THE DREAM DATABASE: A MULTIMODE DATABASE INCLUDING OPTICS, RADAR, DSM (SRTM) AND OSM LABELS FOR DEEP MACHINE LEARNING PURPOSES
Résumé
This paper describes a multimodal remote sensing database, called DREAM (Data Rang or EArth Monitoring), developed from open-source data. The method of development of the database is described, as well as its specificity. The database includes radar, optical, rasterized Open Street Map datasets, and DEM data for two types of landscapes: France and the United States. Already used in deep learning multimodal data registration and in style transfer simulation, this database can also be used for classification, speckle filtering, and image quality improvement needs.
Origine : Fichiers produits par l'(les) auteur(s)