Quantifying heterogeneity in synthetic aperture radar (SAR) data is critical for accurate geophysical interpretation and remote sensing applications. We propose a test statistic based on a non-parametric estimation of Rényi entropy to characterize return heterogeneity from SAR intensity data. The statistic is refined using bootstrap to improve its stability, size, and power. This approach enhances heterogeneity quantification by capturing scale-dependent variations and addressing data-driven uncertainty. Experimental results establish the robustness of the proposed method in distinguishing heterogeneity patterns.

Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered encoder–decoder neural network designed to address the key challenges in deforestation mapping, including scale heterogeneity, temporal dynamics, and computational efficiency. The proposed framework integrates a modified YOLOv8 backbone, spatial attention (SA) mechanisms, and a conjugated Dice–Focal loss function to enhance sensitivity to small- and large-scale deforestation patterns in temporal remote sensing (RS) data. An extensive battery of tests was conducted using two datasets from the Amazon region, exploring both single-image and image-pair inputs under varying contextual and class balance conditions. The results attest to substantial improvements in accuracy and computational efficiency compared to 13 deep learning (DL) methods, establishing the proposed model as effective in deforestation monitoring scenarios, where accuracy, scalability, and computational cost are simultaneously critical.

In this letter, considering the effectiveness of 2-D principal component analysis (2DPCA) on the exploration of local spatial relationships, a reconstruction-based 2DPCA (Rec-2DPCA) operation was designed for feature extraction and injected into the architecture of PCANet for change detection of bitemporal synthetic aperture radar (SAR) image. Specifically, as the projection of an image patch on one eigenvector computed by 2DPCA breaks the one-to-one relationship between feature map and eigenvalue, we adopted Rec-2DPCA at various network layers and developed two variants of PCANet, namely, 2DPCANet and (2-D + 1-D)PCANet. In the experiments, using three real SAR image datasets, we analyzed the performance of all comparison methods, and our proposals achieved a more appealing performance than other methods.

Polarimetric Synthetic Aperture Radar (PolSAR) sensors have emerged as a groundbreaking remote sensing technology. They enable the acquisition of the amplitude, phase, and orientation of electromagnetic waves across multiple polarizations. This capability provides enhanced potential for detailed environmental analysis. However, challenges such as complex data structures, non-Gaussian noise properties, and low signal-to-noise ratios pose significant barriers to the effective use of PolSAR data. Existing methods for modeling and analyzing PolSAR data are predominantly parametric and rely on assumptions that may fail under certain conditions. Aware of these limitations, this study introduces the use ofU-statistics for PolSAR data analysis. Using information from the diagonal intensities of the covariance matrix, we propose a hypothesis testing mechanism to assess sample homogeneity a top-down hierarchical separability analysis, and aU-statistics-based classification approach. The proposed procedures are validated using an ALOS PALSAR image of the Amazonian region. The results show the robustness and effectiveness of the proposed methods, offering a reliable framework for analyzing and classifying PolSAR data under non-parametric assumptions.

Phase-linking (PL) plays a crucial role in distributed scatterer (DS) InSAR, but conventional approaches often rely on strong prior assumptions about the underlying data distribution and involve solving highly nonlinear optimization problems. In this study, we propose a novel PL framework based on the central limit theorem for circular data (CLTC), which models interferometric phases through trigonometric moments and avoids any prior assumptions about the data distribution. The CLTC-PL formulation transforms the originally nonlinear PL problem into an inherently well-posed and locally linear weighted least-squares estimation, enabling efficient optimization with minimal iterations and error propagation analysis. The proposed method offers clear structural transparency and statistical interpretability, while having strong estimation performance. This work not only improves robust phase estimation, but also introduces a model-free framework where a multivariate normal distribution of trigonometric moments arises naturally via CLTC, allowing statistically grounded inference. Both simulated and real-data experiments validate the effectiveness of the proposed PL mathematical framework.

Newborns with health complications frequently need to be treated in specialized units called Neonatal Intensive Care Units (NICUs). These environments require efficient monitoring and analysis. However, many factors can influence treatment phases, including sound sources and noise levels. Inadequate acoustic conditions and infrastructure can damage babies' health. Our work proposes a valuable method to enable proper monitoring and feedback to medical staff through correctly classifying the main hospital sounds. We performed sound classification in NICUs using Convolutional and Long Short-Term Memory (LSTM) Neural Networks. We focus on three audio classes: cry, human talks, and alerts from hospital machines (beep sounds). The results include extracting relevant sound features and comparing classifiers considering the main NICU sound classes. The CNN and LSTM approaches performed cry sound classification with a precision of 83.5 % and 84.0 %, respectively. To the alerts and talks, the LSTM approach increased CNN recall by 5.8% and 5.6%.

