Back to Search
Start Over
A Multiscale Framework With Unsupervised Learning for Remote Sensing Image Registration.
- Source :
-
IEEE Transactions on Geoscience & Remote Sensing . May2022, Vol. 60, p1-15. 15p. - Publication Year :
- 2022
-
Abstract
- Registration for multisensor or multimodal image pairs with a large degree of distortions is a fundamental task for many remote sensing applications. To achieve accurate and low-cost remote sensing image registration, we propose a multiscale framework with unsupervised learning, named MU-Net. Without costly ground truth labels, MU-Net directly learns the end-to-end mapping from the image pairs to their transformation parameters. MU-Net stacks several deep neural network (DNN) models on multiple scales to generate a coarse-to-fine registration pipeline, which prevents the backpropagation from falling into a local extremum and resists significant image distortions. We design a novel loss function paradigm based on structural similarity, which makes MU-Net suitable for various types of multimodal images. MU-Net is compared with traditional feature-based and area-based methods, as well as supervised and other unsupervised learning methods on the optical-optical, optical-infrared, optical-synthetic aperture radar (SAR), and optical-map datasets. Experimental results show that MU-Net achieves more comprehensive and accurate registration performance between these image pairs with geometric and radiometric distortions. We share the code implemented by Pytorch at https://github.com/yeyuanxin110/MU-Net. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01962892
- Volume :
- 60
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Geoscience & Remote Sensing
- Publication Type :
- Academic Journal
- Accession number :
- 157582500
- Full Text :
- https://doi.org/10.1109/TGRS.2022.3167644