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

Multiple hypothesis combined view selection based dense three-dimensional reconstruction method

A technology of joint view and 3D reconstruction, applied in the field of computer vision, which can solve the problems of low computational efficiency and unsatisfactory model precision.

Active Publication Date: 2018-03-30
HUAZHONG UNIV OF SCI & TECH
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its calculation efficiency is low, and it is oriented to the final surface reconstruction, so it is not very ideal in terms of model fineness

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
  • Multiple hypothesis combined view selection based dense three-dimensional reconstruction method
  • Multiple hypothesis combined view selection based dense three-dimensional reconstruction method
  • Multiple hypothesis combined view selection based dense three-dimensional reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0044] The biggest contribution of this algorithm is to break through the limited propagation problem of the symmetrical checkerboard grid propagation method, and further use the multi-hypothesis joint view selection method to infer a more accurate view aggregation set. exist figure 1 Among them, the core innovation includes two parts: one is to adopt an asymmetric checkerboard grid propagation method; the other is to construct a cost matrix for candidate views and candidate hypotheses, and perform multi-hypothesis joint view selection. The resulting dense 3D model can be used for classification, image-based rendering and localization, etc. Its specific implementation is as follows:

[0045] Such as figure 1 Shown method flow process of the present invention is specifically as follows:

[0046] Random initialization: Select an image in the corrected image set as the reference image, and other images as the source image. On the reference image, generate a random depth value...

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 belongs to the field of computer vision, discloses a multiple hypothesis combined view selection based dense three-dimensional reconstruction method and provides an asymmetric chessboardgrid transmission and multiple hypothesis combined view selection based quick and accurate dense three-dimensional reconstruction method. On the basis of matching cost of neighborhood pixels, asymmetric chessboard grid transmission enables low-cost hypothesis to be preferentially transmitted to a further area to increase algorithm convergence rate. Further, multiple hypotheses are selected by themultiple hypothesis combined view selection method through asymmetric chessboard grid transmission to construct a cost matrix in neighborhood views to extract an appropriate view aggregation set, sothat high accuracy in aggregation cost representation and optimal hypothesis selection is realized. By the method, quickness in algorithm convergence is realized on the premise of making full use of parallel computing power, and accurate robust dense reconstruction results can be obtained.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to a dense three-dimensional reconstruction method based on multi-hypothesis joint view selection. Background technique [0002] The main idea of ​​patch matching is to randomly initialize a corresponding field, and then iteratively propagate the good correspondence between neighboring pixels. Perturbations to increase hypothesis diversity. It was first introduced into stereo vision by Bleyer et al., and then widely promoted. Dense 3D reconstruction methods based on patch matching can generally be divided into three stages: view selection, propagation scheme, and depth fusion. [0003] In the view selection stage, Kang et al. adopted a heuristic view selection method, which selected the best 50% view set from all matching costs for cost aggregation; Galliani et al. adjusted it to select a fixed K A collection of views is used for cost aggregation. However, no matte...

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): G06T17/00
CPCG06T17/00
Inventor 陶文兵徐青山
Owner HUAZHONG 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