This paper explores four distinct target descriptors derived from full-polarimetric Synthetic Aperture Radar (SAR) data. Initially, we define a 2 × 1 real positive target vector by leveraging the mean and standard deviation of complex eigenvalues extracted from the 2 × 2 Sinclair matrix. This vector is the basis for two innovative parameters: 1) the scattering-type parameter, and 2) the scattering asymmetry parameter. Furthermore, we introduce the scattering purity and complexity parameters derived from the mean and standard deviation of the real positive eigenvalues of a Hermitian positive semi-definite 3 × 3 coherency (covariance) matrix. We highlight the efficacy of these parameters by conducting an experimental analysis with several canonical targets. Subsequently, we investigate their performance by thoroughly examining Radarsat-2 full-polarimetric SAR data.

Characterization and classification of natural and human-made targets using polarimetric Synthetic Aperture Radar (SAR) data have been widely explored for diverse applications. The Cloude and Pottier scattering-type parameter α has become a standard tool for target characterization and classification. However, it fails to discriminate between all canonical targets. In response to this limitation, this research introduces an alternative scattering-type parameter capable of distinguishing all canonical targets. To achieve this, we first define a real 2 × 1 vector comprising two roll-invariant descriptors derived from the 2 × 2 complex scattering matrix. Subsequently, we calculate the Euclidean norm of this vector relative to a reference real vector associated with a standard dipole scatterer. We leverage this computed Euclidean norm as a key element in formulating our alternate scattering-type parameter. The alternate scattering-type parameter is formulated to effectively characterize a wide spectrum of targets, encompassing both coherent and incoherent. We systematically evaluate the performance of our proposed alternate scattering-type parameter against the well-established Cloude-Pottier α parameter for a diverse set of targets. Additionally, we introduce a target classification framework for dominant scatterers utilizing the vector with two roll-invariant descriptors. To validate our approach, we conducted experiments utilizing two full-polarimetric Earth observation datasets acquired in the C- and L- bands and one full-polarimetric Lunar dataset in the L-band. These datasets were selected to showcase and validate the efficacy of both the alternate scattering-type parameter and the target classification framework.

Change detection is a fundamental task that involves assessing changes in a given region over multiple time periods. It has been widely applied across various fields, including monitoring deforestation, urban expansion, and natural disaster analysis. In this article, we address the critical and complex issue of automatically identifying types of changes in land cover using remotely sensed imagery. While conventional unsupervised change detection methods typically focus on comparing pairs of images and making a binary decision between “change” and “nonchange,” our approach tackles the challenge of analyzing long image series and identifying the kind of change. Under this condition, the unsupervised change detection process allows for a more informative identification of the land cover dynamics. Moreover, our approach transforms input data to a new representation, capturing the target’s spectral response changes over time. Through the utilization of stochastic distances and an optimized thresholding scheme, areas exhibiting minimal spectral response variance are classified as unchanged, effectively distinguishing them from regions undergoing modifications. Next, by applying autocorrelation analysis, regions exhibiting temporal modifications are segregated into periodic (i.e., seasonal) and aperiodic (i.e., permanent) change cases. Experimental validation using both simulated and real-world remote sensing image series demonstrates the effectiveness of the proposed approach.

This work aims to develop techniques for the fusion of statistical evidences obtained from the application of Statistical Information Theory (SIT) and Statistical Information Geometry (SIG) in image processing and analysis, with a specific focus on Polarimetric Synthetic Aperture Radar (PolSAR) imagery. The goal is to generate a single solution superior to individual solutions. Furthermore, properties or measures that assess the quality of results will also be employed to evaluate the effectiveness of fusion methods in detecting edge evidence.

Machine-learning-based methods provide attractive solutions to algal bloom detection. However, the effective utilization of training sets remains a crucial challenge. Taking the extraction of Ulva prolifera as an example, to improve the detection accuracy, this manuscript presents a model based on self-sampling and semicorrelated co-training. The self-sampling module comprises balanced sampling and gradient descent to enhance the efficiency of extracting useful information from U.prolifera training sets. Balanced sampling optimizes the distribution of sampling points, while gradient descent determines the optimal number of sampling points. During the iteration process, useful information will be continuously extracted driven by the self-sampling module as the input of training for the subsequent machine-learning algorithm. The classical semisupervised machine-learning approach named co-training is a very effective semisupervised approach, but it requires two views to be sufficient and independent, a condition that is difficult to meet in practical applications. To address this issue, we developed a semicorrelated co-training module to achieve the two-view condition. To mitigate the problem of limited labeled samples, both labeled and unlabeled samples are used as inputs for the semicorrelated co-training module. Benefiting from the self-sampling module and the semicorrelated co-training module, the experimental results based on different U. prolifera datasets from MODIS and Sentinel-1 synthetic aperture radar (SAR) show that the proposed model in the manuscript has contributed to the improvement of the detection accuracy of U.prolifera.

