FN Archimer Export Format
PT J
TI Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval
BT 
AF Ristea, Nicolae-Cătălin
   Anghel, Andrei
   Datcu, Mihai
   Chapron, Bertrand
AS 1:1;2:1;3:2;4:3;
FF 1:;2:;3:;4:PDG-ODE-LOPS-SIAM;
C1 Research Center for Spatial Information (CEOSpaceTech) and the Department of Telecommunications, University Politehnica of Bucharest, Bucharest, Romania
   Research Center for Spatial Information (CEOSpaceTech), University Politehnica of Bucharest, Bucharest, Romania
   Laboratoire d'Ocanographie Physique et Spatiale (LOPS), Plouzané, Ifremer, France
C2 UNIV POLITEHNICA BUCHAREST, ROMANIA
   UNIV POLITEHNICA BUCHAREST, ROMANIA
   IFREMER, FRANCE
SI BREST
SE PDG-ODE-LOPS-SIAM
UM LOPS
IN WOS Ifremer UMR
   copubli-europe
IF 8.2
TC 3
UR https://archimer.ifremer.fr/doc/00840/95206/102904.pdf
LA English
DT Article
DE ;Radar polarimetry;Image retrieval;Doppler effect;Synthetic aperture radar;Transformers;Task analysis;Sea surface;Doppler centroid estimation (DCE);image retrieval;ocean imagery;remote sensing (RS);subapertures decomposition;synthetic aperture radar (SAR);unsupervised learning
AB A spaceborne synthetic aperture radar (SAR) can provide accurate images of the ocean surface roughness day-or-night in nearly all-weather conditions, being a unique asset for many geophysical applications. Considering the huge amount of data daily acquired by satellites, automated techniques for physical features extraction are needed. Even if supervised deep learning methods attain state-of-the-art results, they require a great amount of labeled data, which are difficult and excessively expensive to acquire for ocean SAR imagery. To this end, we use the subaperture decomposition (SD) algorithm to enhance the unsupervised learning retrieval on the ocean surface, empowering ocean researchers to search into large ocean databases. We empirically prove that SD improves the retrieval precision with over 20% for an unsupervised transformer autoencoder network. Moreover, we show that SD brings an important performance boost when Doppler centroid images are used as input data, leading the way to new unsupervised physics-guided retrieval algorithms. 
PY 2023
SO Ieee Transactions On Geoscience And Remote Sensing
SN 0196-2892
PU Institute of Electrical and Electronics Engineers (IEEE)
VL 61
IS 5207111
UT 000996488200015
DI 10.1109/TGRS.2023.3272279
ID 95206
ER

EF