Skip to Main content Skip to Navigation
Conference papers

SAR image despeckling through convolutional neural networks

Abstract : In this paper we investigate the use of discriminative model learning through Convolutional Neural Networks (CNNs) for SAR image despeckling. The network uses a residual learning strategy, hence it does not recover the filtered image, but the speckle component, which is then subtracted from the noisy one. Training is carried out by considering a large multitem-poral SAR image and its multilook version, in order to approximate a clean image. Experimental results, both on synthetic and real SAR data, show the method to achieve better performance with respect to state-of-the-art techniques.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01710036
Contributor : Giovanni Chierchia <>
Submitted on : Thursday, February 15, 2018 - 3:19:40 PM
Last modification on : Wednesday, February 26, 2020 - 7:06:07 PM
Long-term archiving on: : Tuesday, May 8, 2018 - 12:52:47 AM

File

1704.00275.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01710036, version 1

Citation

Giovanni Chierchia, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva. SAR image despeckling through convolutional neural networks. IEEE International Geoscience and Remote Sensing Symposium, Jul 2017, Fort Worth, Texas, United States. ⟨hal-01710036⟩

Share

Metrics

Record views

300

Files downloads

784