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.

Seasonal snow is one of the most dynamic components of the cryosphere. The structure and composition of snowpacks is complex and highly variable, both in space and also in time. This study evaluates a new method for identifying phase changes of seasonal snow cover in the Argentinean Andes using Sentinel-1 Synthetic Aperture Radar (SAR) data available in Google Earth Engine (GEE) through time series derivatives and positive and negative anomalies. The results were compared with an approach based on fixed threshold time series phase change detection.

In this work, we propose two parameters in radar polarimetry: (i) scattering purity and (ii) scattering complexity. To obtain these expressions, we use inequalities on the bounds of the condition number in terms of the mean ( $m$ ) and standard deviation ( $s$ ) of the eigenvalues of a Hermitian positive semi-definite matrix. The polarimetric scattering purity characterizes the overall polarization structure in the scattered wave. In contrast, the polarimetric scattering complexity describes the mixture of orthogonal polarized pure components in the scattered wave. We discuss the variability of these metrics over various land cover classes using full-polarimetric C-band Synthetic Aperture Radar (SAR) data. We compare their spatial variations over the ocean surface, built-up areas, and vegetation. We notice significant differences in the purity and complexity characteristics across a wide range of targets in the scene.

We provide a comparison between competitive approaches, the Gambini's algorithm (GA) and a CFAR method (The Co-efficient of Variation Detector), to highlight their strengths and weaknesses. In doing so, we help researchers and practitioners making informed decisions towards the best technique to be applied in any situation of interest. Both methods were able to detect edges in the simulated images used in this work. The GA has the advantage of finding a single pixel as an edge while the CFAR method detects multiple edges, mainly when the edge is a ramp edge. In the other hand, the CFAR method can be directly applied to the images while the GA needs to have as input a region of interest and lines where the transition point between distributions (edges) are detected.

Polarimetric Synthetic Aperture Radar images provide important information about the scene under observation. There are several ways in which such information can be extracted, among them the visualization of polarimetric decompositions. A polarimetric decomposition extracts features which, in principle, are related to basic components of the scene. Its visualization depicts such components as variations in hue and intensity, but its interpretation may be hampered by low contrast. Several image enhancement techniques may be applied to improve such a representation, but they may hamper the information contents. We propose an approach for such enhancement based on the visual content that does not alter the interpretability of color images based on polarimetric decompositions and, at the same time, enhances the user's ability to extract visual information. The technique also provides a quantitative measure of such visual content.

SAR imagery is always accompanied by speckle because it is obtained with coherent illumination. Given the multiplica-tive property of speckle, ratio-based metrics are widely used in SAR image quality assessment. In this paper, using the hy-potheses testing principle, a likelihood ratio test (LRT) based metric was designed for similarity measure in intensity SAR imagery. Then, using non-local means (NLM) scheme, an LRT-based NLM filter was proposed for speckle reduction of SAR imagery. In the experiments, using simulated intensity speckled images, the performance of the designed method is analyzed.

Polarimetric synthetic aperture radar (PolSAR) sensors have reached an essential position in remote sensing. The images they provide have speckle noise, making their processing and analysis challenging tasks. We discuss an edge detection method based on the fusion of evidences obtained in the intensity channels hh, hv, and vv of PolSAR multilook images. The method consists of detecting transition points in the thinnest possible range of data that covers two regions using maximum likelihood under the Wishart distribution. The fusion methods used are: simple average, multiresolution discrete wavelet transform (MR-DWT), principal component analysis (PCA), receiver operating characteristic (ROC) statistics, multiresolution stationary wavelet transform (MR-SWT), and a multiresolution method based on singular value decomposition (MR-SVD). A quantitative analysis suggests that PCA and MR-SVD provide the best results.

We develop a memory graph convolutional network (MGCN) framework for sea surface temperature (SST) prediction. The MGCN consists of two memory layers: one graph layer and one output layer. The memory layer captures SST temporal changes via temporal convolution units and gate linear units. The graph layer encodes SST spatial changes in terms of characteristics derived from graph Laplacian. The output layer encapsulates information from the previous layers and produces SST prediction results. The MGCN characterizes both the temporal and spatial changes, rendering a comprehensive SST prediction strategy. We use daily mean SST data for two areas near the Bohai Sea and the East China Sea for experimental evaluations and validate that the MGCN performs better than other traditional machine learning methods for nearshore SST prediction. In addition, we test the MGCN on weekly and monthly mean SST datasets and validate that the MGCN is robust and suitable for SST prediction.

