Multibaseline and tomographic synthetic aperture radar (SAR) data are often affected by phase distortions known as phase screens. These distortions stem either from atmospheric effects or residual errors in platform motion. Calibrating and compensating for the phase screen is crucial to prevent spreading and defocusing in multidimensional tomographic imaging. Given the growing interest in artificial intelligence and deep learning, we aim to utilize their potential to develop a phase calibration process for SAR tomographic data. Our proposed framework is based upon a convolutional neural network (CNN) and generates training patches directly from the tomographic images under consideration, without relying on external references or resources. Once trained, the network effectively estimates phase distortions across the entire image; these are then used to calibrate the tomographic data. Experimental results from AfriSAR and UAVSAR tomographic datasets are included to showcase the effectiveness of the proposed solution.

In the above article [1], the correct reference associated with equation (2) on page 3, left column, is the below paper: 1) P. Imperatore and G. Fornaro, “Joint Phase-Screen Estimation in Airborne Multibaseline SAR Tomography Data Processing,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–14, 2024, Art. no. 4412614, doi: 10.1109/TGRS.2024.3446186.

The proposal of deep learning (DL) solutions for SAR image despeckling is recently widespread. Such solutions have been mainly designed in a DL perspective by leveraging the training and validation stage on the use of typical norm-based cost functions. For going beyond the DL perspective, in this paper we propose a SAR based validation stage by using SAR assessing metrics in the design and hyper-parameter selection of neural networks. In a first phase, SAR assessing metrics may be used only as validation metrics with the aim of highlighting critical issues that can not be spotted with standard image-processing quality metrics. In a second phase, the same SAR assessing metrics may be used directly for enhancing the DL solution by the addressing specific issues arisen during the previous SAR based validation stage. To this aim, three different DL SAR despeckling solutions and four different SAR assessing metrics have been considered. The outcome of this analysis shows the importance of including SAR knowledge in the training and validation stages of the design of a DL solution for SAR image despeckling.

This paper addresses the phase miscalibration within the broader scope of tomographic synthetic aperture radar (SAR) image focusing. Phase errors, typically independent from one acquisition to another, result in a dispersion and defocusing effect in the multi-dimensional imaging space. Dealing with this issue, particularly in the presence of volumetric scattering, poses a significant challenge. In this paper, we propose a novel framework for phase calibration in tomographic data. Our proposed framework employs deep learning solutions to estimate calibration phases, eliminating the need for model assumptions, external data sources, or phase unwrapping. In this approach, training data patch are directly derived from the data under consideration. Post-training, the network can effectively mitigate atmospheric phase screens or calibrate individual interferograms. Experimental results are included to demonstrate the effectiveness of the proposed method.

Synthetic Aperture Radar (SAR) serves as a fundamental system for Earth observation. Specifically, Polarimetric SAR (PolSAR) sensors capture images of diverse polarization scenes, enhancing the retrievable information. Due to their coherent nature, SAR images represent complex data affected by multiplicative noise known as speckle. The presence of this noise impedes image interpretation, making speckle removal a crucial pre-processing step for further applications. Recently, various Deep Learning (DL)-based methods have been proposed for speckle removal in PolSAR data, relying on different strategies for constructing training datasets. This complicates practical comparisons due to the absence of ground truth. In this paper, a comparison of the impact of different PolSAR despeckling methods on classification applications is studied. Some different PolSAR despeckling filters shows the different ability on improving the classification. In general, DL-based methods have greater improvement ability and potential.

The status of coastal zones has a great impact on economy and population and, therefore, the monitoring of shoreline is a crucial task. In order to have a wide scale and rapid monitoring, remote sensing represents a perfect opportunity, In particular, the ability of working all day in any meteorological conditions makes Synthetic aperture radar (SAR) system attractive for such task. At the same time, the ability of rapidly processing huge data makes deep learning an appealing solution. The aim of this work is to examine the effectiveness and potential of utilizing a deep learning solution for identifying and extracting coastlines from satellite SAR images. Firstly, a specific training dataset has been created using SAR data and ancillary information for retrieving position of coastline. Finally, the shoreline extraction has been performed as deep learning based segmentation task.

SAR despeckling is a fundamental task for improving the interpretation of SAR images and the performance of further tasks (classification and detection). The spreading of deep learning solutions has highlighted one main common issue: the availability of a training dataset. The construction of a training dataset is, indeed, limited by the absence of real ground truth. In this paper, an analysis of different approaches for constructing training dataset based on either fully simulation or real data has been carried out. The results show the importance of including real data properties within the training dataset.

Synthetic Aperture Radar (SAR) are fundamental tools for target classification and detection in the different applicative scenarios (military, agriculture, etc…). Extracting geometrical features of a target strongly help in its detection and classification. Indeed, the extraction of Attribute Scattering Center (ASC) characteristics is widely used from improving SAR target recognition. ASC extraction is a challenging task that requires the accurate estimation of tiny details (shape, orientation, etc…) from the SAR target backscattering. In this work, the aim is to exploit the potential of deep learning for ASC extraction. Considering a simulated environment, a deep-learning based classification solution is defined for extracting the target characteristics.We proposed a multi classification heads VGG solution, which can extract scattering parameters from complex images and also guarantee the estimation accuracy.

The building height estimation of urban environments is a challenging problem for Synthetic Aperture Radar (SAR). SAR Tomography (TomoSAR) conducts a series of acquisitions to realize a 3D reconstruction. Classical 3D focusing algorithms’ performance tends to be affected by the limited number of acquisitions, and the uneven baselines. Inspired by the advanced performance of TSNN on forest height estimation, in this study, we apply TSNN to reconstruct building height and we compare the obtained results with a classical Tomography approach. The experimental results are based on the data acquired by the DLR’s ESAR sensor at L-band over Dresden, Germany. The results illustrate the possibility of using the deep learning-based approach for building height estimation on urban environments.

Forest measurement is crucial for tracking climate change and quantifying the global carbon cycle. Synthetic Aperture Radar Tomography has become an effective technique to realize 3D forest structure monitoring. Recently a Deep Learning approach, named TomoSAR Neural Network (TSNN), has been proven a valid method for forest height and underlying topography estimation with polarimetric TomoSAR data. In this study, we evaluate the generalization ability of TSNN in working in different target areas, with different sensors and acquisition parameters. The experimental results demonstrate the robustness and generalization ability of TSNN.

Polarimetric Synthetic Aperture Radar (PolSAR) data plays an important role in Earth observation. In this field, deep learning (DL) method can achieve high classification performance on PolSAR image dataset and, in particular, vision transformer(ViT) has achieved significant breakthroughs. Compared with convolutional layers, ViT is able to extract global feature and find the global relationship, which can help to improve the performance of classification. The aim of this work is to exploit the potential of ViT for PolSAR classification. In this case, we propose a simple classification method based on transformer, called Pol-Trans. The PolSAR data is pre-processed to get the coherency matrix. Then the image patch of the pixel to be classified is flattened as the tokens. Finally, with the class embedding, our transformer can output the classification result of the PolSAR data. Our experiments on the ALOS2 PolSAR dataset of San Francisco shows the effectiveness of our method.

