Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.telecom-paris.fr/hal-03129006
Contributor : Emanuele Dalsasso <>
Submitted on : Tuesday, February 2, 2021 - 3:51:25 PM
Last modification on : Sunday, March 7, 2021 - 3:16:32 AM

Links full text

Identifiers

  • 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. 2021. ⟨hal-03129006⟩

Share

Metrics

Record views

12