2022-08-25, 12:30–13:00 (Europe/Rome), Room Verde
OTBTF is a remote module of the Orfeo ToolBox enabling deep learning with remote sensing images.
Created in 2018, it aimed to provide a generic framework for various kind of raster-oriented deep-learning based applications.
Originally, OTBTF included user-oriented applications for patches sampling, model training, and inference on real world remote sensing images, and a few python scripts to help users with no coding skills to generate some ready-to-use models.
A few years later, it has been used for a wide range of applications, like landcover mapping at country scale, super-resolution, optical image cloud removal, etc.
This talk will present a few selected IA based applications powered by OTBTF in the framework of research projects, public policies support, or teaching.
We will present the recent features added in OTBTF and we are very happy to introduce what is next!
More details on the project on the github repository: github.com/remicres/otbtf
Rémi Cresson is with the French National Research Institute for Agriculture, Food and Environment. His research and engineering fields include remote sensing images processing at scale, high performance computing, machine learning, and geospatial data interoperability. He is member of the Orfeo ToolBox Project Steering Committee and charter member of the OSGeo foundation.