Synthetic aperture radar (SAR) are fundamental system for Earth Observation. In particular, polarimetric SAR (PolSAR) sensors provide images of a scene at different polarizations, enriching the information that can be retrieved. Due to their coherent nature, SAR images are complex data affected by a multiplicative noise, called speckle. The presence of this noise hinders the interpretation of images, making speckle removal a fundamental preprocessing step for further applications. Several deep learning (DL)-based approaches have been recently proposed for speckle removal in PolSAR data relying, due to the lack of a real ground truth, on different strategies for constructing training datasets making a real comparison complicated. In this work, a study on the construction of a training dataset for PolSAR despeckling is proposed. In particular, considering the analysis recently conducted on the construction of the dataset for training supervised neural networks for SAR amplitude despeckling, the aim is to extend such studies to the PolSAR case. In particular, the commonly used multitemporal approach, relying on the stack of real data, is compared with the so-called hybrid approach, in which a mixture of real and synthetic data is proposed. A specific DL solution has been chosen for such comparison, but the analysis could be extended to whatever supervised neural network. Moreover, for the sake of completeness, results are also compared with a well-assessed PolSAR despeckling filter in the literature.

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images, compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Surface deformation caused by an earthquake is crucial for a better understanding of the development of geological structures and seismic hazards in an active tectonic area. On September 24, 2019, an earthquake with a magnitude of 5.6 Mw and a depth of 10 km struck Mirpur, Pakistan, causing significant damage. The study area is already facing numerous problems due to natural hazards, and the additional surface deformations caused by this earthquake have further increased its vulnerability. The objective of this study was to estimate the surface deformation associated with the earthquake. InSAR analysis was applied to 10 Sentinel-1A SAR images captured between July 30, 2019, and October 22, 2019, resulting in the generation of 7 interferograms that provided information on ground displacement caused by the earthquake. The estimated deformation range showed approximately -8 cm of subsidence and a 20 cm uplift of the surface along the line of sight (LOS). Vertical deformation was also estimated to range from -3 cm to 17 cm.

SAR (Synthetic Aperture Radar) sensors are fundamental tools for the Earth Observation. Actually, SAR images are affected by a multiplicative noise speckle that require a filtering step crucial for further application: classification, detection, etc. As in all image processing task, deep learning has been widely used for SAR image despeckling in the last years. Many methods have been proposed with different architectures, cost functions, training approaches, showing impressive performance. Actually, differently from natural domain denoising, an extensive comparison of such methods is still missing. As matter fact, such methods focus their comparison on few testing images. The aim of this paper is to propose and carry out the comparison among DL (Deep Learning) based methods not only in the testing phase but explointg the validation dataset used during the training for evaluating performance on SAR based metrics. The aim is to give an assessment on a more wide scenarios.

Synthetic Aperture Radar (SAR) are fundamental systems for the Earth Observation, providing images in any meteorological condition, during day and night. Due to their coherent nature, SAR images are complex data affected by a multiplicative noise called speckle impairing their interpretation. Therefore, speckle removal is a fundamental task for further applications. Following the interesting results obtained for single-channel despeckling, a deep learning approach is proposed for Polarimetric SAR (PolSAR) despeckling. In particular, the aim is to extend the outcome obtained on the construction of the dataset for SAR amplitude despeckling to the PolSAR case. In order to take fully advantage of such approach a multi-objective neural network has been considered. In particular, the hybrid approach has been used for creating a dataset for training a network following supervised approach. Comparison with state of art methods on real PolSAR images have shown the good versatility of such approach: the hybrid approach together with the multi-objective cost function lead the network to a good trade-off between noise suppression and texture preservation.

Forests play an important role in the global carbon cycle, and subsequently global climate change. Synthetic Aperture Radar Tomography (TomoSAR) can achieve three-dimensional forest structures relying on the multibaseline image acquisition. At present, plenty of TomoSAR approaches are based on fully polarimetric TomoSAR datasets which require costly data acquisition. The aim of this paper is to exploit the potential of deep learning for retrieving forest height by using single polarimetric data, going beyond the limitation of the requirement for full polarization. We design a fully connected network handling the forest height reconstruction problem from a classification task perspective. The network is trained using the covariance matrix elements of single polarimetric images acquired by ONERA over Paracou region as input, while LiDAR data acts as reference. Experimental results generally show good performance for forest height and underlying topography reconstruction and, a good robustness if compared with the results driven by fully polarimetric images.

Forest characterization and monitoring are highly important for tracking climate change, utilizing ecology resources, and biodiversity applications. Synthetic Aperture Radar Tomography (TomoSAR) provides the opportunity to reconstruct three-dimensional structures of the penetrable media relying on multi-baseline image acquisition. In forest applications, TomoSAR serves as a powerful technical tool for reconstructing forest height and underlying topography. Presently, a number of reconstruction methods are based on fully polarimetric TomoSAR datasets which require costly data acquisition. The aim of this paper is to go beyond the limitation of the requirement for full polarization by extending Tomographic SAR Neural Network (TSNN), a neural network for TomoSAR, to the case of single-polarimetric (SP) and dual-polarimetric (DP) TomoSAR data for retrieving forest height and underlying topography. Experimental results indicate that TSNN trained by SP or DP TomoSAR data is a powerful candidate to estimate forest height and underlying topography with high accuracy.

Synthetic aperture radar (SAR) systems can be designed with different polarimetric modalities. Most spaceborne SAR systems acquire dual-polarimetric data to meet various operational requirements. They are designed to capture more information about the Earth’s surface than single-pol systems and to cover a wider area than full-pol modalities. Dual-polarimetric data may not be as informative as fully polarimetric images. Several methods exist to augment dual-polarimetric images to take the capabilities of fully polarimetric data. Such methods, nevertheless, are either specific to special dual-pol modalities, i.e., compact modes, or rely on model assumptions that may not be valid in various scattering scenarios. In this article, a new framework for reconstructing fully polarimetric information from typical modalities of dual-pol data is proposed. The framework uses deep learning solutions to augment dual-polarimetric data without relying on model assumptions. Besides the specific architecture of the network used, which makes it efficient to extract distinctive features, a specific loss function is defined to account for the different scattering properties of the polarimetric data. Experiments on different real data show that the reconstruction performance of the proposed framework is superior to the conventional reconstruction method that widely experimented in the literature. Moreover, the pseudo-fully polarimetric data reconstructed by the proposed method closely match the actual fully polarimetric images acquired by radar systems, confirming the reliability and effectiveness of the proposed method.

