Nonlocal CNN SAR Image Despeckling

Davide Cozzolino,Giovanni Poggi,Giuseppe Scarpa,Luisa Verdoliva

doi:10.3390/rs12061006

Abstract

We propose a new method for SAR image despeckling, which performs nonlocal filtering with a deep learning engine. Nonlocal filtering has proven very effective for SAR despeckling. The key idea is to exploit image self-similarities to estimate the hidden signal. In its simplest form, pixel-wise nonlocal means, the target pixel is estimated through a weighted average of neighbors, with weights chosen on the basis of a patch-wise measure of similarity. Here, we keep the very same structure of plain nonlocal means, to ensure interpretability of results, but use a convolutional neural network to assign weights to estimators. Suitable nonlocal layers are used in the network to take into account information in a large analysis window. Experiments on both simulated and real-world SAR images show that the proposed method exhibits state-of-the-art performance. In addition, the comparison of weights generated by conventional and deep learning-based nonlocal means provides new insight into the potential and limits of nonlocal information for SAR despeckling.

Highlights

Synthetic Aperture Radar (SAR) images are becoming more and more relevant for a large number of applications
We propose a new method for SAR image despeckling, which performs nonlocal filtering with a deep learning engine
In [31], we proposed to use nonlocal means filtering with weights computed patch-by-patch by means of a dedicated convolutional neural networks (CNN), so as to compare the weights provided by the network with those output by conventional nonlocal methods

Summary

Introduction

Synthetic Aperture Radar (SAR) images are becoming more and more relevant for a large number of applications. They represent a perfect complement to optical remote sensing images, because of their completely unrelated imaging mechanisms and their ability to ensure all-time all-weather coverage. Further problems arise because of the non-stationary nature of noise, and the peculiar statistics of SAR images, markedly different from those of natural images. In this challenging scenario, a SAR despeckling technique should satisfy multiple contrasting requirements, as outlined in [5]: 1. A SAR despeckling technique should satisfy multiple contrasting requirements, as outlined in [5]: 1. suppress most of the speckle in homogeneous regions; 2. preserve textures; 3. preserve region boundaries and other linear structures; 4. avoid altering natural or man-made permanent scatterers; and 5. avoid introducing filtering artifacts

Objectives

Methods

Discussion

Conclusion