Сommon domain construction method for radar and optical Earth remote sensing images matching
Computer Optics · 01.06.2026
DOI: 10.18287/coj1980 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Optics, online erschienen am 01.06.2026. Verfasst von A.N. Borisov und 2 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Gefördert von: Ministry of Science and Higher Education of the Russian Federation.
Abstract (Originalsprache)
This paper presents a new method for constructing a common domain for digital Earth remote sensing images acquired by two types of sensors: a multispectral optical sensor and a synthetic aperture radar. After translation to a common domain, initially heterogeneous images become sufficiently similar to be coregistered by image matching methods, developed for standard images. The problem of constructing a common domain is considered as a task of simultaneous training of two U-Net neural networks. A proposed method is compared with an existing method based on the pix2pix generative neural network, which performs domain translation from the radar to the optical domain. Results of image matching using the well-known SIFT algorithm, the state-of-the-art RoMa and DeDoDe algorithms, and the RIFT2 heterogenous image matching algorithm are presented. Experimental studies demonstrate the clear advantage of a proposed method: a proposed method in combination with the trained RoMa network achieves the matching success rate of 99.9% with the average corner error of 0.84 pixels; pix2pix in combination with DeDoDe achieves the matching success rate of 98% with the average corner error of 4.3 pixels.
Förderung
- Ministry of Science and Higher Education of the Russian Federation
Zitieren
APA
Borisov, A., Myasnikov, V., & Sergeev, V. (2026). Сommon domain construction method for radar and optical Earth remote sensing images matching. Computer Optics. https://doi.org/10.18287/coj1980
Vancouver
Borisov A, Myasnikov V, Sergeev V. Сommon domain construction method for radar and optical Earth remote sensing images matching. Computer Optics. 2026. doi:10.18287/coj1980
BibTeX
@article{Borisov2026,
author = {Borisov, A.N. and Myasnikov, V.V. and Sergeev, V.V.},
title = {Сommon domain construction method for radar and optical Earth remote sensing images matching},
journal = {Computer Optics},
year = {2026},
doi = {10.18287/coj1980}
}
EUVIMED