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

An indoor scene reconstruction method based on component extraction

A technology for indoor scenes and basic components, applied in interdisciplinary fields, can solve problems such as inability to accurately complete scene reconstruction, lack of unilateral measured data, and reconstruction objects

Active Publication Date: 2018-12-28
XIAN UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reconstruction results depend on the size of the model library and the selection of feature points during the matching process. For the single-sided measured point cloud data, the discrete point cloud does not contain topological information, and there are a large number of missing reconstruction objects in the single-sided measured data. The existing model-based The matching scene reconstruction method cannot complete the scene reconstruction accurately

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
  • An indoor scene reconstruction method based on component extraction
  • An indoor scene reconstruction method based on component extraction
  • An indoor scene reconstruction method based on component extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0124] The present invention will be described in detail below in conjunction with specific embodiments.

[0125] The present invention is an indoor scene reconstruction method based on component extraction, such as figure 1 As shown, follow the steps below:

[0126] Step 1. Perform rough detection on the indoor scene, extract each linear element in the indoor scene as a linear dataset; extract every flat element in the indoor scene as a flat dataset; extract every cylindrical element in the indoor scene as Cylindrical data set.

[0127] Step 1 is implemented according to the following steps,

[0128] Step 1.1. The point cloud data in a given indoor scene is D, D={p i |i=1,2,...,n}, p i Is a three-dimensional discrete point, i is a natural number that is not 0, n is a natural number, p i ={x i ,y i ,z i }, where x i , Y i ,z i Respectively denote p i Each coordinate value of;

[0129] Step 1.2, search p i The nearest neighbor point p, and find p i The local neighborhood is by Get p ...

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 indoor scene reconstruction method based on component extraction, a method for extracting basic shape components from indoor scene by using shape detection and plane decomposition. Based on point cloud data, a method based on boundary detection and a method based on a directed bounding box are used to realize that fitting of basic shape components in an indoor scene, thelargest member in the basic shape member set is selected as the reference member to find the best composite component with the reference component as the center, match the composite component and thestandard model of the standard model library one by one, find the component combination with the highest matching degree, so as to identify the object composed of the best composite component, at thesame time replace the corresponding standard model in the standard model library, and finally complete the reconstruction of indoor scene. The invention ensures the accuracy of the scene object component extraction and the shape integrity of the scene object, and better ensures the accuracy of the indoor scene reconstruction.

Description

Technical field [0001] The invention belongs to the interdisciplinary technical field combining computer graphics and virtual reality, and specifically relates to an indoor scene reconstruction method based on component extraction. Background technique [0002] 3D scene analysis and reconstruction is an important aspect of virtual reality and 3D data scene visualization. 3D scene reconstruction has gradually entered people’s daily lives, such as in autonomous navigation, reverse engineering, simulation experiments, video games, and medical fields. widely used. [0003] Traditional scene reconstruction technology pays more attention to the integrity of reconstruction results, but as the application of scene reconstruction technology has penetrated into all aspects of people's daily life, the demand for the viewing of scene reconstruction results is getting higher and higher, and the reconstruction results are required to be closer to the real scene. If the real scene of the world p...

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 Applications(China)
IPC IPC(8): G06T7/50G06K9/00G06K9/62
CPCG06T7/50G06T2207/10028G06V20/10G06F18/2321
Inventor 宁小娟李璠王映辉
Owner XIAN UNIV OF 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