A speckle filter for Sentinel-1 SAR Ground Range Detected data based on Residual Convolutional Neural Networks
This addresses the problem of noise reduction in remote sensing imagery for earth observation applications, representing an incremental advancement in applying deep learning to this domain.
The paper tackles speckle noise filtering in Sentinel-1 SAR data by proposing a residual convolutional neural network method, achieving clear improvements in metrics like PSNR, SSIM, and ENL compared to state-of-the-art approaches.
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.