Deep learning for the semantic segmentation of SAR ocean images

When:
01/01/2020 – 02/01/2020 all-day
2020-01-01T01:00:00+01:00
2020-01-02T01:00:00+01:00

Annonce en lien avec l’Action/le Réseau : aucun

Laboratoire/Entreprise : Lab-STICC/CLS
Durée : 36 mois
Contact : ronan.fablet@imt-atlantique.fr
Date limite de publication : 2020-01-01

Contexte :
There is an overwhelming amount of data from Copernicus Sentinel-1 satellites. For instance, thousands
of images are produced every day representing a daily average of 3,45 TB SAR data published. A significant
amount covers ocean surface, used for a wide range of applications involving public and private
stakeholders. Notwithstanding the current great impact of Sentinel-1 images for the oceanographic
community, we believe the imaging capabilities of these C-band SAR data acquired over ocean surface are
not fully exploited.
Beyond wind field measurements, sea ice monitoring or oil spill detection, a set of metocean features are
well observed by S-1 sensors. To name a few, atmospheric fronts, oceanic fronts, rain cells, micro
convective cells, internal waves, gravity waves, biologic slicks, upwelling or wind streaks are phenomena
of potential interest for many end-users while being generally discarded in the SAR images. For academic
science and industry, new research perspectives and new potential applications/services could be
triggered with the proposed advanced monitoring of these metocean mechanisms. In addition, flagging
of these features could also benefit to current products/services providing better data quality. With recent
progress in computer vision thanks to Deep Learning approaches in conjunction with the rise of large
database and higher computing power, these flagging activities are now possible.

Sujet :
See detailed description in attached document or at:
http://sites.ieee.org/france-grss/files/2019/07/Thesis_CLS-IMT_DL-SAR.pdf

Profil du candidat :
Msc. or engineer degree in computer science, data science, applied maths, signal processing and/or remote sensing

Formation et compétences requises :
Skills:
o Master of Science (or equivalent) in Applied Mathematics, Computer Science or Machine (Deep) Learning
o Good programming skills (Python) with proven experience (i.e. github project)
o Ideally experience with cloud computing (Dockers, Kubernetes…)

• Know-how: fluency in written communication (writing technical notes and scientific articles – in
English in particular) and oral communication (presentation at contractual meetings or scientific
conferences), work organization, scientific rigor.

• Soft skills: Dynamism, enthusiasm, good interpersonal skills, autonomy, capacity for innovation,
taste for teamwork.

Adresse d’emploi :
lab-STICC, IMT Atlantique, Brest
CLS, Brest

Document attaché : Thesis_CLS-IMT_DL-SAR.pdf