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

Fast Matching and Stitching Method for Super Large Image Based on Block Subgraph Search

A super-large-scale, sub-image technology, applied in the field of two-dimensional image matching, can solve the problems of long time-consuming, low-efficiency large-scale image matching and stitching, and achieve the effect of shortening the matching time

Active Publication Date: 2019-06-28
XIDIAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for fast matching and stitching of ultra-large images based on block subgraph search, so as to solve the problems of low efficiency and time-consuming matching and stitching of large images

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
  • Fast Matching and Stitching Method for Super Large Image Based on Block Subgraph Search
  • Fast Matching and Stitching Method for Super Large Image Based on Block Subgraph Search
  • Fast Matching and Stitching Method for Super Large Image Based on Block Subgraph Search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Such as figure 1 As shown, the method of fast matching and mosaicing of ultra-large images based on block subgraph search is characterized in that it includes the following steps,

[0042] Step 1, use the GDAL library to read and display two large-scale images (here, the large-scale image file size is generally greater than 10000×10000pixels), the image with the largest total number of pixels is marked as A, and the image with the smallest total number of pixels is marked as B;

[0043] Step 2, determine the block method of the two images, and cut and block;

[0044] Step 3, search for the block, comprehensively use the color feature, texture feature and shape feature of the image to calculate the similarity between the blocks, and search for a pair of block subgraphs whose similarity meets the conditions in order; if the search is successful , proceed to feature matching in step 5; if the search fails, proceed to step 4;

[0045] Step 4, swap the names of the two ima...

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 a fast matching and splicing method of ultra-large-scale images based on block sub-image search, which is used to speed up the matching speed and improve the matching efficiency. First, use the GDAL library to read and display two large-scale images, named A and B respectively. Then, the two large-scale images are divided and cropped in a certain way to obtain many sub-images, with one sub-image of image B as the target. Image, search for the subimage with the greatest similarity among the subimages of image A. If the similarity meets the conditions, match the features of this pair of subimages; if the similarity does not meet the conditions, change to another subimage in image B. The picture is the target image, search in A again, and so on; if a sub-picture that meets the conditions is still not found, rename the image, swap A and B, and repeat the above-mentioned blocking and search process to find a sub-picture that satisfies the conditions. A pair of subgraphs are used for feature matching. The present invention can speed up the matching process and improve the registration efficiency for large-scale images.

Description

technical field [0001] The invention belongs to the field of two-dimensional image matching. Specifically, it is a method for fast matching and stitching of ultra-large images based on block subgraph search. Background technique [0002] Image registration and stitching technology has a wide range of applications in the fields of computer vision, medical image processing, and material mechanics. Images acquired under different conditions for the same object, such as images from different acquisition devices, at different times, from different shooting angles, etc., sometimes require image registration and stitching for different objects. Traditional image registration methods include grayscale-based and feature-based methods. The grayscale-based registration algorithm directly uses the grayscale information of the image to measure the similarity between images, and then adopts a certain search strategy to determine the transformation parameters to maximize the similarity. ...

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): G06T3/00G06T3/40G06T7/30
CPCG06T3/4038G06T2207/20221G06T3/14
Inventor 刘贵喜赵丹张娜李斯王义敏
Owner XIDIAN UNIV
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