Discriminative learning models for remote sensing
Date:
Seminar at IGN, the French National Mapping Agency, in the MATIS lab.
Abstract : in this talk I will talk about the use of machine learning models for scene understanding. Precisely, various discriminative approaches will be explored and applied to several practical use cases in remote sensing, ranging from satellite Earth-observation to low-altitude UAV mapping, and from various kinds of image data to 3D point-clouds. Building on the gain in performances and accuracy of the last years, we will show how it is now possible to semantize the world that surrounds us.