The generalized degree of polarimetric purity is a vital descriptor widely studied and interpreted for electromagnetic wave characterization. It is invariant under the rotation of the reference frame. In this work, we first propose an alternate expression of this purity measure using the mean$(m)$and standard deviation$(s)$of the real positive eigenvalues of a Hermitian positive semidefinite matrix. We then use this expression to propose a polarimetric scattering purity and scattering complexity measure. To obtain these expressions, we use certain inequalities on the bounds of the condition number for Hermitian positive definite matrices defined in terms of$m$and$s$. The polarimetric scattering purity parameter characterizes the overall polarization structure in the scattered wave. In contrast, the polarimetric scattering complexity parameter describes the mixture of orthogonal polarized pure components in the scattered wave. First, we demonstrate the two proposed measures by analyzing two cases: 1) multiple scattering and 2) a mixture of canonical targets. Then, we utilize full-polarimetric C- and L-band synthetic aperture radar (SAR) data to describe the variation of these measures over various land cover classes. We compare their spatial variations over the ocean surface, built-up areas, and vegetation. We observe notable contrasts in the purity and the complexity parameters over a diverse mixture of targets in the scene. Finally, we critically interpret the variation of the two measures over the temporal scene of rice crop acquired by C-band full-polarimetric SAR data. These analyses affirm the importance of these measures for explicit target characterization. The open-source version of the code is available athttps://github.com/Subho07/scattering-purity-and-complexity

A prompt and effective response to natural disasters is essential. Polarimetric Synthetic Aperture Radar (PolSAR) images playa crucial role in helping decisions in these scenarios, especially in adverse weather or the absence of sunlight. In this context, PolSAR images still provide information. In these situations, the process of finding precise boundaries to determine the extent of the disaster is an essential issue as PolSAR image resolutions are usually high (of the order of 10 m). The fusion of information from the intensity channels of PolSAR images for edge detection enhances the precision of edges presented in these images. In this work, we propose three metrics: the accuracy (Mac), the$\mathrm{F}_{1}$-score (Mfe), and the Matthews correlation coefficient normalized (nMcc). These metrics quantify the influence of the information from the intensity channels of PolSAR images on the information fusion process for edge detection.

Built-up area extraction from remote sensing images is essential for urban planning, disaster management and industrial development. In this study, we propose two built-up area indices for full (FP) and dual (DP) polarimetric Synthetic Aperture Radar (SAR) data. The built-up area index for FP SAR data is based on the dominant scattering mechanism of the electromagnetic (EM) waves from urban targets. In contrast, the built-up area index for DP SAR data is based on the scattering reflection symmetry property. The two proposed indexes are validated with full and extracted dual pol (VV-VH) scenes of a C-band RADARSAT-2 SAR data over urban San-Francisco. They show encouraging results in detecting urban areas within a SAR resolution cell. The overall accuracy of delineating built-up area is 84.2% for FP SAR data and 79% for DP SAR data.

Target decomposition methods for polarimetric Synthetic Aperture Radar (PolSAR) data aim at explaining the scattering information. In this regard, several conventional model-based methods use scattering power components to analyze polarimetric SAR data. However, the typical hierarchical process to enumerate power components uses various branching conditions, leading to several limitations. This study uses the 3D Barakat degree of polarization (DoP) to obtain the scattered wave polarization state. We employ the DoP to obtain the even bounce, odd-bounce, and diffuse scattering power components. Besides, we propose a measure of target scattering asymmetry, which is subsequently utilized to obtain the helicity power. All the power components in our approach are roll-invariant and non-negative, and the decomposition preserves the total power. We utilized C-band full polarimetric RADARSAT-2 data to show the effectiveness of the proposed decomposition.

Implementation of complex SAR speckle filtering algorithms is usually limited to experimental settings, that make use of heavy-duty computers or processing clusters. Operational applications of SAR imagery, such as those used to map flash-flooded areas, or to flag on-going deforestation, usually are not able to take advantage of these advanced filtering techniques. Here we introduce SDNLM3D, a fast and effective 3D filtering algorithm based on the non-local paradigm, suitable to be applied on cloud environments, such as the Google Earth Engine (GEE). A systematic, real-world based benchmark of more than 700 variations of the SDNLM3D revealed that the optimized version of the SDNLM3D filter outperforms the usual filters used operationally.

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.

