How to handle spatial correlations in SAR despeckling? Resampling strategies and deep learning approaches - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

How to handle spatial correlations in SAR despeckling? Resampling strategies and deep learning approaches

Abstract

Speckle noise strongly affects Synthetic Aperture Radar (SAR) images, causing strong intensity fluctuations that make them difficult to analyze. Although many speckle reduction algorithms have been proposed, how to effectively deal with the spatial correlations of speckle remains an open question, especially in the most recent deep learning approaches. This paper tries to address this problem. Existing approaches to tackle the speckle correlations are described. Then, a standard training strategy for deep learning is proposed. Two models are trained and the increased robustness brought by including a Total Variation (TV) term in the loss function is analyzed on Sentinel-1 images.
Fichier principal
Vignette du fichier
EUSAR2020denoisingreview.pdf (1.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02538046 , version 1 (09-04-2020)
hal-02538046 , version 2 (07-07-2021)

Identifiers

  • HAL Id : hal-02538046 , version 2

Cite

Emanuele Dalsasso, Loïc Denis, Florence Tupin. How to handle spatial correlations in SAR despeckling? Resampling strategies and deep learning approaches. EUSAR 2021: 13th European Conference on Synthetic Aperture Radar, Mar 2021, Leipzig (virtual), Germany. pp.1-6. ⟨hal-02538046v2⟩
325 View
593 Download

Share

Gmail Facebook X LinkedIn More