Skip to main content
Publications | Persons | Institutes | Projects
[ report an error in this record ]basket (1): add | show Print this page

one publication added to basket [391532]
D4SC: deep supervised semantic segmentation for seabed characterization in low-label regime
Arhant, Y.; Tellez, O.L.; Neyt, X.; Pizurica, A. (2023). D4SC: deep supervised semantic segmentation for seabed characterization in low-label regime, in: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. pp. 6932-6935. https://dx.doi.org/10.1109/IGARSS52108.2023.10282903
In: (2023). IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. IEEE: USA. ISBN 979-8-3503-3174-5; e-ISBN 979-8-3503-2010-7. ccxxxvi, 4791 pp. https://dx.doi.org/10.1109/IGARSS52108.2023, more

Available in  Authors 
Document type: Conference paper

Keyword
    Marine/Coastal
Author keywords
    Seabed; Semantic Segmentation; Synthetic Aperture Sonar; Deep Learning

Authors  Top 

Abstract

    Seabed characterisation consists in the study of the physical and biological properties of the bottom of the oceans. It is effectively achieved with sonar, a remote sensing method that captures acoustic backscatter of the seabed. Classical Machine Learning (ML) and Deep Learning (DL) research have failed to successfully address the automatic mapping of the seabed from noisy sonar data. This work introduces the Deep Supervised Semantic Segmentation model for Seabed Characterisation (D4SC), a novel U-Net-like model tailored to such data and low-label regime, and proposes a new end-to-end processing pipeline for seabed semantic segmentation. That dual contribution achieves state-of-the-art results on a high resolution Synthetic Aperture Sonar (SAS) survey dataset.


All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors