Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Communication dans un congrès

Despeckling Sentinel-1 GRD images by deep learning and application to narrow river segmentation

Abstract : This paper presents a despeckling method for Sentinel-1 GRD images based on the recently proposed framework "SAR2SAR": a self-supervised training strategy. Training the deep neural network on collections of Sentinel 1 GRD images leads to a despeckling algorithm that is robust to space-variant spatial correlations of speckle. Despeckled images improve the detection of structures like narrow rivers. We apply a detector based on exogenous information and a linear features detector and show that rivers are better segmented when the processing chain is applied to images pre-processed by our despeckling neural network.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal.telecom-paris.fr/hal-03129006
Contributeur : Emanuele Dalsasso Connectez-vous pour contacter le contributeur
Soumis le : mardi 2 février 2021 - 15:51:25
Dernière modification le : samedi 25 juin 2022 - 09:24:17

Lien texte intégral

Identifiants

  • HAL Id : hal-03129006, version 1
  • ARXIV : 2102.00692

Citation

Nicolas Gasnier, Emanuele Dalsasso, Loïc Denis, Florence Tupin. Despeckling Sentinel-1 GRD images by deep learning and application to narrow river segmentation. IGARSS 2021, Jul 2021, Bruxelles, Belgium. ⟨hal-03129006⟩

Partager

Métriques

Consultations de la notice

54