Synthetic Aperture Radar (SAR) images are impaired by the presence of speckle. Despite the deep interest of scholars in the last decades, SAR image despeckling is still an open issue. Among different approaches, recently, many Deep Learning (DL) methods have been proposed following both supervised and unsupervised training approaches. There are two main challenges within the supervised framework: training data, and cost functions. Our approach builds training datasets which are varied and realistic using a multi-category Generalized Gaussian Coherent SAR simulator. It allows modeling a variety of SAR scenarios beyond the fully developed speckle hypothesis, which is only valid in homogeneous areas. Such multi-category simulated speckle is then applied to a noise-free reference obtained by multi-looking a temporal stack of actual SAR images in order to obtain the noisy input. We design an effective multi-objective cost function that accounts for texture, edge, and statistical properties preservation. We show the superiority of our approach assessing numerically and quantitatively its performance with three different SAR datasets.

Forest height and underlying terrain reconstruction is one of the main aims in dealing with forested areas. Theoretically, Synthetic Aperture Radar Tomography (TomoSAR) offers the possibility to solve the layover problem, making it possible to estimate the elevation of scatters located in the same resolution cell. This paper describes a deep learning approach, named Tomographic SAR Neural Network (TSNN), that aims at reconstructing forest and ground height using multipolarimetric multibaseline (MPMB) SAR data and Light Detection and Ranging (LiDAR) based data. The reconstruction of the forest and ground height is formulated as a classification problem, in which TSNN, a feed-forward network, is trained using covariance matrix elements as input vectors and quantized LiDAR-based data as the reference. In our work, TSNN is trained and tested with P-band MPMB data acquired by ONERA over Paracou region of French Guiana in the frame of the European Space Agency’s campaign TROPISAR and LiDAR-based data provided by the French Agricultural Research Center. The novelty of the proposed TSNN is related to its ability to estimate height with a high agreement with LiDAR-based measurement and actual height with no requirement for phase calibration. Experimental results of different covariance window sizes are included to demonstrate TSNN conducts height measurement with high spatial resolution and vertical accuracy outperforming the other two TomoSAR methods. Moreover, the conducted experiments on the effects of phase errors in different ranges show that TSNN has a good tolerance for small errors and is still able to precisely reconstruct forest heights.

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.

A fast and precise detection of floating plastics debris is necessary for monitoring and saving the sea ecosystem. Recent studies have demonstrated how remote sensing (and in particular satellites) can be helpful in such detection. In particular, data provided by satellite sensors allow to continuously monitoring wide areas of our planet interested by plastic litters. In this work, the possibility of exploiting different optical remote sensing satellite methods is investigated: the analysis is conducted starting from multi-spectral data and moving tom hyperspectral one. Data acquired from Sentinel 2 and from PRISMA sensors are considered showing the added value of these systems in the detection of marine litter within marine areas.

InSAR phase are affected by noise that impairs the performance of applications such as topography, 3D reconstruction, DEM profile, etc. Therefore a denoising step is fundamental. In the last decades many methods for InSAR phase denoising have been proposed such as Local, Non Local and other kind of filters. Inspired by the great success of deep learning in image denoising, methods relying on convolutional neural networks have been proposed recently. In this work, inspired by the outcomes of an amplitude despeckling filter, a multi-objective neural network for interferometric phase denoising is proposed: a cost function composed of three terms takes into account fringe, edges and statistical preservation. The encouraging results are validated quantitatively and qualitatively on a simulated dataset.

Elevation estimation of canopy and ground is one of the main aims in dealing with forest scenario using Synthetic Aperture Radar (SAR) Tomography. Theoretically, SAR Tomography (TomoSAR) provides layover solution, allowing to reconstruct the elevation of the different contributions collapsing in the same resolution cell. TomoSAR is commonly applied on both urban and vegetated areas. Within the latter scenario, one of the most interesting outcomes of TomoSAR is the possibility of separating the canopy and ground, allowing the reconstruction of their height maps. Within this paper, we propose a Deep Learning (DL) based method for TomoSAR. In particular, a neural network was trained for predicting the elevation value of canopy and ground of an area under investigation, based on a stack of SAR fully polarimetric multi-baseline acquisitions. The method uses the Light Detection And Ranging (LiDAR) data as reference and exploit a classification approach. The process was operated on a tropical forest over the TropiSAR2009 test site in Paracou, French Guiana. Testing results on real data are presented showing interesting results.

In the framework of deep learning for synthetic aperture radar (SAR) speckle reduction, the methods presented in the literature mainly focus on the definition of new architectures and cost functions for better catching and preserving the properties of a real SAR image. The achieved results are interesting and promising but with many left open issues. The main critical problem, shared by all the methods, is the construction of a training dataset. This is due to the lack of a noise-free reference. In this work, a comparison among different training approaches (synthetic, multitemporal, and hybrid) is carried out in order to analyze their benefits and drawbacks. Four convolutional neural network (CNN)-based methods have been trained with the three different datasets for their assessment. Results on real SAR images have been carried out showing the peculiarities of each training approach.

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.

Interferometric Synthetic Aperture Radar is an effective and widely adopted tool for earth observation. Based on interferograms it is possible to infer several information about the observed area. Two main problems affecting the interferogram can limit its application: phase noise and phase wrapping. In this paper the attention is focused on the first issue. Several algorithms have been developed for interferogram restoration. Given the wide spread of Deep Learning (DL) in the framework of image processing, DL based algorithms have been proposed for interferogram denoising. Most of the efforts have been devoted in designing specific network architectures or training dataset, rather than on the definition of a specific cost function, well suited for the problem under investigation. The aim of this manuscript is to define a new multi-objective cost function, specifically thought for the interferograms restoration problem: the idea is to provide a cost function able to take into account multiple aspects of the data under investigation (i.e. multi-objective). The cost function is implemented within a Convolutional Neural Network and a specific realistic training dataset is built, to account the main characteristics of real interferograms. The final outcome of the paper is the proposal of a new robust and accurate interferometeric phase denoising algorithm (namely InSAR-MONet ), able to remove undesired noise and, at the same time, able to preserve important phase details. The assessment of the method is conducted on simulated and real datasets, comparing quantitatively and qualitatively InSAR-MONet with the state of the art interferometric denoising algorithms.

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.

In this paper the effectiveness of a CNN based interferometric phase unwrapping algorithm combined with phase noise filtering is analysed. In particular, the considered processing chain relies on a pre-processing step with the nonlocal filter InSAR-BM3D followed by a deep CNN solution for restoring the absolute phase. The analyses is conducted on simulated data with different coherence values and aims at comparing the performance of the unwrapping with and without the pre-processing step. This paper is the first step towards a unique deep learning solution for jointly unwrapping and restoring the absolute phase.

