SAR image despeckling using pre-trained convolutional neural network models - Télécom Paris
Communication Dans Un Congrès Année : 2019

SAR image despeckling using pre-trained convolutional neural network models

Xiangli Yang
  • Fonction : Auteur
L. Denis
Wen Yang
  • Fonction : Auteur

Résumé

Despeckling is a longstanding topic in synthetic aperture radar (SAR) imaging. Many different schemes have been proposed for the restoration of SAR images. Among the different possible strategies, the methods based on convolutional neural networks (CNNs) have shown to produce state-of-the-art results on SAR image restoration. However, to learn an effective model it is necessary to collect a large number of speckle-free SAR images for training. To bypass this problem, we propose to directly use pre-trained CNN models on additive white Gaussian noise (AWGN) and transfer them to process SAR speckle. To include such CNNs Gaussian denoisers, we use the multi-channel logarithm approach with Gaussian denoising (MuLoG). Experimental results, both on synthetic and real SAR data, show the method achieves good performance.
Fichier non déposé

Dates et versions

hal-02292438 , version 1 (19-09-2019)

Identifiants

Citer

Xiangli Yang, L. Denis, Florence Tupin, Wen Yang. SAR image despeckling using pre-trained convolutional neural network models. 2019 Joint Urban Remote Sensing Even, May 2019, Vannes, France. ⟨10.1109/jurse.2019.8809023⟩. ⟨hal-02292438⟩
75 Consultations
0 Téléchargements

Altmetric

Partager

More