Check patentability & draft patents in minutes with Patsnap Eureka AI!

Binary description and matching method of image feature points based on point group comparison strategy

A technology of image feature points and binary description, which is applied in the directions of instrumentation, calculation, character and pattern recognition, etc., and can solve problems such as single pixel instability

Active Publication Date: 2019-05-14
HENAN POLYTECHNIC UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the shortcomings of the existing binary matching descriptors, which are easily affected by noise and unstable when comparing the gray scale of a single pixel, and proposes a binary description and matching method of image feature points based on a point group matching strategy, which mainly includes The following steps:

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
  • Binary description and matching method of image feature points based on point group comparison strategy
  • Binary description and matching method of image feature points based on point group comparison strategy
  • Binary description and matching method of image feature points based on point group comparison strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Such as figure 1 Shown is the image feature point binary description and matching method flow chart based on the point group comparison strategy of the present invention, which mainly includes the following steps: collecting images and performing preprocessing, using SIFT or Harris corner detection algorithm to extract the two images respectively Feature points, determine the feature point support area and calculate the main direction of the feature point, select 32 sampling points in the feature point support area, determine 144 sets of sampling point pairs in the feature point support area, and perform binarization processing based on the point group comparison strategy 1. Construct the binary feature descriptor of the feature point, and use the NNDR criterion to match the feature point based on the binary feature descriptor. The specific implementation details of each step are as follows:

[0020] Step S1: collecting images and performing preprocessing, specifically...

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 binary description and matching method of image feature points based on the point group comparison strategy of the present invention includes: collecting images and performing preprocessing, using SIFT or Harris corner point detection algorithms to extract feature points on two images respectively, and determining feature point support areas And calculate the main direction of the feature point, select 32 sampling points in the support area of ​​the feature point, determine 144 sets of sampling point pairs in the support area of ​​the feature point, perform binarization processing based on the point group comparison strategy, and construct the binary feature of the feature point Descriptors, based on binary feature descriptors and using NNDR criteria for feature point matching. The method provided by the invention has better stability than the existing binary description and matching method which directly compares the gray value of a single pixel point.

Description

technical field [0001] The invention relates to the field of feature point matching in image processing, in particular to the construction of binary descriptors in digital images and a feature point matching method. Background technique [0002] Taking the proposal and application of SIFT technology (D.Lowe, Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision.2004, 60(2):91–110) as an important symbol, feature point matching technology is used in target recognition, target It has been widely used in many scenes such as tracking and scene stitching. In recent years, with the rapid and widespread application of mobile smart devices, the binary description and matching method of feature points with small storage space and high processing efficiency has become an important technology and research hotspot. [0003] The existing feature point binary description methods mainly include BRISK (S. Leutenegger, M. Chli, and R. Siegwart. ...

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): G06K9/62G06K9/46
CPCG06V10/462G06V10/44G06V10/751
Inventor 刘红敏王志衡司马海峰霍占强贾利琴姜国权王静
Owner HENAN POLYTECHNIC UNIV
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