In radar polarimetry, incoherent target decomposition techniques help extract scattering information from polarimetric synthetic aperture radar (SAR) data. This is achieved either by fitting appropriate scattering models or by optimizing the received wave intensity through the diagonalization of the coherency (or covariance) matrix. As such, the received wave information depends on the received antenna configuration. Additionally, a polarimetric descriptor that is independent of the received antenna configuration might provide additional information which is missed by the individual elements of the coherency matrix. This implies that existing target characterization techniques might neglect this information. In this regard, we suitably utilize the 2-D and 3-D Barakat degree of polarization which is independent of the received antenna configuration to obtain distinct polarimetric information for target characterization. In this study, we introduce new roll-invariant scattering-type parameters for both full-polarimetric (FP) and compact-polarimetric (CP) SAR data. These new parameters jointly use the information of the 2-D and 3-D Barakat degree of polarization and the elements of the coherency (or covariance) matrix. We use these new scattering-type parameters, which provide equivalent information as the Cloude α for FP SAR data and the ellipticity parameter χ for CP SAR data, to characterize various targets adequately. Additionally, we appropriately utilize these new scattering-type parameters to obtain unique non-model-based three-component scattering power decomposition techniques. We obtain the even-bounce, and the odd-bounce scattering powers by modulating the total polarized power by a proper geometrical factor derived using the new scattering-type parameters for FP and CP SAR data. The diffused scattering power is obtained as the depolarized fraction of the total power. Moreover, due to the nature of its formulation, the decomposition scattering powers are non-negative and roll-invariant while the total power is conserved. The proposed method is both qualitatively and quantitatively assessed utilizing the L-band ALOS-2 and C-band Radarsat-2 FP and the associated simulated CP SAR data.

Change detection is a topic of great interest in remote sensing. A good similarity metric to compute the variations among the images is the key to high-quality change detection. However, most existing approaches rely on the fixed threshold values or the user-provided ground truth in order to be effective. The inability to deal with artificial objects such as clouds and shadows is a significant difficulty for many change-detection methods. We propose a new unsupervised change-detection framework to address those critical points. The notion of homogeneous regions is introduced together with a set of geometric operations and statistic-based criteria to characterize and distinguish formally the change and nonchange areas in a pair of remote sensing images. Moreover, a robust and statistically well-posed family of stochastic distances is also proposed, which allows comparing the probability distributions of different regions/objects in the images. These stochastic measures are then used to train a support-vector-machine-based approach in order to detect the change/nonchange areas. Three study cases using the images acquired with different sensors are given in order to compare the proposed method with other well-known unsupervised methods.

The scattering information from targets is either estimated by fitting suitable scattering models or by optimizing the received wave intensity through the diagonalization of the coherency (or covariance) matrix. In this study, a new roll-invariant scattering-type parameter is introduced, which jointly uses the 3D Barakat degree of polarisation and the elements of the coherency matrix as the received wave information from full-polarimetric (FP) SAR data. This scattering-type parameter is analogous to that of Cloude-Pottier's α for FP SAR data. Furthermore, we utilize this new scattering-type parameter to obtain a unique non-model based three-component scattering power decomposition technique. The powers obtained from the proposed technique are guaranteed to be non-negative, with the total power being conserved. The proposed method is qualitatively and quantitatively assessed using the L-band ALOS-2 and the C-band Radarsat-2 FP SAR data.

The statistical properties of Synthetic Aperture Radar (SAR) image texture reveal useful target characteristics. It is well-known that these images are affected by speckle and prone to extreme values due to double bounce and corner reflectors. The GI0distribution is flexible enough to model different degrees of texture in speckled data. It is indexed by three parameters: α, related to the texture, γ, a scale parameter, and L, the number of looks. Quality estimation of α is essential due to its immediate interpretability. In this letter, we exploit the connection between the GI0and Pareto distributions. With this, we obtain six estimators that have not been previously used in the SAR literature. We compare their behavior with others in the noisiest case for monopolarized intensity data, namely single look case. We evaluate them using Monte Carlo methods for noncontaminated and contaminated data, considering convergence rate, bias, mean squared error, and computational time. We conclude that two of these estimators based on the Pareto law are the safest choices when dealing with actual data and small samples, as is the case of despeckling techniques and segmentation, to name just two applications. We verify the results with an actual SAR image.

Built-up (BU) area extraction from remote sensing images is important to monitor and manage urbanization and industrialization. In this letter, we propose two BU area extraction techniques based on the analysis of fully polarimetric synthetic aperture radar (PolSAR) data. Both methods exploit the geodesic distance on the unit sphere in the space of Kennaugh matrices. The first method is based on the three dominant scattering types in the scene and compares them with scattering models; if any of them matches with BU type elementary scattering models, then the pixel is said to belong to a BU area. The second method is based on a novel PolSAR BU index (RBUI) composed by considering scattering mechanisms from BU structures. The two proposed techniques are validated on two different urban scenes, one acquired at C-band by RADARSAT-2 and other at L-band by ALOS-2 SAR sensors.

In this letter, we propose a new despeckling filter for fully polarimetric synthetic aperture radar (PolSAR) images defined by 3×3 complex Wishart distributions. We first generalize the well-known structure tensor to deal with PolSAR data which allows to efficiently measure the dominant direction and contrast of edges. The generalization includes stochastic distances defined in the space of the Wishart matrices. Then, we embed the formulation into an anisotropic diffusion-like schema to build a filter able to reduce speckle and preserve edges. We evaluate its performance through an innovative experimental setup that also includes Monte Carlo analysis. We compare the results with a state-of-the-art polarimetric filter.

