Synthetic Datasets and Evaluations for Sub-pixel Displacements Estimation from Optical Satellite Images with Deep Learning
Fiche du document
Auteur
Date
26 octobre 2023
Discipline
Types de document
Périmètre
Langue
Identifiant
- doi: 10.57745/UOGRPY
Source
Collection
Mots-clés
Earth and Environmental Sciences satellite remote sensing satellite imagery deep learning geodesy earthquake tectonicsSujets proches
Learning process Scholarship LearningCiter ce document
Tristan Montagnon, « Synthetic Datasets and Evaluations for Sub-pixel Displacements Estimation from Optical Satellite Images with Deep Learning », Recherche Data Gouv, ID : 10.57745/UOGRPY
Métriques
Partage / Export
Résumé
Contains 3 synthetic datasets (UNI, DIS, UNI-5px), with three corresponding trained models, based on a CNN architecture. The three datasets contains pairs of small (either 16x16 or 32x32 pixels) windows that simulate shifts. Contains also evaluations on realistic synthetics examples of a deep learning pipeline using two of the three models presented.