Machine Learning is a transverse field that aims at extracting information from data in order to make decisions and predictions. I currently work to develop new architectures ( ShaResNet ), apply them various application fields from classification to cartography to 3D scene understanding to space wearther prediction.
Computational Geometry and reconstruction was the core area of my thesis. Understanding 3D scenes, and reconstructing abstracted surfaces is a major interest to me. I work on outdoor scenes ( Semantic3D ) as well as indoor data for robotics ( SUNRGB-D ).
at LIGM (ENPC), under the supervision of Renaud Marlet.
Subject: “Automatic reconstruction of 3D building information models”.
Previous research at ONERA
Earth Observation data is now massively available through satellite programs like Copernicus. This allows the emergence of new algorithms and techniques to cartography, analysis or restoration of multiple sensors active (SAR) or passive (optical) images. I am particularly interested in dealing with partially annoted data to create robust machine learning techniques abble to diggest multi-temporal data.
Some projects I have worked on while being a reasearcher at ONERA
DeLTA, deep machine learning for aerospace applications
Medusa for Big Data in Earth Observation
Inachus for Urban Search and Rescue