Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Geometric shape recognition method and feature recognition method of basic primitive point cloud surface

A technology of geometric shapes and recognition methods, which is applied in the computer field, can solve problems such as distinction, and achieve the effects of strong robustness, avoiding blindness, and simple and feasible recognition methods

Active Publication Date: 2021-02-09
SOUTHWEAT UNIV OF SCI & TECH
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing surface feature recognition methods do not clearly distinguish the two processes

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
  • Geometric shape recognition method and feature recognition method of basic primitive point cloud surface
  • Geometric shape recognition method and feature recognition method of basic primitive point cloud surface
  • Geometric shape recognition method and feature recognition method of basic primitive point cloud surface

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In the following, a method for recognizing the geometric shape of a point cloud surface of a basic primitive and a method for recognizing a feature of a point cloud surface according to the present invention will be described in detail with reference to the accompanying drawings and exemplary embodiments.

[0028] Specifically, the present invention recognizes the geometric shapes of five basic primitives from the point cloud model based on the Gaussian map. In the stage of surface geometric shape recognition, the basic primitives are divided into two groups by using the feature saliency of the Gaussian map of the primitives. It is a plane-cylindrical-conical surface group and a spherical-toroidal surface group, and the plane, cylindrical surface and conical surface in the plane-cylindrical-conical surface group are distinguished by analyzing the characteristics of the Gaussian image. And in sphere-torus group, because sphere and torus can't be identified by Gaussian map...

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 provides a geometric shape recognition method and a feature recognition method of a point cloud surface of a basic graphic element. The geometric shape recognition method comprises the following steps: based on the Gaussian mapping method, the feature saliency of the Gaussian image is used to group the basic primitives to obtain a plane-cylindrical-conical surface group and a spherical-circular surface group; through the Gaussian image feature analysis , identify the plane, cylinder and conical surface in the plane-cylindrical-cone group; construct the Laplacian Beltrami operator, calculate the operator value of the Laplacian Beltrami operator, and use the operator The subvalues ​​Mean and Variance identify the sphere and torus in the Sphere‑Torus group. The feature recognition method includes: identifying the geometric shape of the point cloud surface of the basic primitive; and extracting the shape geometric parameters according to the recognized geometric shape of the point cloud curved surface of the basic primitive. The beneficial effects of the invention include that the identification method is simple and feasible, has good pertinence, and enhances the guidance of parameter extraction.

Description

technical field [0001] The invention relates to the field of computers, and is used for surface reconstruction technology. More specifically, it relates to a geometric shape recognition method of a point cloud surface of a basic primitive and a feature recognition method of a point cloud surface of a basic primitive. Background technique [0002] The surface of the physical sample is composed of multiple curved surface patches. After the point cloud model is segmented, multiple corresponding curved surface patch regions are formed. Since the region does not have corresponding geometric information, it is impossible to accurately reconstruct each curved surface patch. Analyze and study the point cloud surface Feature recognition is of great significance. The traditional point cloud reconstruction method does not carry out surface patch recognition, but uses methods such as implicit functions to uniformly model the point cloud model to obtain an overall approximate surface, or...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T15/00
CPCG06T15/005G06T17/30G06T2215/06
Inventor 李自胜肖晓萍
Owner SOUTHWEAT UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com