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

Optimized calculation-based characteristic point matching method

A feature point matching and optimization computing technology, applied in computing, computer components, instruments, etc., can solve the problems of non-unique matching results, weak Hopfield neural network optimization ability, and mismatching

Inactive Publication Date: 2011-04-27
TIANJIN POLYTECHNIC UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the relative position information is not unique to the matching results, and the Hopfield neural network itself is not capable of optimization, it is easy to fall into the local minimum, so it is easy to cause false 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
  • Optimized calculation-based characteristic point matching method
  • Optimized calculation-based characteristic point matching method
  • Optimized calculation-based characteristic point matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] figure 1 The result of feature point matching in several continuous target images using the method of the invention is given. During the experiment, the energy function chooses the form of equation (7). In other words, when selecting feature points, it is necessary to find M feature points in the template image and N feature points in the target image, MM0 Must be greater than the feature threshold of the target image I N0 , Namely I M0 >I N0 .

[0043] It can be seen from the results of the example that the method of the present invention can achieve correct matching of the feature points in consecutive target images, and the success rate is better than that of the traditional method. The reason is that the energy function not only contains the relative position information of the feature points, but also In addition, the gray level matching information of the feature points is used, so the energy function evaluates the matching accuracy more accurately, and the hystereti...

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 belongs to the field of machine vision and target identification, and in particular relates to an optimized calculation-based characteristic point matching method. The method comprises the following steps of: respectively detecting characteristic points in a template image and a target image by using window area direction variation as a measured value of the characteristic points; controlling the number of the characteristic points by setting a characteristic threshold value; determining a matching criterion energy function according to the relative position information and gray scale information of the characteristic points; and performing optimized calculation on the energy function by using a hysteretic and chaotic neural network to solve a matching result of the characteristic points in the two images. The method can be applied to a target identification system.

Description

Technical field [0001] The invention belongs to the field of machine vision and target recognition, and relates to a feature point matching method based on optimization calculation, and in particular to a method for realizing image feature point matching by optimizing a constructed energy function. Background technique [0002] Feature point matching has always been an important research content in the field of machine vision and target recognition. It has important application value in target recognition and tracking, monitoring and security systems. The gray-scale-based matching method is a commonly used traditional feature point matching method. This method uses the image to be matched as a template, and overlaps and moves on the reference image. In the template movement, similarity calculation is performed between the template and the reference sub-images at different positions. After traversing the entire image, the area with the best similarity calculation with the referen...

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): G06K9/00G06N3/02
Inventor 修春波
Owner TIANJIN POLYTECHNIC 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