Guided Patchwise Nonlocal SAR Despeckling

Vitale, Sergio; Cozzolino, Davide; Scarpa, Giuseppe; Verdoliva, Luisa; Poggi, Gianfranco

doi:10.1109/tgrs.2019.2906412

Cited by 46 publications

(63 citation statements)

References 47 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This kind of complementary evaluation was used in the seminal work by Buades et al [38] in the introduction of the nonlocal means filters. The use of such alternative approach for the case of multiplicative noise appears in [39] and, from that, many works include this analysis [15,37,40,41] to assess the filter performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Statistical Properties of an Unassisted Image Quality Index for SAR Imagery

2019

View full text Add to dashboard Cite

The M estimator is a recently proposed image-quality index used to evaluate the despeckling operation in SAR (Synthetic Aperture Radar) data. It is used also to rank despeckling filters and to improve their design. As a difference with traditional image-quality estimators, it operates not on the filtered result but on a derived one, i.e., the ratio image. However, a deep statistical analysis of its properties remains open and, with it, the ability to use it as a test statistic. In this work, we focus on obtaining insights into its distribution as well as on exploring other remarkable statistical properties of this unassisted estimator. This study is performed through EDA (Exploratory Data Analysis) and the well-known ANOVA (ANalysis Of VAriance). We test our results on a set of simulated SAR data and provide guides to enrich the M estimator to extend its capabilities.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Following this idea, Vitale et al [41] proposed a new second order component: RIS (Ratio Image Structuredness).…”

Section: Introductionmentioning

confidence: 99%

Statistical Properties of an Unassisted Image Quality Index for SAR Imagery

2019

View full text Add to dashboard Cite

show abstract

“…There is a unique exception for intensity, as estimated by the 7×7 refined Lee filter, for which the case of correlated noise is better than the decorrelated case. While all local spatial filters substantially share this behavior, nonlocal filters, e.g., [8,9,14], are expected to be more or less sensitive to correlation, depending on the landscape, because they may average samples that are more or less sparse within the search area surrounding the current pixel.…”

Section: Tests On Simulated Polsar Datamentioning

confidence: 99%

“…Bayesian estimators in either spatial [3,4] or wavelet domains [5][6][7] have long attained top performance. During recent years, the interest of scientists has progressively moved towards nonlocal [8,9] and deep-learning [10] approaches.…”

Section: Introductionmentioning

confidence: 99%

Accurate Despeckling and Estimation of Polarimetric Features by Means of a Spatial Decorrelation of the Noise in Complex PolSAR Data

et al. 2020

View full text Add to dashboard Cite

In this work, we extended a procedure for the spatial decorrelation of fully-developed speckle, originally developed for single-polarization SAR data, to fully-polarimetric SAR data. The spatial correlation of the noise depends on the tapering window in the Fourier domain used by the SAR processor to avoid defocusing of targets caused by Gibbs effects. Since each polarimetric channel is focused independently of the others, the noise-whitening procedure can be performed applying the decorrelation stage to each channel separately. Equivalently, the noise-whitening stage is applied to each element of the scattering matrix before any multilooking operation, either coherent or not, is performed. In order to evaluate the impact of a spatial decorrelation of the noise on the performance of polarimetric despeckling filters, we make use of simulated PolSAR data, having user-defined polarimetric features. We optionally introduce a spatial correlation of the noise in the simulated complex data by means of a 2D separable Hamming window in the Fourier domain. Then, we remove such a correlation by using the whitening procedure and compare the accuracy of both despeckling and polarimetric features estimation for the three following cases: uncorrelated, correlated, and decorrelated images. Simulation results showed a steady improvement of performance scores, most notably the equivalent number of looks (ENL), which increased after decorrelation and closely attained the value of the uncorrelated case. Besides ENL, the benefits of the noise decorrelation hold also for polarimetric features, whose estimation accuracy is diminished by the correlation. Also, the trends of simulations were confirmed by qualitative results of experiments carried out on a true Radarsat-2 image.

show abstract

“…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. SAR-optical fusion is arguably a major topic in remote sensing image processing [1][2][3][4]. Unfortunately, extracting reliable information from full-resolution (single-look) SAR images is a very difficult task due to the presence of intense multiplicative speckle noise.…”

Section: Introductionmentioning

confidence: 99%

Nonlocal CNN SAR Image Despeckling

et al. 2020

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Guided Patchwise Nonlocal SAR Despeckling

Cited by 46 publications

References 47 publications

Statistical Properties of an Unassisted Image Quality Index for SAR Imagery

Statistical Properties of an Unassisted Image Quality Index for SAR Imagery

Accurate Despeckling and Estimation of Polarimetric Features by Means of a Spatial Decorrelation of the Noise in Complex PolSAR Data

Nonlocal CNN SAR Image Despeckling

Contact Info

Product

Resources

About