A Object Reconstruction Method Based on Dictionary Learning

A dictionary learning and target technology, which is applied in the field of target reconstruction based on dictionary learning, can solve problems such as noise and holes, and achieve the effect of reducing calculation time and calculation amount.

Active Publication Date: 2019-02-15
BEIHANG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technology of the present invention solves the problem: overcomes the deficiencies of the prior art, and provides a method for object reconstruction based on dictionary learning to construct a sparse point cloud model of the target, and utilizes the sparse point cloud The local geometric similarity of the model is extended to avoid dense matching in the target non-textured area, and fundamentally solve the noise and hole problems caused by traditional methods

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
  • A Object Reconstruction Method Based on Dictionary Learning
  • A Object Reconstruction Method Based on Dictionary Learning
  • A Object Reconstruction Method Based on Dictionary Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in detail below with reference to the drawings and embodiments.

[0037] Such as figure 1 As shown, the present invention is a method based on dictionary learning for target refocusing. The specific steps are as follows.

[0038] 1. Use the existing dense point cloud model to build a point cloud dictionary library

[0039] The elements in the point cloud patch library are taken from some existing 3D point cloud models. Specifically, remember a three-dimensional point cloud model as M={X 0 ,X 1 ,...,X t-1 }, where X i Is the points contained in model M, t is the number of points contained in M, divide M into several point cloud patches, denoted as P 0 , P 1 ……P l-1 (l is the number of point cloud patches obtained by division), they satisfy formulas (7)~(9)

[0040] P 0 ∪P 1 ∪...P l-1 =M (7)

[0041]

[0042] s min ≤|P i |≤s max (9)

[0043] Equations (7) and (9) respectively illustrate P 0 , P 1 ……P l-1 You can cover the entire M, and you...

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 relates to a target reconstruction method based on dictionary learning. Firstly, existing dense point cloud models are utilized for constructing a point cloud dictionary library; then asparse point cloud model of the target is constructed, and is expanded by virtue of the point cloud dictionary library for obtaining a complete dense three-dimensional model, and features are constructed in a process of expansion on the basis of local curvature invariance of point cloud surface pieces to be used as bases of expansion; and finally, surface reconstruction is carried out on the model, which is obtained by expansion in the previous step, to complete target reconstruction. The method can greatly reduce computation time, and has very good performance for reconstruction of targets ofwhich image texture is not rich or texture areas are repeated.

Description

Technical field [0001] The invention relates to a target reconstruction method based on dictionary learning, which is suitable for targets with simple structure but lacking texture, and can effectively solve the holes and large area missing in the reconstruction results of such targets, and improve the integrity of the reconstruction model. Background technique [0002] With the development of computer graphics and reverse engineering, people pay more and more attention to how to obtain high-precision three-dimensional models of objects. This technology is called three-dimensional reconstruction technology. The three-dimensional reconstruction technology mainly includes the steps of obtaining and preprocessing of the model data in the early stage, the registration and fusion of the point cloud data, and the surface reconstruction of the point cloud data. Finally, the real object is converted into a digital model that can be displayed by the computer. [0003] Similar to the human e...

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): G06T17/00
CPCG06T17/00G06T2200/04G06T2207/20081
Inventor 袁丁刘韬张弘
Owner BEIHANG UNIV
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