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

Deep convolutional GAN-based optical image and SAR image registration method

A deep convolution and image registration technology, applied in the field of image processing, can solve the problems of poor accuracy and robustness of registration results

Active Publication Date: 2018-09-07
XIDIAN UNIV
View PDF11 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an optical and SAR image registration method based on deep convolution GAN, which solve

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
  • Deep convolutional GAN-based optical image and SAR image registration method
  • Deep convolutional GAN-based optical image and SAR image registration method
  • Deep convolutional GAN-based optical image and SAR image registration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] like figure 1 As shown, the optical and SAR image registration method based on deep convolution GAN provided by the present invention comprises the following steps:

[0056] Step 1, get training samples:

[0057] (1a) Reading in the registered heterogeneous images, the heterogeneous images include SAR images and optical images;

[0058] (1b) Use the SIFT method to extract the SIFT feature point A of the optical image, and take the coordinates of the extracted SIFT feature point A as the center point, cut out a 32*32 optical image block on the optical image; at the same time, in the SAR image Get the feature point B corresponding to the coordinates of the SIFT feature point A extracted in step (1b);

[0059] (1c) Randomly select a feature point C on the SAR image, and then take the coordinates of feature point B and feature point C as the center on the SAR ima...

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 deep convolutional GAN-based optical image and SAR image registration method. The method comprises the following steps of: obtaining a training sample; constructing two generative adversarial networks; expanding training sample data; constructing a feature extraction and matching network; training the feature extraction and matching network by adoption of a cross iteration strategy; predicting a matching relationship; removing mis-matching points; calculating a geometric transformation matrix; and registering images. According to the method, the problems that neural network training samples are lack of data, samples are single and extracted image features lose space information in the prior art are overcome, the robustness of different-source image registration iseffectively improved, and higher-precision registration for SAR images and optical images is realized.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an optical and SAR image registration method based on deep convolution GAN. Background technique [0002] In recent years, image registration technology has been widely used in military, scientific research and daily life, especially in remote sensing image analysis in the field of remote sensing, medical image recognition and processing in the medical field, and computer vision in the field of artificial intelligence. Wait. The information complementarity between heterogeneous images is very beneficial to obtain complete image information, so heterogeneous image registration has very important research value and significance. [0003] The existing image registration methods are mainly divided into two types, one is the method based on gray level, and the other is the method based on local salient features. Among them, the method based on grayscale is to us...

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): G06T7/33G06N3/04G06N3/08
CPCG06N3/08G06T7/33G06T2207/30181G06T2207/10044G06T2207/10024G06T2207/20084G06T2207/20081G06N3/045
Inventor 权豆焦李成王爽王若静梁雪峰方帅马晶晶孙莉
Owner XIDIAN 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