Supercharge Your Innovation With Domain-Expert AI Agents!

Scale-invariant feature point extraction method applied to image matching

A scale-invariant feature and extraction method technology, applied in the field of image matching, can solve the problem of low image matching accuracy, achieve the effects of improving matching accuracy, reasonable scale area division, and improving accuracy

Inactive Publication Date: 2021-06-15
HARBIN UNIV OF COMMERCE
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the accuracy of image matching using Fast feature points is not high, the present invention provides a scale-invariant feature point extraction method applied to image matching

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
  • Scale-invariant feature point extraction method applied to image matching
  • Scale-invariant feature point extraction method applied to image matching
  • Scale-invariant feature point extraction method applied to image matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0044] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0045] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.

[0046] Such as figure 1 As shown, a method for extracting scale-invariant feature points applied to image match...

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 scale-invariant feature point extraction method applied to image matching, solves the problem of low image matching precision by using Fast feature points in the prior art, and belongs to the technical field of image matching. The method comprises the following steps: calculating scale region values of pixel points in an image under different scales, and establishing a scale pyramid; comparing the scale region values of each pixel point under different scales with the scale region values of the surrounding eight pixel points, screening out candidate feature points, calculating scale response scores of the image under different scales, carrying out non-maximum suppression on the screened-out candidate feature points, screening out the candidate feature point with the maximum scale response score, performing interpolation calculation by using the response scores of the current scale and the upper and lower scales to obtain an accurate scale, and removing the candidate feature points of which the offsets exceed a set value to obtain the remaining candidate feature points as scale-invariant feature points; and combining the obtained scale invariant feature points with Surf region description to generate local features, performing a matching experiment on the image to obtain a matching result, and analyzing the matching result.

Description

technical field [0001] The invention relates to a scale-invariant feature point extraction method, which belongs to the technical field of image matching. Background technique [0002] The main function of scale-invariant feature point extraction is to combine it with scale region features for image matching or point cloud generation. It plays a pivotal role in motion estimation, image stitching, 3D reconstruction, and automatic driving. Because the image generation process depends on factors such as different angles, planes, and distances, there is a certain affine between images. This places a requirement on the scale invariance of the feature points, and the determination of the position and scale of the feature points will have a great impact on the delineation of the subsequent scale area, which is directly related to the matching accuracy. At the same time, in addition to inter-image affine, image chromatic aberration, brightness changes, etc. increase the difficulty...

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): G06K9/46G06K9/62
CPCG06V10/40G06F18/22
Inventor 孙华东韩小为张旭刘良赵志杰张立志邱泽国
Owner HARBIN UNIV OF COMMERCE
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