A speckle filter for Sentinel-1 SAR Ground Range Detected data based on Residual Convolutional Neural Networks

TL;DR

This paper introduces a novel deep learning-based speckle filter for Sentinel-1 SAR data, demonstrating significant improvements over existing methods in noise reduction and image quality metrics.

Contribution

It presents an effective CNN-based approach for speckle filtering that simplifies training data extraction and outperforms current state-of-the-art techniques.

Findings

Improved PSNR and SSIM metrics on simulated and real SAR data.

Enhanced image quality with higher ENL values.

Demonstrated effectiveness of CNN architecture for speckle noise reduction.

Abstract

In recent years, machine learning (ML) algorithms have become widespread in all the fields of remote sensing (RS) and earth observation (EO). This has allowed the rapid development of new procedures to solve problems affecting these sectors. In this context, this work aims at presenting a novel method for filtering speckle noise from Sentinel-1 ground range detected (GRD) data by applying deep learning (DL) algorithms, based on convolutional neural networks (CNNs). The paper provides an easy yet very effective approach to extract the large amount of training data needed for DL approaches in this challenging case. The experimental results on simulated speckled images and an actual SAR dataset show a clear improvement with respect to the state of the art in terms of peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), equivalent number of looks (ENL), proving the effectiveness of the proposed architecture.