SAR image interpretation is always impaired by speckle that is a multiplicative noise due to interference among the backscatterings from targets inside a resolution cell. Many algorithms for both single and multi-channel SAR despeckling have been proposed in the last forty years following different approaches. Recently, a multi-objective convolutional neural network, named MONet, has been proposed for single channel SAR despeckling. It relies on a mulit-objectvie cost function that takes into account three main aspects of the SAR images: noise removal, details and statistics preservation. Inspired by MONet, in this paper a deep learning method for InSAR phase filtering is proposed. The idea is to benefit from the multi-objective cost function defined in MONet that seems to perfectly fit with the interferogram denoising. This is the first step towards a solution able to provide a complete processed multi-channel product.

Among the different deep learning-based methods proposed for SAR image despeckling, the main issue seems to construct reliable training data sets. In the statistical-based solution MONet, which assumes square root Gamma distributed speckle in the simulation, the authors showed that despeckling results on actual SAR images are stringently related to the considered training dataset and its statistical distributions. This paper develops realistic simulated data sets for feeding the MONet architecture, including backscattering mechanisms arising in different existing SAR scenarios. We consider a generalized Gaussian coherent scatterer model for SAR correlated clutter simulation for this aim. The use of such simulation has a twofold effect within the considered framework: from one side, it allows generating several noisy patches, used as input data; on the other, it allows including different speckle distributions for different actual SAR scenarios. Results on SAR images show the effectiveness of such simulation.

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.

With reference to the application of multichannel (polarimetric or interferometric) synthetic aperture radar (SAR) data, despeckling is a mandatory task in order to exploit fully the image information. Thanks to the long-standing studies, there exist several despeckling techniques that have shown to be powerful tools for filtering multichannel SAR images. Often, such techniques rely on the estimation of the covariance matrix. However, in the literature, the performance evaluation of the filtering operation, which represents a fundamental aspect, has been mainly addressed for a single intensity/amplitude SAR image. In this letter, we present two nonreference indices for the evaluation of the polarimetric/interferometric covariance matrix. The proposed quality indices assess the statistical similarity of the ratio between the original and filtered covariance matrices to the properties derived from the pure speckle model. The analyses both on simulated and real data show that the results of filter ranking by the proposed method are in agreement with the visual evaluation and are consistent with the common polarimetric quality measures.

Deep learning (DL) in remote sensing has nowadays become an effective operative tool: it is largely used in applications, such as change detection, image restoration, segmentation, detection, and classification. With reference to the synthetic aperture radar (SAR) domain, the application of DL techniques is not straightforward due to the nontrivial interpretation of SAR images, especially caused by the presence of speckle. Several DL solutions for SAR despeckling have been proposed in the last few years. Most of these solutions focus on the definition of different network architectures with similar cost functions, not involving SAR image properties. In this article, a convolutional neural network (CNN) with a multi-objective cost function taking care of spatial and statistical properties of the SAR image is proposed. This is achieved by the definition of a peculiar loss function obtained by the weighted combination of three different terms. Each of these terms is dedicated mainly to one of the following SAR image characteristics: spatial details, speckle statistical properties, and strong scatterers identification. Their combination allows balancing these effects. Moreover, a specifically designed architecture is proposed to effectively extract distinctive features within the considered framework. Experiments on simulated and real SAR images show the accuracy of the proposed method compared with the state-of-art despeckling algorithms, both from a quantitative and qualitative point of view. The importance of considering such SAR properties in the cost function is crucial for correct noise rejection and details preservation in different underlined scenarios, such as homogeneous, heterogeneous, and extremely heterogeneous.

SAR images are affected by multiplicative noise that impairs their interpretations. In the last decades several methods for SAR denoising have been proposed and in the last years great attention has moved towards deep learning based solutions. Based on our last proposed convolutional neural network for SAR despeckling, here we exploit the effect of the complexity of the network. More precisely, once a dataset has been fixed, we carry out an analysis of the network performance with respect to the number of layers and numbers of features the network is composed of. Evaluation on simulated and real data are carried out. The results show that deeper networks better generalize on both simulated and real images.

Backscattering separation coming from ground and canopy is one of the main aims in dealing with forest scenario using synthetic aperture radar (SAR) tomography. Theoretically SAR tomography (TomoSAR) provides layover solution, but in practice, insufficient vertical resolution using typical reconstruction approaches may not be sufficient for identification of the vertically aligned scatterers. To cope with this intrinsic issue, we proposed a method that separates the ground and canopy backscatterings based on Random- Volume-over-Ground (RVOG) model and by employing the generalized likelihood ratio test (GLRT) detection schemes over the covariance matrix. Such a separation allows identification of interference of the backscattering, which simply brings the possibility to resolve and separate ground and canopy superposition in the tomogram. Experimental validation of the proposed methodology is provided using a real data set acquired by the ONERA SETHI in the framework of the ESA's campaign, TropiSAR.

This paper deals with the characterization of permanent scatterers in polarimetric synthetic aperture radar (SAR) images of urban environment. To this aim, the main purpose of this paper is to investigate how spaceborne SAR tomography (TomoSAR) can be employed to identify and distinguish the target scattering mechanisms. Along this, the conventional H-α classifier can be adapted to the reconstructed polarimetric coherence matrix, i.e. T, in a multi-dimensional space. However, dealing with multitemporal multi-baseline satellite images, the accurate tomographic reconstruction requires permanent scatterers between all the acquisitions. To cope with this issue, a generalized likelihood ratio test (GLRT)-based tomographic approach for polarimetric SAR tomography is developed. The proposed framework of scatterer detection and characterization is evaluated using TerraSAR-X polarimetric multi-baseline data sets over an urban area in France.

Earth observation using spaceborne sensors with short revisiting time has forgone the limits of conventional assessment methods. In this paper, we investigate the use of SAR Tomography (TomoSAR) to monitor infrastructures, using Morandi Bridge in Genoa, Italy, as a case study. Morandi Bridge suffered a partial collapse due to a structural failure on August 14, 2018. The main issues to be considered for using TomoSAR as a means of an early warning system in structural health monitoring are discussed, highlighting the differences respect to monitoring applications dealing with subsidence and deformation of extended areas. A set of 70 Sentinel-1A images of the bridge over a period of three years prior to the bridge collapse are analyzed using 5D TomoSAR based on Sup-GLRT scatterers detection technique. Preliminary results indicate that possible temporal and thermal deformations of the static structure can be estimated using the method considered.

In the last decades, several approaches for solving the Phase Unwrapping (PhU) problem using multi-channel Interferometric Synthetic Aperture Radar (InSAR) data have been developed. Many of the proposed approaches are based on statistical estimation theory, both classical and Bayesian. In particular, the statistical approaches based on the use of the whole complex multi-channel dataset have turned to be effective. The latter are based on the exploitation of the covariance matrix, which contains the parameters of interest. In this paper, the added value of the Non Local (NL) paradigm within the InSAR multi-channel PhU framework is investigated. The analysis of the impact of NL technique is performed using multi-channel realistic simulated data and X-band data.

Speckle reduction is a major issue for many SAR imaging applications using amplitude, interferometric, polarimetric or tomographic data. This subject has been widely investigated using various approaches. Since a decade, breakthrough methods based on patches have brought unprecedented results to improve the estimation of radar properties. In this paper, we give a review of the different adaptations which have been proposed in the past years for different SAR modalities (mono-channel data like intensity images, multi-channel data like interferometric, tomographic or polarimetric data, or multimodalities combining optic and SAR images), and discuss the new trends on this subject.

In SAR domain many application like classification, detection and segmentation are impaired by speckle. Hence, despeckling of SAR images is the key for scene understanding. Usually despeckling filters face the trade-off of speckle suppression and information preservation. In the last years deep learning solutions for speckle reduction have been proposed. One the biggest issue for these methods is how to train a network given the lack of a reference. In this work we proposed a convolutional neural network based solution trained on simulated data. We propose the use of a cost function taking into account both spatial and statistical properties. The aim is two fold: overcome the trade-off between speckle suppression and details suppression; find a suitable cost function for despeckling in unsupervised learning. The algorithm is validated on both real and simulated data, showing interesting performances.

Temporal decorrelation is one of the major problems in synthetic aperture radar (SAR) tomography (TomoSAR) of a natural environment that leads to blurring and spreading in focused image space. In the context of spatiotemporal focusing using the multi-temporal multi-baseline (MB) SAR data, a model-based differential TomoSAR is employed. Along this and with the aim of temporal decorrelation-robust focusing, a differential tomography framework based on generalized Capon estimator is investigated. The method can cope with temporal decorrelation of the distributed environment by spatiotemporal focusing with optimal bandwidth of the distributed signal. In addition, the method employs an additional parameter for coherence channel balancing in the model of generalized Capon that benefits from it in characterizing the spatiotemporal backscattering by mitigating the inconsistency between channels. The analysis is performed with a realistic simulation of temporal decorrelation in the presence of different decorrelation sources and taking into account the dependence on the vertical structure of the forested area. Effectiveness of the proposed framework has been assessed on both simulated and real data sets by evaluation and characterization of the canopy and under foliage ground in terms of deviation between the estimated covariance matrix and one of the generalized TomoSAR models.

Although the first filtering algorithms have been proposed more than 30 years ago, despeckling of synthetic aperture radar images is still an open issue. A new boost has been provided by nonlocal (NL) means filters. The idea of NL filters is to move from the exploitation of spatial neighboring pixels to the exploitation of similar pixels found across the image. The difference between the NL algorithms is mainly related to the definition of the similarity between pixels and how similar pixels are exploited in the restoration process. Generally, to define the similarity, the patches are adopted. In this paper, a new similarity criterion for selecting similar pixels is presented. It is based on the definition of the ratio patch between the patch containing the pixel to be restored and the patch containing a candidate similar pixel. If the two pixels are similar, it is expected that the corresponding ratio patch will follow a specific statistical distribution. A modified version of the Kolmogorov-Smirnov distance is introduced to decide whether the statistical distribution of the ratio patch follows the expected one. To reduce the possible artifacts, anisotropy is exploited. Considering the proposed approach, the designed algorithm turns to be unbiased, able to provide the restored solution without any thresholding procedure, in which the tuning is substantially unsupervised and able to work with both single-look and multilook images. The algorithm has been tested on different simulated and real data. Qualitative and quantitative analyses validate the proposed approach, showing very good despeckling capabilities.

This paper explores the main issue surrounding the multidimensional synthetic aperture radar (SAR) image focusing techniques, suchlike those caused by the atmosphere propagation delays or by residual platform motion. The problem brings unknown contributions to the phases of complex received signal that it is generally independent of acquisitions track to track and leads spreading and defocusing in multi-dimensional space. To deal with these issues, in this paper an auto-focusing procedure based on sharpness optimization of the reconstructed signal has been employed. The main concern about this technique is that sharpness optimization by itself however can introduce unwanted and uncontrollable vertical shifts in the focused image. To tackle this issue, the phase error is estimated by multiple integration of second derivative of the phase with respect to baseline. The estimation of the calibration phase is performed by optimizing contrast or entropy of the vertical profile with the constraint of a zero phase derivative. In this way, unwanted vertical shifts are avoided and the correct height reference is preserved. Experimental results from the proposed method are evaluated by vertical profile reconstruction performance in the controlled conditions by simulated dataset over the forested area and multi-baseline data acquired by ONERA in Guyana in the frame of European space agency's campaign TROPISAR.

Synthetic aperture radar (SAR) tomography is the most typical approach to generate the elevation map of the observed scene through the 3D imaging from multi-baseline acquisition. Typically, the nominal scatterers can be derived by evaluation of the presented peaks in the reconstructed scattering reflectivity through the array signal processing methods. In this paper, we investigate the possibility to improve the height reconstruction process and achieve a reliable elevation map by jointly estimating and regularizing the solution of array processing techniques. In particular, an a priori is added to the cost function of desired parameter estimation in the processing chain. The algorithm is evaluated using simulated data correspond to the E-SAR airborne sensor of the German Aerospace Center (DLR).

This paper addresses the problem of SAR Tomographic (TomoSAR) imaging, allowing the detection of multiple scatterers in presence of partially correlated Gaussian clutter. TomoSAR is a multidimensional imaging technique that has proven its ability in localizing the scatterers, reconstructing the elevation profile of the structures on the ground (3D reconstruction) and estimating the temporal deformations and thermal dilations of the scene (5D reconstruction). In the literature statistical based TomoSAR reconstruction refers to a signal model where in each range-azimuth resolution cell one or more scatterers are interfering in presence of noise and clutter signals, modeled as zero-mean complex circular white Gaussian random vectors. In this paper, we propose to extend a generalized likelihood ratio test (GLRT) detector, proposed by the authors and denoted Fast-Sup-GLRT, to a different signal model, where a correlated clutter model is considered. Results on TerraSAR-X real data are presented.

Synthetic Aperture Radar (SAR) image despeckling is still an open issue. Several approaches have been proposed in the last decades. The recently proposed Non Local approaches are often considered as the state of art of SAR despeckling. The difference between the NL algorithms presented in literature is mainly related to the adopted distance metric between patches and on the rule used for averaging the selected pixels. Within this manuscript a new metric for selecting similar patches is presented. The metric is based on the statistical distribution of the complex noisy image. The Kolmogorov-Smirnov (KS) test is adopted to compare the statistical distribution and to select similar patches. The approach has been tested and validate on real data, showing interesting performances.

