PolSAR (Fully Polarimetric Synthetic Aperture Radar) imagery is used in Earth observation and remote sensing for various applications such as land use and land cover classification, change detection, etc. The occurrence of speckle in PolSAR images, however, degrades the performance of all image processing techniques and therefore prevents their full use for various applications. Several speckle reduction methods have been developed in the literature over the last forty years, highlighting the importance of this issue. Despite this extensive knowledge, speckle removal is yet an open problem that is far from being fully solved. Recently, Deep Learning (DL) has achieved great success in speckle reduction of SAR images. The data-driven nature of this technique provides improved flexibility and the ability to capture a variety of features from PolSAR images, thereby enhancing the performance of the speckle reduction process. In this paper, a new despeckling technique is proposed in the context of deep convolutional neural networks for de-noising the polarimetric covariance or coherence matrix. The method controls the training process with respect to several characteristic features of PolSAR images defined by the combination of three different cost functions. In particular, the goal is to balance the different features, including spatial details and speckle statistical properties, in the denoising process. The proposed method is experimentally validated with real airborne datasets and compared with existing despeckling approaches.

Synthetic aperture radar (SAR) interferometry (InSAR) has shown great potential in the monitoring of Earth’s surface and detection of the possible slow temporal deformations. Within the framework of multibaseline SAR interferometry, the availability of multiple interferograms obtained from multipass satellite observations can significantly improve the accuracy of the estimated target parameters, i.e., the residual height and the mean deformation velocity. The parameters can be estimated in the maximum likelihood (ML) sense and through the data covariance matrix. However, the presence of artifact and outliers may impair the parameter estimation, specifically when the candidate cells are subject to temporal decorrelation and atmospheric phase noise effects. In this letter, the exploitation of contextual spatial information is proposed to reduce the possible ambiguity and improve the accuracy of ML-based parameter estimation. The proposed approach adds a regularization term (or a constraint) to the ML’s model in order to include the information about the scene velocity variation. Hence, the resulted nonconvex optimization is resolved using the graph-cut concept. The method is evaluated using the simulated and two real data sets acquired by Constellation of Small Satellites for Mediterranean basin Observation (COSMO-SkyMed) and Sentinel-1A sensors over Tehran, Iran; and the results are validated using the global positioning system-based measurements.

Among the large number of synthetic aperture radar (SAR) image despeckling approaches existing in literature, nonlocal (NL) filters have received a desirable boost. However, often NL approaches define the similarity criterion based on model assumptions, such as a fully developed speckle model. This assumption may not be verified in high-resolution images of urban environments. To address this issue, a standalone model-free despeckling framework is proposed in this article. The presented approach provides a generic framework for denoising a variety of SAR products, from a single-intensity/amplitude image to polarimetric and interferometric SAR data. In particular, the method is based on the empirical distributional similarity between the patch containing the pixel to be recovered and the patch containing a similar candidate pixel. To decide whether the patches follow a similar distribution, the Kolmogorov–Smirnov test is adapted. Finally, the restoration process aggregates the selected similar pixels based on their relative importance derived from their distribution similarities. To mitigate the blurring effect and preserve the resolution, the inhomogeneity of the ratio image is used to perform the bias reduction step. The designed generic despeckling filter was tested on different products of SAR data. The results show that the method proves to be an unbiased restoration approach and is able to preserve structures and textures. It works fully automatically and efficiently with single and multilook (and multichannel) images.

This paper addresses the 3D classification of superimposed target scattering mechanisms in polarimetric synthetic aperture radar (SAR) images of urban environments. Theoretically, the solution of this problem is possible with polarimetric tomographic SAR focusing techniques. In this work, we investigate how SAR Tomography (TomoSAR) can be used to identify and distinguish the superimposed target mechanisms. In particular, various strategies are employed to separate and characterize the polarimetric scattering patterns of targets in layover regions. Extensive and comparative analyses are performed to answer how accurately different strategies can identify the polarimetric scattering pattern.

Among available methods for geodetic measurements, synthetic aperture radar (SAR) interferometry (InSAR) has been considered as a powerful tool for the monitoring of earth's surface, digital elevation model generation and possible slow temporal deformation mapping. In this context, multi-baseline SAR interferometry with the availability of multiple interferograms obtained from multi-pass satellite observations significantly improves the accuracy of the estimated target's parameters, i.e. the residual height and the mean deformation velocity. In this paper contextual spatial information has been exploited as a regularization term in order to improve the capability of multibaseline SAR Interferometry in dealing with possible artifacts and outliers induced by temporal decorrelation and remained atmospheric phase noise effects which can impair the accuracy of estimated target's parameters. The superiority of regularized processing is related to depletion of velocity variations over the scene and reducing ambiguity in parameter estimation. The proposed method is evaluated using a simulated and a real data set acquired by COSMO-SkyMed sensor over Tehran, Iran; and the results are compared with conventional adapted approach in the literature. The evaluation indicated that adaptation of contextual information can significantly improve the interferometric-based parameter estimation over partially coherent targets which are affected by outliers and artifacts.