Crop growth monitoring using compact-pol synthetic aperture radar (CP-SAR) data is gaining attention with the rapid advancements toward operational applications. In this article, we propose a vegetation index for compact polarimetric (CP) SAR data [compact-pol radar vegetation index (CpRVI)]. The CpRVI is derived using the concept of a geodesic distance between the Kennaugh matrices projected on a unit sphere. This distance is utilized to compute a similarity measure between the observed Kennaugh matrix and the Kennaugh matrix of an ideal depolarizer (a realization of vegetation canopy). The similarity measure is then modulated with a scaled quantity derived from the scattering power ratio of the same and opposite sense polarization with respect to the transmitted circular polarization. In this article, we utilize time-series-simulated RADARSAT Constellation Mission (RCM) compact-pol SAR data (RH-RV) obtained from the full-pol RADARSAT-2 observations during the soil moisture active passive (SMAP) validation experiment 2016 (SMAPVEX16-MB) campaign in Manitoba, Canada, to assess the proposed vegetation index. Among the various crops grown in this region, in particular, we analyze the growth stages of wheat and soybean due to their different canopy structures. A temporal analysis of the proposed CpRVI with crop biophysical parameters [the plant area index (PAI) and vegetation water content (VWC)] at different phenological stages confirms the trend of CpRVI with the plant growth. Nevertheless, variations of CpRVI values are apparent with different plant densities for both the crop types. Also, the linear regression analysis confirms that the CpRVI values significantly correlate with PAI (r = 0.72 and 0.85) and VWC (r = 0.62 and 0.75) for both wheat and soybean. We observed good retrieval of PAI and VWC for both wheat and soybean.

We propose a generic scattering power factorization framework (SPFF) for polarimetric synthetic aperture radar (PolSAR) data to directly obtain N scattering power components along with a residue power component for each pixel. Each scattering power component is factorized into similarity (or dissimilarity) using elementary targets and a generalized volume model. The similarity measure is derived using a geodesic distance between pairs of 4×4 real Kennaugh matrices. In standard model-based decomposition schemes, the 3×3 Hermitian-positive semi-definite covariance (or coherency) matrix is expressed as a weighted linear combination of scattering targets following a fixed hierarchical process. In contrast, under the proposed framework, a convex splitting of unity is performed to obtain the weights while preserving the dominance of the scattering components. The product of the total power (Span) with these weights provides the nonnegative scattering power components. Furthermore, the framework, along with the geodesic distance (GD) is effectively used to obtain specific roll-invariant parameters such as scattering-type parameter (αGD), helicity parameter (τGD), and purity parameter (PGD). A PGD/αGDunsupervised classification scheme is also proposed for PolSAR images. The SPFF, the roll invariant parameters, and the classification results are assessed using C-band RADARSAT-2 and L-band ALOS-2 images of San Francisco.

This article proposes a generalized modeling and simulation approach for correlated synthetic aperture radar (SAR) texture based on the Gaussian coherent scatterer model. It is rooted in the physics-based coherent scatterer assumption where each observation in an SAR image is a coherent sum of multiple underlying Gaussian scatterers. The proposal generalizes existing single-point statistical models by allowing the number of scatterers to be a correlated random field. It can also generate the desired spatial correlation texture by stipulating the structure in both the Gaussian scattered field and the number of scatterers. This generalized model is derived theoretically and then validated by both simulations and experiments with SAR data from actual sensors.

The NLM (Nonlocal Means) approach is an effective framework for noise reduction. It relies on building, for each pixel, a convolution matrix whose entries are measures of similarities between patches. Such measures have to be computed between positive-definite Hermitian matrices when it comes to Polarimetric Synthetic Aperture Radar (PolSAR) imagery. Speckle reduction in this kind of images is a difficult task, as it is expected that several properties are well preserved by the filter. Torres et al. (2014) used a test statistic between Wishart distributions based on the Hellinger distance to compute such measures of similarity. In this work we assess the impact of using this and two other stochastic distances (Kullback-Leibler and Bhattacharya) under the same framework. The comparison is made using mean preservation, equivalent number of looks, edge correlation and the structural similarity index.

