Semantic Segmentation of Metoceanic Processes Using SAR Observations and Deep Learning

Type Article
Date 2022-02
Language English
Author(s) Colin AurélienORCID1, 2, Fablet Ronan1, Tandeo Pierre1, 2, Husson Romain2, Peureux Charles2, Longépé Nicolas3, Mouche AlexisORCID4
Affiliation(s) 1 : IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France
2 : Collecte Localisation Satellites, F-31520 Brest, France
3 : Φ-Lab Explore Office, ESRIN, European Space Agency (ESA), F-00044 Frascati, Italy
4 : Laboratoire d’Oceanographie Physique et Spatiale, Ifremer, F-31520 Brest, France
Source Remote Sensing (2072-4292) (MDPI AG), 2022-02 , Vol. 14 , N. 4 , P. 851 (14p.)
DOI 10.3390/rs14040851
WOS© Times Cited 8
Note This article belongs to the Topic Big Data and Artificial Intelligence
Keyword(s) SAR, segmentation, metocean, deep learning, supervised learning, weakly-supervised learning, Sentinel-1

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.

Full Text
File Pages Size Access
Publisher's official version 14 1 MB Open access
Top of the page

How to cite 

Colin Aurélien, Fablet Ronan, Tandeo Pierre, Husson Romain, Peureux Charles, Longépé Nicolas, Mouche Alexis (2022). Semantic Segmentation of Metoceanic Processes Using SAR Observations and Deep Learning. Remote Sensing, 14(4), 851 (14p.). Publisher's official version : , Open Access version :