English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Speckle reduction is a longstanding topic in synthetic aperture radar (SAR)images. Many different schemes have been proposed for the restoration ofintensity SAR images. Among the different possible approaches, methods based onconvolutional neural networks (CNNs) have recently shown to reachstate-of-the-art performance for SAR image restoration. CNN training requiresgood training data: many pairs of speckle-free / speckle-corrupted images. Thisis an issue in SAR applications, given the inherent scarcity of speckle-freeimages. To handle this problem, this paper analyzes different strategies onecan adopt, depending on the speckle removal task one wishes to perform and theavailability of multitemporal stacks of SAR data. The first strategy applies aCNN model, trained to remove additive white Gaussian noise from natural images,to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channelLOgarithm with Gaussian denoising). No training on SAR images is performed, thenetwork is readily applied to speckle reduction tasks. The second strategyconsiders a novel approach to construct a reliable dataset of speckle-free SARimages necessary to train a CNN model. Finally, a hybrid approach is alsoanalyzed: the CNN used to remove additive white Gaussian noise is trained onspeckle-free SAR images. The proposed methods are compared to otherstate-of-the-art speckle removal filters, to evaluate the quality of denoisingand to discuss the pros and cons of the different strategies. Along with thepaper, we make available the weights of the trained network to allow its usageby other researchers.

SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy