Unsupervised Multistep Deformable Registration of Remote Sensing Imagery Based on Deep Learning

Maria Papadomanolaki (1, 2) , Stergios Christodoulidis (2) , Konstantinos Karantzalos (1) , Maria Vakalopoulou (2, 3)

1 NTUA - National Technical University of Athens [Athens]
2 MICS - Mathématiques et Informatique pour la Complexité et les Systèmes
3 OPIS - OPtimisation Imagerie et Santé

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.

Mots clés: spatial gradients; deformation; satellite; very high resolution imagery; urban and peri-urban; learning-based registration; dense displacements; alignment

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Maria Papadomanolaki, Stergios Christodoulidis, Konstantinos Karantzalos, Maria Vakalopoulou. Unsupervised Multistep Deformable Registration of Remote Sensing Imagery Based on Deep Learning. Remote Sensing, 2021, 13 (7), ⟨10.3390/rs13071294⟩. ⟨hal-03538150⟩