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

Full-field dense point fast matching method

A matching method and dense technology, applied in the field of image processing, can solve problems such as difficult to meet the needs of real-time high-precision measurement, and achieve the effect of improving efficiency and matching speed.

Active Publication Date: 2018-01-16
XI AN JIAOTONG UNIV
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, although most of the existing new digital speckle correlation algorithms have improved search matching speed and accuracy, it is still difficult to meet the needs of some real-time high-precision measurements

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
  • Full-field dense point fast matching method
  • Full-field dense point fast matching method
  • Full-field dense point fast matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0021] see figure 1 The method for fast matching of full-field dense points of the present invention includes: importing a reference image M001, importing a target image M002, selecting a reference sub-area M003, selecting a search area M004, adjusting the position and size of the search area M005, histogram statistics M006, and local template matching M007 , Comparing whether it is greater than the threshold M008, matching the full template M009, determining the best matching point M010, recording the displacement M011, completing the search M012.

[0022] The specific operation steps are: first import the reference image M001, import the target image M002, select the reference sub-area M003 in the reference image as the matching full template, and select the search area M004 in the target image; Part of the pixels form a local template, and use the local t...

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 present invention provides a full-field dense point fast matching method. The method comprises: a. selecting a reference subarea as a matching full template in a reference image, and selecting a search area in a target image; b. employing part of pixel points in the reference subarea to form a partial template, and employing the partial template to perform matching of the partial template in the search area; c. calculating related coefficient value of each sliding, comparing the obtained related coefficient value of each sliding through calculation with a threshold value, selecting a candidate matching window, performing full template matching of the candidate matching window, and determining an optimum matching point, and if the related coefficient value of each sliding is smaller than the threshold value, neglecting the search area to continuously calculate related coefficient values of the next search area; and d. calculating and generating a new threshold value according to a related coefficient value after histogram statistics, recording a displacement component of the last optimum matching point, adaptively regulating the position and the size of the next matching point search area, changing parameters of a selected search area, and performing the next searching matching. A matching speed and a precision can be improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for fast matching of full-field dense points. Background technique [0002] The three-dimensional deformation and shape measurement of materials or objects has extremely wide applications in the fields of aerospace, quality control, reverse engineering, safety monitoring and material science. In recent years, with the rapid development of image processing and machine vision, visual measurement methods have attracted more and more attention. The digital speckle correlation method is the most computationally complex method in the process of object three-dimensional information acquisition. It obtains its deformation and other mechanical properties by performing correlation calculations on the displacement of the measured object before and after deformation or two speckle field images before and after deformation. As one of the visual measurement methods, it has the advanta...

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): G06K9/46G06K9/62
Inventor 张国和屠德成苏亚丽黄凯梁峰
Owner XI AN JIAOTONG 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