Fusing a multispectral image with a co-registered higher resolution single panchromatic band, provided by any multiresolution satellite systems, to rise the resolution of the former to that of the latter is known as pansharpening, and can be regarded as a guided super-resolution problem. Recently the use of convolutional neural networks (CNNs) has been extended to the pansharpening problem achieving state-of-the-art performance. Following this research line, the objective of this work was two-fold: provide a trained CNN model fitted to a specific sensor (WorldView-3) and explore a range of architectural configurations varied in both width and depth, seeking for the optimal one. Numerical and visual results show that the proposed solution compares favourably against reference methods.

This letter analyzes the impact of the accuracy of estimation of the data covariance matrix in synthetic aperture radar tomography of vegetated areas. The characterization of volumetric areas requires a robust estimation of the covariance matrix, which is usually performed by means of an averaging operation of neighboring pixels. In this letter, a different approach, based on the use of local and nonlocal (NL) neighborhoods of pixels, is evaluated. The analysis considers the quality of the reconstructed vertical profile obtained using both single and fully polarimetric multibaseline (MB) data. In the case of fully polarimetric data, two procedures for obtaining the vertical reconstruction are analyzed: the sum of Kronecker product decomposition of the covariance matrix and a procedure based on the full-rank estimation of a 3-D coherence matrix. The analysis of the impact of NL technique on the robust estimation of covariance matrix and on the capability of separating the interfering signals is performed using simulated and P-band real MB data.

Reconstruction of elevation maps from a collection of synthetic aperture radar (SAR) images obtained in interferometric configuration is a challenging task. Reconstruction methods must overcome two difficulties: the strong interferometric noise that contaminates the data and the 2π phase ambiguities. Interferometric noise requires some form of smoothing among pixels of identical height. Phase ambiguities can be solved, up to a point, by combining linkage to the neighbors and a global optimization strategy to prevent from being trapped in local minima. This paper introduces a reconstruction method, PARISAR, that achieves both a resolution-preserving denoising and a robust phase unwrapping (PhU) by combining nonlocal denoising methods based on patch similarities and total-variation regularization. The optimization algorithm, based on graph cuts, identifies the global optimum. Combining patch-based speckle reduction methods and regularization-based PhU requires solving several issues: 1) computational complexity, the inclusion of nonlocal neighborhoods strongly increasing the number of terms involved during the regularization, and 2) adaptation to varying neighborhoods, patch comparison leading to large neighborhoods in homogeneous regions and much sparser neighborhoods in some geometrical structures. PARISAR solves both issues. We compare PARISAR with other reconstruction methods both on numerical simulations and satellite images and show a qualitative and quantitative improvement over state-of-the-art reconstruction methods for multibaseline SAR interferometry.

SAR tomography (TomoSAR) allows facing the problem related to the interference of coherent scatterers within the same pixels due to the occurrence of layover. Whereas, full imaging the continuous reflectivity profile along the elevation dimension is a typical framework to deal with the non-coherent volumetric scatterers in the forested area. Layover usually arises in volumetric scenario and leads to discontinuity in the reconstructed vertical reflectivity image. This paper aims to investigate the possibility of addressing layover issue in forested area by exploiting the unified non-local (NL) filtering of multi-baseline (MB) covariance matrix. To this aim, the performance of non-parametric Capon spectral estimation technique has been analyzed using the NL filtered MB covariance matrix and efficient vertical reflectivity profile reconstruction is demonstrated, which almost addressed the layover issues.

Automatic Target Recognition (ATR) aims at detecting the presence and at recognizing the typology and the orientation of targets within a scenario, by using an unsupervised approach. In Syntethic Aperture Radar imaging this turns to be a difficult task due to the specific characteristics of clutter and background noise. Within this manuscript a new two-steps ATR algorithm based on Kolmogorov-Smirnov test is presented. The method has been tested on real MSTAR datasets showing interesting performances.

In the last decade, Persistent Scatterer Interferometry (PSI) and SAR tomography (TomoSAR) have been used for reconstructing the elevation profile of a scene, starting from a set of co-registered Synthetic Aperture Radar (SAR) images. The possible advantage of TomoSAR over classical interferometric methods consists in the potential capability of improving the detection of single scatterers presenting stable proprieties over time (Persistent Scatterers or PS), as well as to enable the detection of multiple scatterers interfering within the same range-azimuth resolution cell. In urban environment, when only single dominant scatterers are present in each range-azimuth resolution cell, both methods can be exploited to estimate the altitude, deformation rate and thermal expansion of a subset of reliable scatterers, which are selected on the basis of different criteria. This paper is focused on a performance analysis of the two class of methods, using the results obtained in urban environment on simulated and real TerraSAR-X data. A concise description of both techniques, along with a discussion on their potential capabilities in selecting the most reliable scatterers, is given.

One of the main challenges in Interferometric Synthetic Aperture Radar (SAR) is the accurate height reconstruction of the observed scene. Recently, approaches based on Extended Kalman Filter (EKF) have been proposed. Most of them are based on the hypothesis of height profile continuity. Such condition greatly reduces their applicability, being only valid for particular scenarios. Within this paper, we present a novel Kalman-based height reconstruction approach, specifically designed to work with multichannel data related to any type of scenario, both smooth or sharp. The novelty of the technique consists in its ability in detecting and correctly handling sharp height discontinuities while regularizing smooth areas. The approach is able to maintain the high computational efficiency typical of EKF and to work in an almost unsupervised way. The methodology has been tested and validated on both simulated and real X-band (TerraSAR-X and COSMO-SkyMed) high-resolution data sets. Reported results are encouraging and interesting, showing the correctness and the validity of the proposed approach.

A novel approach for speckle reduction in SAR images is presented. An enhanced version of the Wiener Filter is proposed in order to locally adapt the filter characteristic to the image behavior, modelled by Markov Random Fields. First results on simulated and real data are reported.

Within this manuscript a novel Multi-channel InSAR phase unwrapping method is proposed. The approach implements an Extended Kalman Filter for jointly unwrap the phase and regularize the result. The novelty of the methodology consists in the probabilistic data association step that has been implemented in order to improve the robustness of EKF for PhU. Encouraging results on simulated dataset are reported.

In this paper the problem of despeckling Synthetic Aperture Radar images is addressed. An algorithm developed in the Bayesian estimation theory framework is presented. In particular, considering single look images, the algorithm applies an homomorphic filter followed by an Iterative Wiener filter to reduce the speckle. The proposed approach is tested on simulated and real X-band datasets showing interesting noise reduction capabilities.

In this paper we propose a new approach for height retrieval using multi-channel SAR interferometry. It combines patch-based estimation and total variation regularization to provide a regularized height estimate. The non-local likelihood term adaptation relies on NL-SAR method, and the global optimization is realized through graph-cut minimization. The method is evaluated both with synthetic and real experiments.

