FN Archimer Export Format
PT J
TI Semantic Segmentation of Metoceanic Processes Using SAR Observations and Deep Learning
BT 
AF Colin, Aurélien
   Fablet, Ronan
   Tandeo, Pierre
   Husson, Romain
   Peureux, Charles
   Longépé, Nicolas
   Mouche, Alexis
AS 1:1,2;2:1;3:1,2;4:2;5:2;6:3;7:4;
FF 1:;2:;3:;4:;5:;6:;7:PDG-ODE-LOPS-SIAM;
C1 IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France
   Collecte Localisation Satellites, F-31520 Brest, France
   Φ-Lab Explore Office, ESRIN, European Space Agency (ESA), F-00044 Frascati, Italy
   Laboratoire d’Oceanographie Physique et Spatiale, Ifremer, F-31520 Brest, France
C2 IMT ATLANTIQUE, FRANCE
   CLS, FRANCE
   ESRIN, ITALY
   IFREMER, FRANCE
SI BREST
SE PDG-ODE-LOPS-SIAM
UM LOPS
IN WOS Ifremer UMR
   DOAJ
   copubli-france
   copubli-europe
IF 5
TC 10
UR https://archimer.ifremer.fr/doc/00751/86279/91605.pdf
LA English
DT Article
DE ;SAR;segmentation;metocean;deep learning;supervised learning;weakly-supervised learning;Sentinel-1
AB Through the Synthetic Aperture Radar (SAR) embarked on the satellites Sentinel-1A and Sentinel-1B of the Copernicus program, a large quantity of observations is routinely acquired over the oceans. A wide range of features from both oceanic (e.g., biological slicks, icebergs, etc.) and meteorologic origin (e.g., rain cells, wind streaks, etc.) are distinguishable on these acquisitions. This paper studies the semantic segmentation of ten metoceanic processes either in the context of a large quantity of image-level groundtruths (i.e., weakly-supervised framework) or of scarce pixel-level groundtruths (i.e., fully-supervised framework). Our main result is that a fully-supervised model outperforms any tested weakly-supervised algorithm. Adding more segmentation examples in the training set would further increase the precision of the predictions. Trained on 20 × 20 km imagettes acquired from the WV acquisition mode of the Sentinel-1 mission, the model is shown to generalize, under some assumptions, to wide-swath SAR data, which further extents its application domain to coastal areas. 
PY 2022
PD FEB
SO Remote Sensing
SN 2072-4292
PU MDPI AG
VL 14
IS 4
UT 000765116100001
DI 10.3390/rs14040851
ID 86279
ER

EF