Unsupervised Multistep Deformable Registration of Remote Sensing Imagery Based on Deep Learning
Open Access
- 29 March 2021
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 13 (7) , 1294
Abstract
Image registration is among the most popular and important problems of remote sensing. In this paper we propose a fully unsupervised, deep learning based multistep deformable registration scheme for aligning pairs of satellite imagery. The presented method is based on the expression power of deep fully convolutional networks, regressing directly the spatial gradients of the deformation and employing a 2D transformer layer to efficiently warp one image to the other, in an end-to-end fashion. The displacements are calculated with an iterative way, utilizing different time steps to refine and regress them. Our formulation can be integrated into any kind of fully convolutional architecture, providing at the same time fast inference performances. The developed methodology has been evaluated in two different datasets depicting urban and periurban areas; i.e., the very high-resolution dataset of the East Prefecture of Attica, Greece, as well as the high resolution ISPRS Ikonos dataset. Quantitative and qualitative results demonstrated the high potentials of our method.Keywords
This publication has 30 references indexed in Scilit:
- IC‐P‐174: Fast Automatic Segmentation of Hippocampal Subfields and Medial Temporal Lobe Subregions In 3 Tesla and 7 Tesla T2‐Weighted MRIAlzheimer's & Dementia, 2016
- Graph-Based Registration, Change Detection, and Classification in Very High Resolution Multitemporal Remote Sensing DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- A Multistage Approach for Image RegistrationIEEE Transactions on Cybernetics, 2015
- Efficient and Automated Multimodal Satellite Data Registration through MRFs and Linear Programming2014
- Automatic Descriptor-Based Co-Registration of Frame Hyperspectral DataRemote Sensing, 2014
- Deformable Medical Image Registration: A SurveyIEEE Transactions on Medical Imaging, 2013
- CO-REGISTRATION BETWEEN MULTISOURCE REMOTE-SENSING IMAGESThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- Multisensor image registration via implicit similarityIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Unbiased diffeomorphic atlas construction for computational anatomyNeuroImage, 2004
- A contour-based approach to multisensor image registrationIEEE Transactions on Image Processing, 1995