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

Multi-modal image robust matching VNS method

A multi-modal image, robust technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as large-angle rotation and nonlinear radiation differences, achieve uniform distribution, optimize convergence conditions, and eliminate non-linear radiation. Effects of Linear Radiation Differences

Active Publication Date: 2021-09-03
10TH RES INST OF CETC
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It mainly solves the problems of large-angle rotation and nonlinear radiation difference between images

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
  • Multi-modal image robust matching VNS method
  • Multi-modal image robust matching VNS method
  • Multi-modal image robust matching VNS method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] refer to figure 1 . According to the present invention, the following steps are adopted: according to the input image, a multi-scale and multi-directional Log-Gabor odd symmetric filter is used to filter the original image to obtain an edge structure map of multiple scales and directions, and then the multi-scale and multi-directional edge The structural map is superimposed and accumulated, and the cumulative structural feature map of the original image is constructed for subsequent feature extraction and description;

[0028] Step 2: Calculate the cumulative components of the above-mentioned multi-scale and multi-directional edge structure graph in the horizontal and vertical directions of the image, and calculate the direction information of the pixel point by pixel to obtain the characteristic direction map;

[0029] Step 3: Extract FAST feature points on the cumulative structure feature map, take each feature point as the center, extract the cumulative structure f...

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

A multi-modal image robust matching VNS method disclosed by the invention is high in matching success rate and strong in adaptability. According to the technical scheme, the method comprises: filtering an original image by adopting an odd symmetry filter, performing superposition accumulation on obtained edge structure diagrams of multiple scales and directions, and constructing an accumulation structure feature diagram; calculating a feature directional diagram through the components of the edge structure diagrams of multiple scales and directions in the horizontal and vertical directions of the image; constructing a local structure feature map direction field by using an accumulation structure feature map and a feature direction map in a local neighborhood of the feature points, constructing a feature descriptor by using the accumulation structure feature map and the direction feature map, and carrying out descriptor vector normalization by replacing an Euclidean distance with a mahalanobis distance; taking a nearest neighbor Hellinger distance as a matching measure, and obtaining an initial matching result through bidirectional matching; and improving and optimizing the convergence performance of the random sampling method, considering the precision at the same time, carrying out gross error elimination on an initial matching result, and obtaining an inner point set with high accuracy.

Description

technical field [0001] The present invention relates to fields widely used in visual navigation of UAVs, ground target tracking and positioning, registration of remote sensing images, and detection of changes in satellite images, and in particular relates to a modal robust image matching for remote sensing image processing of UAV vision-assisted navigation method. Background technique [0002] At present, mainstream UAV positioning and navigation mainly include inertial navigation, global satellite navigation and radio navigation. The inertial navigation system (INS) has good autonomy, high short-term accuracy, and strong anti-interference. Its main disadvantage is that the positioning error accumulates rapidly with time, and the high-precision inertial navigation system is not only heavy and bulky, but also expensive. The global satellite navigation system (GNSS, including GPS, GLONASS, Beidou and Galileo, etc.) has high positioning accuracy, and the error does not accumul...

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): G06K9/00G06K9/46
CPCY02T10/40
Inventor 谢勋伟赖作镁姜家财刘杰
Owner 10TH RES INST OF CETC
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