3D reconstruction method based on multi-field-depth image fusion

A technology of 3D reconstruction and depth-of-field image, which is applied in the field of 3D reconstruction, can solve the problems of low 3D reconstruction accuracy and the inability to obtain the 3D shape of the sample to be tested, and achieve the effect of high 3D reconstruction accuracy and real results

Active Publication Date: 2018-04-13
山西盘古深度智能信息技术有限公司
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a 3D reconstruction method based on multi-depth image fusion in order to solve the problems of low 3D reconstruction accuracy and the inability to obtain the real 3D shape of the sample to be measured in the above-mentioned prior art

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
  • 3D reconstruction method based on multi-field-depth image fusion
  • 3D reconstruction method based on multi-field-depth image fusion
  • 3D reconstruction method based on multi-field-depth image fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Such as figure 1 As shown, a kind of three-dimensional reconstruction method based on multi-depth image fusion described in this embodiment, wherein: comprises the following steps:

[0025] (1) Obtain high-resolution original image sequences with different depths of field at the same position of the sample to be tested;

[0026] Wherein, the method for obtaining the original image sequence: firstly find the positions of the upper surface and the lower bottom surface of the sample to be tested by manually adjusting the longitudinal displacement of the camera, set the camera shooting range at the distance between the upper surface and the lower bottom surface, and then move the camera longitudinally and equidistantly Continuously collect images with different depths of field at the same position of the sample to be tested, and obtain n original image sequences I 1 , I 2 ,...,I n ;

[0027] (2) Obtain the corresponding high and low frequency coefficients through static...

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

A 3D reconstruction method based on multi-field-depth image fusion belongs to the technical field of 3D reconstruction. The problem that the precision of 3D reconstruction is low and the true 3D morphology of a sample under test cannot be obtained is solved. The technical scheme includes the following steps: (1) acquiring a high-resolution original image sequence with different depth of field in the same position of a sample under test; (2) carrying out static wavelet transformation on the original image sequence to obtain corresponding high and low frequency coefficients; (3) designing corresponding fusion rules for the high and low frequency coefficients to obtain high and low frequency fusion coefficients, obtaining a fused image through inverse static wavelet transformation, and obtaining an initial 3D reconstruction result based on the high frequency fusion rule; (4) carrying out Gaussian low-pass filtering on the initial 3D reconstruction result to obtain a final 3D reconstruction result of the sample under test; and (5) mapping the fused image and the final 3D reconstruction result one by one to obtain a true 3D reconstruction result of the sample under test. The 3D reconstruction method of the invention has the advantages of high precision of 3D reconstruction, true reconstruction result, and the like.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional reconstruction, and in particular relates to a three-dimensional reconstruction method based on multi-depth image fusion. Background technique [0002] In recent years, more and more products are developing towards precision and intelligence. With the continuous innovation of product processing and manufacturing technology, it will inevitably lead to the integration and automation of industrial production lines. Therefore, replacing manual inspection with 3D machine vision inspection technology has become The inevitable trend of technological development. The current mainstream 3D reconstruction methods mainly include laser confocal 3D reconstruction, structured light 3D reconstruction, and image sequence 3D reconstruction based on SFF (Shape From Focus). [0003] Among them, the laser confocal three-dimensional reconstruction method has high reconstruction accuracy, but its point scann...

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 闫涛钱宇华彭甫镕宋艳涛胡志国杜亮
Owner 山西盘古深度智能信息技术有限公司
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