Phase Unwrapping (PhU) is the operation needed in order to generate 3-Dimensional height profile starting from Synthetic Aperture Radar (SAR) data acquired in the interferometric configuration. Due to the presence of height discontinuities (buildings) and due to the presence of noise, PhU becomes a difficult task to face in urban scenarios. In this paper we propose a new methodology especially thought for generating 3D height profiles of urban areas when multiple interferograms are available. The technique is based on the use of Kalman Filter in its Extended form (Extended Kalman Filter - EKF). The main peculiarity of the technique is the introduction of a specific step in the PhU procedure able to identify the possible height discontinuities and to consequently adapt the EKF behaviour. The algorithm is validated on both simulated and real cases.

A novel Phase Unwrapping (PhU) technique for InSAR interferometric stacks based on statistical estimation theory is presented. The approach is intended for exploiting both amplitude and phase of the acquired data in order to express the multi-baseline likelihood function without the assumption of independence among channels, i.e. by considering the full mutual correlation matrix. Moreover, the contextual information is adopted for regularizing the solution, obtaining a Maximum A Posteriori (MAP) estimator. First results on real datasets related to an urban scenario are presented, showing the interesting performances of the proposed method in terms of Digital Elevation Model (DEM) reconstruction.

Within this manuscript a novel technique for joint Digital Elevation Model (DEM) reconstruction and deformation estimation is presented. In particular, a Maximum A Posteriori (MAP) estimator that makes use of Gaussian Markov Random Fields (MRF) is proposed. The advantage of the approach, with respect to classical Permanent Scatterers (PS) based techniques, consists of its ability to evaluate the height and the deformation for all resolution cell across the scene, instead of only strong scatterers. Thus, the method is able to work also in natural scenarios, or in general when few PS are available. First results are presented on a simulated dataset with COSMO-SkyMed acquisition parameters.

In this letter, an innovative technique for change detection in urban areas using very high resolution synthetic aperture radar multichannel stacks is proposed. Instead of using the amplitude image, as in classical change detection approaches, the proposed technique uses the full complex image in a Markovian framework. The complex data are modeled using Markov random field hyperparameters, which are particular local parameters that take into account the spatial correlation between pixels. Starting from two data sets, the pre- and the postevent ones, the proposed algorithm, first, estimates the two hyperparameter maps and, then, compares the similarity between them. If a change occurs between the pre- and the postevent acquisitions, the statistical distribution of the hyperparameter maps will change. The maximum distance between the two obtained statistical distributions provides an index of changes. This sort of spatial correlation maps is computed using statistical estimation techniques, while the similarity comparison is computed using the two-step Kolmogorov-Smirnov statistic test. The algorithm is validated on simulated data and tested on real COSMO-SkyMed data acquired on the area of Naples, showing interesting and promising results.

The objective of synthetic aperture radar (SAR) edge detection is the identification of contours across the investigated scene, exploiting SAR complex data. Edge detectors available in the literature exploit singularly amplitude and interferometric phase information, looking for reflectivity or height difference between neighboring pixels, respectively. Recently, more performing detectors based on the joint processing of amplitude and interferometric phase data have been presented. In this paper, we propose a novel approach based on the exploitation of real and imaginary parts of single-look complex acquired data. The technique is developed in the framework of stochastic estimation theory, exploiting Markov random fields. Compared to available edge detectors, the technique proposed in this paper shows useful advantages in terms of model complexity, phase artifact robustness, and scenario applicability. Experimental results on both simulated and real TerraSAR-X and COSMO-SkyMed data show the interesting performances and the overall effectiveness of the proposed method.

In this manuscript a novel approach for SAR urban change detection is presented. Its peculiarity is its ability to detect the changes not directly from the measured amplitude data, but exploiting the whole complex image. In particular, the scene in modelled as a Local Gaussian Markov Random Field, and is described via the so called hyperparameters, which refers to the spatial correlation of pixels. By comparing such hyperparameters obtained from a pre-event and a post-event dataset, we can detect occurred changes. Results on real datasets show good detection accuracy together with very low false alarm rate.

Within this manuscript, a method able to extract lake shore from SAR complex data is proposed. Radar images have many advantages over optical images, such as no cloud coverage or solar illumination problem. The method models the observed scene as a Local Gaussian Markov Random Field and estimates in a Bayesian framework the so called hyperparameters. By proper thresholding such hyperparameters we can retrieve the lake shores. Exploiting SAR data from today available high resolution sensors, we can monitor lake shores with sub-meter precision. In the following, applications to two real data sets, showing the effectiveness of the method, are reported.

Historically, the extraction of coastal line has been performed exploiting optical images, but in the last two decades, some approaches working with synthetic aperture radar (SAR) data have been proposed. Recently, these approaches have been gaining interest due to the availability of high-resolution SAR images. In this letter, a technique for coastal line retrieval from multichannel SAR images is presented. The detection problem is faced in the statistical estimation framework, in particular, exploiting Bayesian estimation theory. The proposed technique is able to detect sea boundaries at full resolution and low error rate in a totally unsupervised way. The performance of the method has been tested using high-resolution COSMO-SkyMed data sets acquired on the Bay of Naples, showing the high accuracy of the proposed technique.

In this work an edge detector for man made structures within Spotlight Synthetic Aperture Radar (SAR) Images is proposed. The algorithm processes both real and imaginary parts of the data and so it is able to fully exploit the acquired image, being optimal from the information theory point of view. The detector has been tested on Cosmo-SKYMED (CSK) Spotlight image and compared to other single image edge detectors, showing interesting and promising results.

Markov Random Fields (MRF) are a powerful and wide adopted tool in image processing. MRFS together with Bayesian Estimation Theory can be used for detecting edges of man made structures in Synthetic Aperture Radar images. In this paper we present a method developed in the Markovian-Bayesian framework which is particularly suited to work in case of high coherence SAR interferometric images pairs, such as TanDEM-X Mission data. A real case study, consisting of a pair of complex TerraSAR-X images, is presented, showing the performances of the algorithm.

The aim of building edge detection is to obtain a map of man-made structure edges of the investigated scene. Different detectors have been developed exploiting synthetic aperture radar (SAR) data, based on the use of the reflectivity difference (working with SAR amplitude images) or of the phase difference (working with SAR interferometric images) between neighboring pixels. In this letter, a novel approach using jointly both the amplitudes and the interferometric phase of two complex SAR images is proposed, based on the hypothesis that information related to building edges can be retrieved in the two data domains. The technique is based on stochastic estimation theory, exploiting, in particular, Markov random fields. Compared to classical amplitude-based edge detectors and to phase-based ones, the proposed method shows an improvement in terms of detection accuracy, false alarm rate, and building shape recovery. The algorithm has been tested and analyzed using simulated data and validated on L-band and X-band real data sets.

