Address:
M. Aurélien COLIN from Mathematical and Electrical Engineering department (MEE) and Labsticc Laboratory, will present his research about :
" On the use of Deep learning for ocean SAR image semantic segmentation "
With water covering 71\% of the surface of the Earth, and most meteorological processes steming from the oceans, their observation is primordial to enhance our comprehension of the Earth system, ameliorate the meteorological models and prevent hazards. Since ERS-1 (launched in 1991), C-Band Synthetic Aperture Radar (SAR) has been used to observe the ocean surfaces. This particular electromagnetic band is especially useful to derive information on waves, winds, precipitations, sea ice... at meso- and sub-mesoscale.
The subject of this thesis is the segmentation, the pixel-per-pixel classification, of the ocean surface C-Band SAR observations. The generation of segmentation maps is possible through the use of machine learning frameworks able to extract information from the large data volume produced by the satellites Sentinel-1A and Sentinel-1B launched respectively 2014 and 2016 as part of ESA's Copernicus program. These observations are colocalized with third-party sensors (ground stations, buoys, satellite-boarded instruments), manually annotated segmentations or meteorological models to be able to train deep learning models and ensure their capacity through extensive tests.
These studies show promising uses of new SAR-derived information and propose guidelines for building dedicated segmentation datasets and models.
Organizer(s)
Thesis acreditation from IMT Atlantique with the Doctoral School MATHSTIC
Key-words: Remote Sensing, Synthetic Aperture Radar, Deep Learning, Oceanography