Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval

  title={Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval},
  author={Nicolae-Cuatualin Ristea and Andrei Anghel and Mihai Datcu and Bertrand Chapron},
—Spaceborne synthetic aperture radar (SAR) can provide accurate images of the ocean surface roughness day-or-night in nearly all weather conditions, being an 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 great amount of labeled data, which are difficult and excessively expensive… 

Figures and Tables from this paper



Guided Deep Learning by Subaperture Decomposition: Ocean Patterns from SAR Imagery

Spaceborne synthetic aperture radar (SAR) can provide meters-scale images of the ocean surface roughness day-or-night in nearly all weather conditions. This makes it a unique asset for many

Classification of the global Sentinel-1 SAR vignettes for ocean surface process studies

Segmentation of Sentinel-1 SAR Images Over the Ocean, Preliminary Methods and Assessments

An assessment of deep learning frameworks is performed, with a focus on the comparison between weakly supervised and supervised methods, and metrics based on the Wassertein distance indicate best performances by the supervised segmentation (U-Net) given operational constraints, thus highlighting the significance of properly annotated data sets.

Prediction of Categorized Sea Ice Concentration From Sentinel-1 SAR Images Based on a Fully Convolutional Network

This article investigates the potential of a fully convolutional network (FCN) for the automatic estimation of sea ice concentration (SIC) and shows the FCN model to be evenly robust to sea ice seasonal variability and incidence angle.

Deep Learning for Predicting Significant Wave Height From Synthetic Aperture Radar

A data set of collocations between SAR and altimeter satellites is curated and the use of deep learning is investigated to predict significant wave height from SAR, demonstrating on test data from 2018 that deep learning reduces the state-of-the-art root mean squared error by 50%, from 0.6 to 0.3 m.

Deep-learning-based information mining from ocean remote-sensing imagery

This review paper first systematically reviewed two deep-learning frameworks that carry out ocean remote-sensing-image classifications and then presented eight typical applications in ocean internal-wave/eddy/oil-spill/coastal-inundation/sea-ice/green-algae/ship/coral-reef mapping from different types of oceanRemote-Sensing imagery to show how effective these deep- learning frameworks are.

Exploring Vision Transformers for Polarimetric SAR Image Classification

As one of the most popular topics in polarimetric synthetic aperture radar (PolSAR) community, PolSAR image classification has always been an important way for PolSAR applications. Constructing

Opportunistic Bistatic SAR Image Classification Using Sub-aperture Decomposition

The proposed framework is based on the use of sub-aperture decomposition of the backscatter in order to create the feature vector and the goal is to identify different scatterer signatures and associate them to specific semantic labels.

A labelled ocean SAR imagery dataset of ten geophysical phenomena from Sentinel‐1 wave mode

The Sentinel‐1 mission is part of the European Copernicus program aiming at providing observations for Land, Marine and Atmosphere Monitoring, Emergency Management, Security and Climate Change. It is

Comparison of CNNs and Vision Transformers-Based Hybrid Models Using Gradient Profile Loss for Classification of Oil Spills in SAR Images

GP loss turns out to be a promising loss function in the context of deep learning with SAR images and significantly improves the mIoU and F1 scores for CNNs as well as ViTs-based hybrid models.