Method of automatic coregistration of digital remote sensing images from different sources

In this paper, a method for the automatic alignment of diverse digital Earth remote sensing images using survey data is proposed. The method is designed to align color, grayscale, multispectral, and radar images, as well as their combinations, with potential differences in spatial resolution of up t...

Full description

Saved in:
Bibliographic Details
Main Authors: A.N. Borisov, V.V. Myasnikov, V.V. Sergeev
Format: Article
Language:English
Published: Samara National Research University 2024-12-01
Series:Компьютерная оптика
Subjects:
Online Access:https://www.computeroptics.ru/eng/KO/Annot/KO48-6/480615e.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850195009455783936
author A.N. Borisov
V.V. Myasnikov
V.V. Sergeev
author_facet A.N. Borisov
V.V. Myasnikov
V.V. Sergeev
author_sort A.N. Borisov
collection DOAJ
description In this paper, a method for the automatic alignment of diverse digital Earth remote sensing images using survey data is proposed. The method is designed to align color, grayscale, multispectral, and radar images, as well as their combinations, with potential differences in spatial resolution of up to four times (optionally – sixteen times). The main stages of the proposed method include: an optional upscaling (up to four times); an optional number of image channels reduction to three or one; keypoint detection, their description and alignment. To achieve a universal and robust solution in the latter stages, the best-known algorithms were compared: SIFT, SAR-SIFT, RIFT, and the trainable RoMa. Experimental studies using the indicated types of space images demonstrate a clear advantage of the trainable neural network model RoMa trained on a variety of heterogeneous images. For additional improvement of the alignment accuracy, we utilized a priori data about the images in the form of their georeferencing information.
format Article
id doaj-art-3a6b5018e40c40da9378f4cdf0850d90
institution OA Journals
issn 0134-2452
2412-6179
language English
publishDate 2024-12-01
publisher Samara National Research University
record_format Article
series Компьютерная оптика
spelling doaj-art-3a6b5018e40c40da9378f4cdf0850d902025-08-20T02:13:52ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792024-12-0148693294310.18287/2412-6179-CO-1604Method of automatic coregistration of digital remote sensing images from different sourcesA.N. Borisov0V.V. Myasnikov1V.V. Sergeev2Samara National Research UniversitySamara National Research UniversitySamara National Research UniversityIn this paper, a method for the automatic alignment of diverse digital Earth remote sensing images using survey data is proposed. The method is designed to align color, grayscale, multispectral, and radar images, as well as their combinations, with potential differences in spatial resolution of up to four times (optionally – sixteen times). The main stages of the proposed method include: an optional upscaling (up to four times); an optional number of image channels reduction to three or one; keypoint detection, their description and alignment. To achieve a universal and robust solution in the latter stages, the best-known algorithms were compared: SIFT, SAR-SIFT, RIFT, and the trainable RoMa. Experimental studies using the indicated types of space images demonstrate a clear advantage of the trainable neural network model RoMa trained on a variety of heterogeneous images. For additional improvement of the alignment accuracy, we utilized a priori data about the images in the form of their georeferencing information.https://www.computeroptics.ru/eng/KO/Annot/KO48-6/480615e.htmldigital remote sensing imagesautomatic image coregistrationmultispectral imagesradar images
spellingShingle A.N. Borisov
V.V. Myasnikov
V.V. Sergeev
Method of automatic coregistration of digital remote sensing images from different sources
Компьютерная оптика
digital remote sensing images
automatic image coregistration
multispectral images
radar images
title Method of automatic coregistration of digital remote sensing images from different sources
title_full Method of automatic coregistration of digital remote sensing images from different sources
title_fullStr Method of automatic coregistration of digital remote sensing images from different sources
title_full_unstemmed Method of automatic coregistration of digital remote sensing images from different sources
title_short Method of automatic coregistration of digital remote sensing images from different sources
title_sort method of automatic coregistration of digital remote sensing images from different sources
topic digital remote sensing images
automatic image coregistration
multispectral images
radar images
url https://www.computeroptics.ru/eng/KO/Annot/KO48-6/480615e.html
work_keys_str_mv AT anborisov methodofautomaticcoregistrationofdigitalremotesensingimagesfromdifferentsources
AT vvmyasnikov methodofautomaticcoregistrationofdigitalremotesensingimagesfromdifferentsources
AT vvsergeev methodofautomaticcoregistrationofdigitalremotesensingimagesfromdifferentsources