Interferometric synthetic aperture radar (SAR) (InSAR) systems allow 3-D reconstruction of observed scene. In this paper, an innovative approach for phase unwrapping and digital elevation model (DEM) generation using multichannel InSAR data is presented. The proposed algorithm, exploiting both the amplitude and phase of the available complex data, is able to unwrap and simultaneously regularize the observed data. In particular, the exploitation of amplitude data within the unwrapping chain helps in preserving sharp discontinuities typical of urban areas. As a result, the technique provides accurate DEM reconstructions. For this aim, a Markovian approach, together with a new graph-cut-based optimization algorithm, has been considered. The method has been developed specifically to work in urban areas with very high resolution InSAR image stacks, being able to automatically compensate possible phase offsets. Results on both simulated and real case studies are reported, showing the effectiveness of the method.

In this work, a novel building edge detector which jointly exploits the full complex SAR image is proposed. The algorithm, starting from both amplitude and phase signals, detects building edges by estimating the spatial correlation between neighboring pixels. The observed scene is modeled using Markov Random Field theory. The proposed procedure is able to correctly identify the building and recover their shapes while maintaining a low false alarm rate, overcoming the limitation of existing techniques.

In this paper a comparison between two techniques developed to recover layover solution in SAR images is presented. SAR Statistical Tomography and Compressive Sensing techniques are described and analyzed in order to provide a set of instruments for 3D SAR imaging able to tackle different scattering mechanisms in layover areas and to recover height reconstruction of an observed scene. The performances of the two techniques are compared on simulated data and some conclusions are drawn.

The aim of this paper is the three dimensional reconstruction of urban areas using Very High Resolution (VHR) images. The proposed innovative approach for the three dimensional reconstruction is based on the joint exploitation of both amplitude and interferometric phase images of a multichannel SAR system. The information provided by the amplitude data is added to the 3D reconstruction chain, considering that in urban areas edges of amplitude image are likely also present in the interferometric phase one and conversely. Differently from other works present in literature, the proposed technique exploits the amplitude image, not only to improve the phase regularization, but also to improve the phase unwrapping step. The results will show the effectiveness of the method.

In this paper, the problem of building edge detection in synthetic aperture radar images is addressed. A new stochastic approach based on local Gaussian Markov random field (LGMRF) is proposed. The algorithm finds the edges of buildings starting from the estimation of the hyperparameters of the LGMRF model. The hyperparameters are seen as an indicator of the spatial correlation between adjacent pixels. The procedure is applied on interferometric data, using single-channel and multichannel configurations. The algorithm has been tested on simulated and real data, providing good results in both cases.

In this paper a methodology for the reconstruction of height profile of earth surface starting from layover affected Synthetic Apertuire Radar data is presented. The proposed approach is based on classical statistical estimation techniques, in particular using Maximum Likelihood Estimator, together with a Gaussian model for the point target response. Multi-channel configuration has been exploited in order to solve the solution ambiguity and to increase the reconstruction accuracy. The performances of the proposed estimator have been evaluated in comparison with the Cramer Rao Lower Bounds for the considered model, showing the effectiveness of the method. The height reconstruction procedure has been tested on a simulated realistic scenario, providing interesting and promising results.

In this letter, a statistical-based approach to recover layover solution in synthetic aperture radar (SAR) images is proposed. The aim of this letter is to develop a methodology in order to separate different scattering contributions collapsed in a single SAR image pixel. After a brief discussion about layover, the proposed model is presented, followed by a discussion about achievable performances using Cramer-Rao lower bounds. In the final part of this letter, the performances of a maximum likelihood estimator are evaluated in a simulated data scenario, showing the effectiveness of the method.

In this letter, a methodology to overcome the layover problem and obtain the 3-D reconstruction of urban areas will be discussed. Interferometric synthetic aperture radar (SAR) (InSAR) systems allow the estimation of height profiles of the Earth surface, but in the case of urban scenarios, estimation becomes a hard task due to the presence of SAR geometrical distortions, with layover above all. First, the layover signal in InSAR images is investigated; then, a procedure to specifically manage layover areas is presented. The proposed method consists of introducing an auxiliary data exploitation, optical data or SAR shadowing, in the maximum a posteriori statistical estimation technique to improve the digital elevation model reconstruction, particularly on phase discontinuities. We test the method on simulated data, showing its effectiveness.

Markovian approaches have proven to be effective for solving the multichannel phase-unwrapping (PU) problem, particularly when dealing with noisy data and big discontinuities. This letter presents a Markovian approach to solve the PU problem based on a newapriorimodel, the total variation, and graph-cut-based optimization algorithms. The proposed method turns out to be fast, simple, and robust. Moreover, compared with other approaches, the proposed algorithm is able to unwrap and restore the solution at the same time, without any additional filtering. A set of experimental results on both simulated and real data illustrates the effectiveness of our approach.

Interferometric SAR (InSAR) systems are able to estimate height profiles of the Earth surface. For the involved estimation problem, Maximum A Posteriori (MAP) statistical technique and Markov Random Field image models have been used, showing to be effective in case of multiple interferograms, obtained via different baselines/frequencies. In this paper, we are interested in the application of such estimation procedure in urban areas, where due to SAR geometry, many geometrical distortions appear. In particular, we focus on the layover problem. We present a procedure to manage layover areas, based on the optical and SAR data fusion. Moreover, we exploit the optical data to improve the a priori term of the MAP approach. We test the method on simulated data, showing the effectiveness of the method.

Multichannel interferometric synthetic aperture radar (InSAR) systems allow the estimation of the height profile of the Earth's surface, exploiting the availability of multiple radar acquisitions, obtained via different baselines/frequencies. Statistical approaches, in particular maximumaposterioritechnique and Markov random-field image models, can be exploited for such estimation problem, which proved to be effective. However, despite the particular solution method used, the problem with multichannel interferometry is that interferograms can be affected from the presence of undetermined phase offsets, which makes it difficult to get correct height estimation in any case. In this letter, we present a procedure to estimate these phase offsets using statistical estimation; we test the procedure on both simulated and real data. For the latter, we show how an optimal estimation of the phase offsets can be used to improve the resolution of an available Shuttle Radar Topography Mission digital elevation model. The obtained results prove the effectiveness of the method and assess the overall quality of the height estimation procedure.

Interferometric SAR (InSAR) systems are able to estimate height profiles of the Earth surface. For the involved estimation problem, Maximum A Posteriori (MAP) statistical technique and Markov Random Field image models have been used, showing to be effective in case of multiple interferograms, obtained via different baselines/frequencies. In this paper, we face the problem of unknown phase offsets presence affecting real interferograms, which makes impossible to retrieve correct height estimations. We present a procedure to estimate these offset values, based on statistical estimation and we test it both on simulated and real data, showing the effectiveness of the method.