In this study, we propose a vegetation index for compact polarimetric (CP) SAR data (CpRVI) using a geodesic distance between two Kennaugh matrices projected on a unit sphere, as given in Ratha et. al. This distance is utilized to compute a similarity measure between the observed Kennaugh matrix and the Kennaugh matrix of an isotropic depolarizer. The proposed vegetation index is compared with the Radar Vegetation Index (RVI) obtained from RADARSAT-2 full-polarimetric SAR data. We use a time series of simulated compact-pol SAR data (RH-RV) obtained from the RADARSAT-2 data acquired during the SMAPVEX16-MB campaign over the Joint Experiment for Crop Assessment and Monitoring (JECAM) test site in Manitoba, Canada to assess the proposed vegetation index. Among the various crops grown in this region, only the growth stages of soybean are analyzed in this work. The temporal trend of CpRVI follows the growth stages of soybean. Regression analysis shows that CpRVI correlates better with the Plant Area Index (PAI) and Vegetation Water Content (VWC) than RVI.

In this paper, a generic scattering power factorization framework for Polarimetric SAR (PolSAR) data is proposed to directly obtain N scattering power components along with a residue power component for each pixel. Each scattering power component can be factorized into similarity (or dissimilarity) with the utilized scattering models. The similarity measure is derived using a geodesic distance between pairs of 4 × 4 real Kennaugh matrices. In a standard model-based decomposition framework, the 3×3 Hermitian positive semi-definite covariance (or coherency) matrix is expressed as a weighted linear combination of scattering targets. The scattering powers are usually obtained by solving an under-constrained system of equations by enforcing certain assumptions to reduce the number of variables. Moreover, the scattering powers are determined following a fixed hierarchy process. In contrast, under the proposed framework a convex splitting of unity is performed to obtain the weights while preserving the dominance of the scattering components. The product of the total power (Span) with these weights provides the non-negative scattering power components. The scattering power distribution obtained using the proposed framework is assessed over some selected areas from a RADARSAT-2 C-band PolSAR image of San Fran-cisco (SF), USA.

SAR image due to its nature of coherent imaging manifests both deterministic semantic information and speckle-like statistical textures. It is necessary to have a general representation scheme of the semantic-statistical two-layer hierarchy of SAR image so that semantic and textural information can be separated. Inspired by the correlated clutter simulation method proposed by Bustos et al [1]–[2], this paper studies a semantic-statistical convolution scheme to generate a SAR image from a semantic map. For each terrain type, we estimate the intensity distribution and correlated texture model and then generate textures with correlated clutter. The method is tested on actual SAR images of E-SAR data including urban and forest areas and Flevoland AirSAR data with 15 terrains.

In this letter, we propose a novel vegetation index from polarimetric synthetic-aperture radar (PolSAR) data using the generalized volume scattering model. The geodesic distance between two Kennaugh matrices projected on a unit sphere proposed by Ratha et al. is used in this letter. This distance is utilized to compute a similarity measure between the observed Kennaugh matrix and generalized volume scattering models. A factor is estimated corresponding to the ratio of the minimum to the maximum geodesic distances between the observed Kennaugh matrix and the set of elementary targets: trihedral, cylinder, dihedral, and narrow dihedral. This factor is then scaled and multiplied with the similarity measure to obtain the novel vegetation index. The proposed vegetation index is compared with the radar vegetation index (RVI) proposed by Kim and van Zyl. A time series of RADARSAT-2 data acquired during the Soil Moisture Active Passive Validation Experiment 2016 (SMAPVEX16-MB) campaign in Manitoba, Canada, is used to assessing the proposed RVI.

Images obtained from coherent illumination processes are contaminated with speckle. A prominent example of such imagery systems is the polarimetric synthetic aperture radar (PolSAR). For such a remote sensing tool, the speckle interference pattern appears in the form of a positive-definite Hermitian matrix, which requires specialized models and makes change detection a hard task. The scaled complex Wishart distribution is a widely used model for PolSAR images. Such a distribution is defined by two parameters: the number of looks and the complex covariance matrix. The last parameter contains all the necessary information to characterize the backscattered data, and thus, identifying changes in a sequence of images can be formulated as a problem of verifying whether the complex covariance matrices differ at two or more takes. This paper proposes a comparison between a classical change detection method based on the likelihood ratio and three statistical methods that depend on information-theoretic measures: the Kullback-Leibler (KL) distance and two entropies. The performance of these four tests was quantified in terms of their sample test powers and sizes using simulated data. The tests are then applied to actual PolSAR data. The results provide evidence that tests based on entropies may outperform those based on the KL distance and likelihood ratio statistics.

Master/Worker distributed programming model enables huge remote sensing data processing by assigning tasks to Workers in which data is stored. Cloud computing features include the deployment of Workers by using virtualized technologies such as virtual machines and containers. These features allow programmers to configure, create, and start virtual resources for instance. In order to develop remote sensing applications by taking advantage of high-level programming languages (e.g., R, Matlab, and Julia), users have to manually address Cloud resource deployment. This paper presents the design, implementation, and evaluation of the Infra.jl research prototype. Infra.jl takes advantage of Julia Master/Worker programming simplicity for providing automatic deployment of Julia Workers in the Cloud. The assessment of Infra.jl automatic deployment is only ~2.8 s in two different Azure Cloud data centers.

