Unlock instant, AI-driven research and patent intelligence for your innovation.

Real-time SIFT image matching method based on Gaussian pyramid grouping

A technology of Gaussian pyramid and matching method, which is applied in the field of real-time image matching to achieve the effect of improving achievability and feasibility

Inactive Publication Date: 2021-03-02
LUOYANG INST OF ELECTRO OPTICAL EQUIP OF AVIC
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the time-consuming problem of SIFT, the present invention improves the algorithm. While ensuring the original matching accuracy, it reduces the time-consuming through the combination of coarse and fine matching, and improves the process of removing mismatches based on RANASC, GMS, and least squares.

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
  • Real-time SIFT image matching method based on Gaussian pyramid grouping
  • Real-time SIFT image matching method based on Gaussian pyramid grouping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] according to figure 1 As shown, combined with the feature extraction principle of SIFT, it can be known that SIFT features have the following characteristics:

[0031] Even if the SIFT feature point coordinates extracted on different groups of Gaussian difference pyramids are the same, the descriptor information contained will not be exactly the same, that is, there will not be exactly the same feature points; the feature points on the Gaussian difference pyramid are distributed in each image. Position, the larger the number of groups, the larger the value of the scale factor of the Gaussian difference pyramid, and the smaller the number of feature points.

[0032] The analysis shows that: for the same group of Gaussian difference pyramids in the original image and the target image, the feature points on it are matched and the mismatch is remove...

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 provides a real-time SIFT (Scale Invariant Feature Transform) image matching method based on Gaussian pyramid grouping. Through algorithm improvement, real-time performance in practicalapplication is improved. While the original matching precision is ensured, the time consumption is reduced by combining coarse and fine matching and improving the mismatching removing process based onRANASC, GMS, least squares and the like aiming at the time consumption problem of SIFT. According to the invention, the matching speed is improved by more than one time compared with the traditionalSIFT; the matching precision is close to that of a traditional SIFT and is superior to that of SURF, the real-time performance of the SIFT algorithm is greatly improved while the matching precision isguaranteed, and the realizability and feasibility of the SIFT in engineering application are improved.

Description

technical field [0001] The invention relates to the fields of image splicing, moving target detection, image navigation, electronic image stabilization and the like, in particular to a real-time image matching method. Background technique [0002] The SIFT algorithm has been widely studied because of its excellent matching performance. The algorithm has invariant characteristics to scale changes, viewing angle rotations, and illumination transformations, as well as good affine invariance, and can reduce image noise and background object occlusion to a certain extent. impact on matching performance. [0003] In the target tracking scene in the military field, for example, when a fighter plane looks at an enemy plane at a high altitude, the environment where the enemy plane is located often includes water bodies, vegetation, land, mountains, etc., and the tracking environment is complex and changeable; in addition, object occlusion, image acquisition and Channel transmission ...

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
IPC IPC(8): G06K9/46G06K9/62G06T3/00
CPCG06V10/462G06V10/757G06T3/02
Inventor 董锦涛陈水忠郭许生
Owner LUOYANG INST OF ELECTRO OPTICAL EQUIP OF AVIC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com