Unlock instant, AI-driven research and patent intelligence for your innovation.

Optical and SAR registration method and system based on cGANs and image conversion

An image conversion and optical technology, applied in the direction of graphic image conversion, neural learning method, image analysis, etc., can solve the problems of nonlinear intensity difference, discrepancy, the difficulty of direct registration of optical and SAR images, etc. effect of speed, avoiding nonlinear intensity differences

Pending Publication Date: 2021-10-08
TIANJIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the different imaging principles and imaging conditions of the SAR remote sensing image and the optical image, there are obvious nonlinear intensity differences and certain geometric structure, rotation, and resolution differences between the formed images, making the difference between the optical image and the SAR image Direct registration is more difficult

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
  • Optical and SAR registration method and system based on cGANs and image conversion
  • Optical and SAR registration method and system based on cGANs and image conversion
  • Optical and SAR registration method and system based on cGANs and image conversion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described in detail through the accompanying drawings and specific embodiments below.

[0042] Such as Figure 1-7 As shown, an embodiment of the present invention provides an optical and SAR registration method based on cGANs and image conversion, including the following steps:

[0043] S1. Acquiring paired SAR images and optical images to be registered; cutting the SAR images to be registered into multiple small image blocks;

[0044] S2. Use the trained conditions to generate an adversarial network to convert the cropped image blocks into synthetic optical image blocks; stitch the synthetic optical image blocks to obtain a synthetic optical image;

[0045] S3. Extract a large number of feature points from the synthesized optical image to form a reference set; extract feature points from the acquired optical image to be registered to form a query set;

[0046] S4. Searching for the nearest neighbor point in the query set accordi...

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 an optical and SAR registration method and system based on cGANs and image conversion. The method comprises the steps: acquiring a to-be-registered SAR image and a to-be-registered optical image in pairs; utilizing the trained conditional generative adversarial network to convert the SAR image into synthetic optical image small blocks; splicing the synthesized optical image small blocks to obtain a synthesized optical picture; extracting a large number of feature points from the synthesized optical picture to form a reference set; extracting feature points from the obtained optical image to be registered to form a query set; searching the nearest neighbor points in the query set according to the feature points in the reference set to form matching point pairs; and performing fine registration on the matching point pairs by using an RANSAC algorithm, and obtaining a fine-registered image after eliminating wrong matching point pairs. The non-linear intensity difference between the images is avoided, and the registration difficulty of the SAR image and the optical image is reduced.

Description

technical field [0001] The invention belongs to the field of image registration, in particular to a registration method and system for optics and SAR based on cGANs and image conversion. Background technique [0002] The data obtained by remote sensing satellites are widely used in various fields, including the monitoring of environmental pollution, forest resources, river information, etc., and the timely response to various disasters. The information obtained by different sensors for earth observation has its own uniqueness. The comprehensive utilization of multi-source remote sensing data is an important research direction in the field of remote sensing applications. It can obtain richer remote sensing information through complementary advantages. Optical remote sensing and synthetic aperture radar (Synthetic Aperture Radar, SAR) are two important technical means to obtain earth observation information by using remote sensing. The target edge in the visible light image i...

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): G06T7/11G06T7/136G06T7/33G06N3/04G06N3/08G06T3/40
CPCG06T7/337G06T7/11G06T7/136G06T3/4038G06N3/08G06T2207/10032G06T2207/20081G06T2207/20084G06T2207/20132G06N3/045
Inventor 罗卿莉李宏
Owner TIANJIN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com