Deep Learning for Ship Classification on Medium Resolution SAR Imagery - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

Deep Learning for Ship Classification on Medium Resolution SAR Imagery

Résumé

This research delves into the classification of maritime vessels, utilizing medium-resolution Synthetic Aperture Radar (SAR) imagery obtained from Sentinel-1, alongside Automatic Identification System (AIS) data streams. The investigation is specifically designed to address a ternary classification challenge involving three distinct ship categories: Tanker, Cargo, and Others. Leveraging a dataset comprising over 80,000 ship images, a Convolutional Neural Network (CNN) ensemble is applied. The results reveal a total classification accuracy of 79%.
Fichier principal
Vignette du fichier
Ship_classification_v12 (1).pdf (186.22 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04277648 , version 1 (09-11-2023)
hal-04277648 , version 2 (07-12-2023)

Licence

Domaine public

Identifiants

  • HAL Id : hal-04277648 , version 2

Citer

Bou Laouz Moujahid, Vadaine Rodolphe, Hajduch Guillaume, Ronan Fablet. Deep Learning for Ship Classification on Medium Resolution SAR Imagery. SeaSAR 2023 - workshop on Coastal and Marine applications of SAR, European Space Agency (ESA), May 2023, longyearbyen, Norway. pp.1-3. ⟨hal-04277648v2⟩
393 Consultations
222 Téléchargements

Partager

More