Heterogeneous Image Matching Method Based on Refined Feature Optimization Extraction

A heterogeneous image and feature optimization technology, applied in the field of radar image interpretation, can solve problems such as low matching accuracy, poor matching timeliness, and insufficient stability, to ensure matching accuracy, overcome nonlinear differences, and overcome difficulties in feature extraction with the same name problem effect

Active Publication Date: 2021-09-03
XIDIAN UNIV
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to propose a heterogeneous image matching method based on refined feature optimization extraction to solve the problems of poor matching timeliness, insufficient stability and low matching accuracy in the above-mentioned prior art, and provide accurate target scenes for aircraft guidance and location information

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
  • Heterogeneous Image Matching Method Based on Refined Feature Optimization Extraction
  • Heterogeneous Image Matching Method Based on Refined Feature Optimization Extraction
  • Heterogeneous Image Matching Method Based on Refined Feature Optimization Extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiment and effect of the present invention are described in detail below in conjunction with accompanying drawing:

[0030] refer to figure 1 , the implementation steps of the present invention include as follows:

[0031] In step 1, different operators are used to calculate the gradient modulus and direction of the two images.

[0032] (1a) Calculate the optical image gradient modulus and direction:

[0033] (1a1) the optical image I O Respectively with the Sobel template m in the x direction x and the Sobel template m in the y direction y Convolve to get the gradient M of the image in the x direction x and the y-direction gradient M y ,in

[0034] (1a2) According to the gradient of the optical image in the x direction and the y direction, calculate the gradient modulus M of the optical image O and direction θ O :

[0035]

[0036] (2a) Calculate the SAR image gradient modulus and direction:

[0037] (2a1) The Gaussian-Gamma double-window function...

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 heterogeneous image matching method based on refined feature optimization extraction, which mainly solves the problem of low matching accuracy in the prior art. The technical solution is: 1. Using different gradient operators to calculate optical images and SAR images respectively Gradient modulus and direction; 2. Use the specific properties of the target in the image to complete the calibration of the region of interest; 3. According to the results of step 1, obtain the edge features of the region of interest in the two images, and obtain a rough matching simulation between the two images through template matching. 4. Use the rough matching affine transformation matrix to obtain the transformed optical image, and then extract the refined features; 5. Perform preliminary matching on the refined features, and remove the singular point interference to obtain the fine matching affine transformation matrix; 6. According to the results of steps 3 and 5, the final affine transformation relationship matrix between the optical image and the SAR image is obtained. The invention can realize precise registration of heterogeneous images and can be used for aircraft guidance.

Description

technical field [0001] The invention belongs to the technical field of radar image interpretation, in particular to a registration method for heterogeneous images, which is suitable for providing more accurate target information for aircraft guidance. Background technique [0002] Satellite remote sensing is an effective means for human beings to observe, analyze and describe the earth environment in which they live. With the development of remote sensing technology, there are more and more types of sensors, and the resolution is getting higher and higher. Image registration with the same resolution has developed to the current multi-band, multi-resolution and multi-imaging mode image registration. The information obtained by a single sensor cannot meet the needs of the application. For example, in the processing of geological disasters, multiple sensor information such as synthetic aperture radar SAR, hyperspectral imaging systems, and infrared night vision devices are ofte...

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): G06K9/00G06K9/46G06T7/33
CPCG06T7/337G06V20/13G06V10/44
Inventor 李亚超胡思茹朱天启全英汇项宇泽
Owner XIDIAN UNIV
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