Nonlocal CNN SAR Image Despeckling
Open Access
- 20 March 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (6) , 1006
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.Keywords
This publication has 52 references indexed in Scilit:
- SAR Image Despeckling by Soft ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Coupling SAR C-Band and Optical Data for Soil Moisture and Leaf Area Index Retrieval Over Irrigated GrasslandsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Impacts of Feature Normalization on Optical and SAR Data Fusion for Land Use/Land Cover ClassificationIEEE Geoscience and Remote Sensing Letters, 2015
- NL-SAR: A Unified Nonlocal Framework for Resolution-Preserving (Pol)(In)SAR DenoisingIEEE Transactions on Geoscience and Remote Sensing, 2014
- How to Compare Noisy Patches? Patch Similarity Beyond Gaussian NoiseInternational Journal of Computer Vision, 2012
- Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based WeightsIEEE Transactions on Image Processing, 2009
- A Review of Image Denoising Algorithms, with a New OneMultiscale Modeling & Simulation, 2005
- SAR speckle reduction using wavelet denoising and Markov random field modelingIEEE Transactions on Geoscience and Remote Sensing, 2002
- Adaptive speckle filters and scene heterogeneityIEEE Transactions on Geoscience and Remote Sensing, 1990
- Speckle analysis and smoothing of synthetic aperture radar imagesComputer Graphics and Image Processing, 1981