recent years, feature extraction methods for point cloud data are mainly divided into methods based on local fitting and methods based on feature detection operators. Among them, the methods based on local fitting gener...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/64G06F18/2135Y02T10/40
Inventor 肖恭兵刘伟东刘屿
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap