Image feature matching method for multi-scale detection based on anisotropic diffusion operation

An anisotropic, image feature technology, applied in the field of computer vision graphics and image processing, can solve the problem of the appearance change of the image to be matched affecting the matching effect, and achieve the effect of increasing the number of repeated feature points, high recognition rate, and strong practical value

Pending Publication Date: 2022-03-22
CHANGCHUN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the influence of illumination changes, viewing angle changes, target shape changes, image noise, etc., the appearance of the image to be matched may change to varying degrees, thus affecting the matching effect.

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
  • Image feature matching method for multi-scale detection based on anisotropic diffusion operation
  • Image feature matching method for multi-scale detection based on anisotropic diffusion operation
  • Image feature matching method for multi-scale detection based on anisotropic diffusion operation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings: an image feature matching method based on multi-scale detection of anisotropic diffusion operation, which is characterized in that anisotropic diffusion is introduced to replace Gaussian filtering, and when the image gradient is large, it is preferred to select The edge information of the image is preserved to extract distinctive features, so as to make up for the defects of Gaussian blur. And in the subsequent establishment of the scale space, add layers to lay a good foundation for feature detection. Finally, a nonlinear quantization-accelerated robust feature descriptor (NLG-SURF) is introduced to generate descriptors for the filtered feature points, and then the image features are matched according to the similarity measure of the descriptors. The process can be described as: introduce anisotropic diffusion to filter the image to be processed, and then use the mathem...

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 relates to an anisotropic diffusion operation-based multi-scale detection image feature matching method, which comprises the following specific steps of: introducing anisotropic diffusion to filter an image to be processed, and then solving a nonlinear diffusion filter equation by using a mathematical framework rapid explicit diffusion scheme to obtain an anisotropic diffusion image; a nonlinear scale space is established; after the scale space is successfully established, entering a feature detection stage, calculating a response value of each point in the image through a Hessian matrix, and detecting a local maximum point in the image according to the response value as a feature point; the feature points are endowed with main directions, descriptor generation operation is carried out by using a specific algorithm, and then image feature matching is carried out by using descriptor similarity measurement; the method is applied to a natural feature-based tracking registration technology, and has a strong practical value in an environment with relatively high requirements on real-time performance and effect.

Description

technical field [0001] The invention relates to a method of constructing a nonlinear scale space based on an anisotropic diffusion method to detect feature points to realize image feature matching, especially an image feature matching method based on multi-scale detection of an anisotropic diffusion operation, belonging to The technical field of computer vision graphics and image processing. Background technique [0002] Graphics and image processing technology is one of the important research contents of computer graphics, and it is also an important part of many computer vision applications such as virtual reality, augmented reality, 3D reconstruction, target recognition, and target tracking. The purpose of image feature matching is to find the homogeneous regions between images, and then establish the corresponding relationship between images according to the mapping of homogeneous regions. However, due to the influence of illumination changes, viewing angle changes, tar...

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): G06V10/75G06V10/44G06V10/46G06T5/20G06K9/62
CPCG06T5/20G06T2207/20192G06T2207/20024
Inventor 李华杨杨陈雨杰徐超权巍韩成胡汉平
Owner CHANGCHUN UNIV OF SCI & TECH
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