Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG

Charles Alban Deledalle, Loïc Denis, Florence Tupin, Sylvain Lobry

Research output: Chapter in Book/Report/Conference proceedingConference paper

1 Citation (Scopus)

Abstract

Due to speckle phenomenon, some form of filtering must be applied to SAR data prior to performing any polarimetric analysis. Beyond the simple multilooking operation (i.e., moving average), several methods have been designed specifically for PolSAR filtering. The specifics of speckle noise and the correlations between polarimetric channels make PolSAR filtering more challenging than usual image restoration problems. Despite their striking performance, existing image denoising algorithms, mostly designed for additive white Gaussian noise, cannot be directly applied to PolSAR data. We bridge this gap with MuLoG by providing a general scheme that stabilizes the variance of the polarimetric channels and that can embed almost any Gaussian denoiser. We describe MuLoG approach and illustrate its performance on airborne PolSAR data using a very recent Gaussian denoiser based on a convolutional neural network.

Original languageEnglish
Title of host publicationEUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages539-543
ISBN (Electronic)9783800746361
Publication statusPublished - 16 Aug 2018
Event12th European Conference on Synthetic Aperture Radar, EUSAR 2018 - Aachen, Germany
Duration: 4 Jun 20187 Jun 2018

Conference

Conference12th European Conference on Synthetic Aperture Radar, EUSAR 2018
CountryGermany
CityAachen
Period4/06/187/06/18

Fingerprint

Speckle
Stabilization
stabilization
Image denoising
random noise
Image reconstruction
restoration
Neural networks

Cite this

Deledalle, C. A., Denis, L., Tupin, F., & Lobry, S. (2018). Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG. In EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings (pp. 539-543). Institute of Electrical and Electronics Engineers Inc..
Deledalle, Charles Alban ; Denis, Loïc ; Tupin, Florence ; Lobry, Sylvain. / Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG. EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 539-543
@inproceedings{9fedf3b7b82e43a9b452e47bf3851470,
title = "Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG",
abstract = "Due to speckle phenomenon, some form of filtering must be applied to SAR data prior to performing any polarimetric analysis. Beyond the simple multilooking operation (i.e., moving average), several methods have been designed specifically for PolSAR filtering. The specifics of speckle noise and the correlations between polarimetric channels make PolSAR filtering more challenging than usual image restoration problems. Despite their striking performance, existing image denoising algorithms, mostly designed for additive white Gaussian noise, cannot be directly applied to PolSAR data. We bridge this gap with MuLoG by providing a general scheme that stabilizes the variance of the polarimetric channels and that can embed almost any Gaussian denoiser. We describe MuLoG approach and illustrate its performance on airborne PolSAR data using a very recent Gaussian denoiser based on a convolutional neural network.",
author = "Deledalle, {Charles Alban} and Lo{\"i}c Denis and Florence Tupin and Sylvain Lobry",
year = "2018",
month = "8",
day = "16",
language = "English",
pages = "539--543",
booktitle = "EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Deledalle, CA, Denis, L, Tupin, F & Lobry, S 2018, Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG. in EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings. Institute of Electrical and Electronics Engineers Inc., pp. 539-543, 12th European Conference on Synthetic Aperture Radar, EUSAR 2018, Aachen, Germany, 4/06/18.

Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG. / Deledalle, Charles Alban; Denis, Loïc; Tupin, Florence; Lobry, Sylvain.

EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 539-543.

Research output: Chapter in Book/Report/Conference proceedingConference paper

TY - GEN

T1 - Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG

AU - Deledalle, Charles Alban

AU - Denis, Loïc

AU - Tupin, Florence

AU - Lobry, Sylvain

PY - 2018/8/16

Y1 - 2018/8/16

N2 - Due to speckle phenomenon, some form of filtering must be applied to SAR data prior to performing any polarimetric analysis. Beyond the simple multilooking operation (i.e., moving average), several methods have been designed specifically for PolSAR filtering. The specifics of speckle noise and the correlations between polarimetric channels make PolSAR filtering more challenging than usual image restoration problems. Despite their striking performance, existing image denoising algorithms, mostly designed for additive white Gaussian noise, cannot be directly applied to PolSAR data. We bridge this gap with MuLoG by providing a general scheme that stabilizes the variance of the polarimetric channels and that can embed almost any Gaussian denoiser. We describe MuLoG approach and illustrate its performance on airborne PolSAR data using a very recent Gaussian denoiser based on a convolutional neural network.

AB - Due to speckle phenomenon, some form of filtering must be applied to SAR data prior to performing any polarimetric analysis. Beyond the simple multilooking operation (i.e., moving average), several methods have been designed specifically for PolSAR filtering. The specifics of speckle noise and the correlations between polarimetric channels make PolSAR filtering more challenging than usual image restoration problems. Despite their striking performance, existing image denoising algorithms, mostly designed for additive white Gaussian noise, cannot be directly applied to PolSAR data. We bridge this gap with MuLoG by providing a general scheme that stabilizes the variance of the polarimetric channels and that can embed almost any Gaussian denoiser. We describe MuLoG approach and illustrate its performance on airborne PolSAR data using a very recent Gaussian denoiser based on a convolutional neural network.

M3 - Conference paper

SP - 539

EP - 543

BT - EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Deledalle CA, Denis L, Tupin F, Lobry S. Speckle reduction in PolSAR by multi-channel variance stabilization and Gaussian denoising: MuLoG. In EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 539-543