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

Automatic SAR image registration based on geometric topological relationship of feature points

A geometric topology and automatic registration technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of low anti-noise ability of feature points and high computational complexity of the same name point, achieve high accuracy and reduce noise. Low impact, low complexity effects

Active Publication Date: 2019-03-12
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the existing SAR image automatic registration technology, such as low anti-noise ability of feature points and high computational complexity of points with the same name, a SAR image automatic registration method based on the geometric topological relationship of feature points is proposed.

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
  • Automatic SAR image registration based on geometric topological relationship of feature points
  • Automatic SAR image registration based on geometric topological relationship of feature points
  • Automatic SAR image registration based on geometric topological relationship of feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0055] The present invention relates to a SAR image automatic registration method based on the geometric topological relationship of feature points. First, the centroid of a fixed area is extracted as a feature point, and then the geometric topological relationship of the feature points under affine transformation is used to find a complete set of matching points. The transformation parameters obtained in the complete matching point pair are inversely transformed to the image to be registered, based on the registration accuracy between the reference image and the inversely transformed image, the correct set of point pairs with the same name is screened out, and the best imitation between images is obtained. Finally, the registration of SAR images is realized.

[0056] figure 1 It is a flow chart of the method, including four steps of image fixed regio...

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 SAR image automatic registration method based on the geometrical topological relationship of feature points, belonging to the field of remote sensing image processing and application. Through five steps of extracting the fixed region and center of mass of the image, determining the geometric topological relationship between pairs of non-collinear matching points, findinga complete set of matching points based on geometric topological relations, screening the set of points with the same name, and image registration, Automatic registration of SAR images under affine transformation is completed, which solves the problems of image gray and noise sensitivity in common SAR image registration methods, and has the advantages of strong anti-noise ability, high registration accuracy and low algorithm complexity, and has a wide application prospect in geographic remote sensing and military reconnaissance.

Description

technical field [0001] The invention relates to an image automatic registration method, in particular to a SAR image automatic registration method with an affine transformation relationship. Background technique [0002] Image registration is a process of linearly or non-linearly transforming two or more images of the same region or object obtained from different periods, different viewpoints, or different sensors, so that the two images can match geometrically. Its working principle is to use the feature point pairs with the same name in the reference image and the image to be registered to obtain the transformation relationship between the two images, so as to transform the coordinate system of the image to be registered into the coordinate system of the reference image. [0003] The parameter estimation of transformation relation is the key technology of automatic image registration. At present, there are mainly two approaches for automatic image registration: (1) method...

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): G06T5/50G06T7/30
CPCG06T5/50G06T7/30
Inventor 王玮晏行伟雷兵施建华
Owner NAT UNIV OF DEFENSE TECH
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