In this paper we study the local behavior of Fully PolSAR (Polarimetric Synthetic Aperture Radar) images defined by 3×3 complex Wishart distributions. We propose a generalization of the well-known structure tensor to Fully PolSAR images, as well as a measure of the smoothness of such predominant direction. This measure provides local information as the predominant direction of maximum variation of the complex Wishart distribution in a neighborhood of an image domain point ( x, y). We use stochastic distances defined in the space of Wishart matrices to generalize de structure tensor to PolSAR images. The study of the local behavior of PolSAR images address a number of processing and analysis problems. In particular, in this paper we apply this new approach to edge estimation using the magnitude of the PolSAR image variation provided by the generalized structure tensor. We also show promising results for simulated and actual Pol-SAR data.

This paper presents a novel scattering power factorization framework in radar polarimetry using a geodesic distance between the 4×4 real Kennaugh matrices of the observed and the elementary targets (viz. dihedral, trihedral, dipole etc.). The framework provides both qualitative and quantitative estimates of the dominance of elementary scattering mechanisms in a pixel. It is also flexible in terms of the number of elementary models against which an observed backscattering may be compared. Under this framework, the observed scattering is evaluated in terms of scattering similarities which provide the dominance of scattering mechanisms. This is then further utilized for a convex splitting of unity to obtain the intermediate weights. This leads to the weights being the product of similarity and dissimilarity of the observed pixel with the elementary scattering models. Finally, these weights are modulated with the total power (Span) to obtain the non-negative scattering powers. The results are shown for full polarimetric single-look ALOS-2 L-band dataset and a multi-look RADARSAT-2 C-band dataset.

The time has come to step down as the Editor-in-Chief for the IEEE Geoscience and Remote Sensing Letters (GRSL). Many things have changed after five years of coordinating the activities of this Journal, and the purpose of this Editorial is summarizing some of them.

In this letter, we propose a novel technique for obtaining scattering components from polarimetric synthetic aperture radar (PolSAR) data using the geodesic distance on the unit sphere. This geodesic distance is obtained between an elementary target and the observed Kennaugh matrix, and it is further utilized to compute a similarity measure between scattering mechanisms. The normalized similarity measure for each elementary target is then modulated with the total scattering power (Span). This measure is used to categorize pixels into three categories, i.e., odd-bounce, double-bounce, and volume, depending on which of the above scattering mechanisms dominate. Then the maximum likelihood classifier of Lee et al. based on the complex Wishart distribution is iteratively used for each category. Dominant scattering mechanisms are thus preserved in this classification scheme. We show results for L-band AIRSAR and ALOS-2 data sets acquired over San Francisco and Mumbai, respectively. The scattering mechanisms are better preserved using the proposed methodology than the unsupervised classification results using the Freeman-Durden scattering powers on an orientation angle corrected PolSAR image. Furthermore: 1) the scattering similarity is a completely nonnegative quantity unlike the negative powers that might occur in double-bounce and odd-bounce scattering component under Freeman-Durden decomposition and 2) the methodology can be extended to more canonical targets as well as for bistatic scattering.

The GI0distribution is a competitive tool for SAR image description. This distribution is useful for describing speckled imagery because it models adequately areas with different degrees of texture. Data simulation is crucial for the development of new methods of automatic interpretation of this type of images. We compare four alternatives for generating data under the GI0distribution. The experiments are performed on a variety of programming languages and, a number of criteria to test the fidelity of the generated data are applied.

Polarimetric Synthetic Aperture Radar (PolSAR) images are an important source of information. Speckle noise gives SAR images a granular appearance that makes interpretation and analysis hard tasks. A major issue is the assessment of information content in these kind of images, and how it is affected by usual processing techniques. We study this problem from the classification accuracy viewpoint. Our input is an actual PolSAR image, the control parameter the size of the MBPolSAR filter, and the output the classification precision obtained applying the SVM algorithm to the filtered data. Kappa, Overall Accuracy, and Classification Accuracy coefficients are the measures of map precision.

Statistical modeling of Synthetic Aperture Radar (SAR) images is an important tool for image processing and interpretation, because it can contribute to a better understanding of the terrain electromagnetic scattering mechanisms. To that end, the G0Idistribution is able to characterize a large number of targets. This distribution depends on three parameters: texture, scale, and the number of looks. The first has received special attention in the literature because it is closely related number of elementary backscatterers in the scene. In this paper we compare estimators for the texture parameter in the single look case. The single-look G0Ilaw is a Pareto distribution whose tail index is related to the texture parameter, so we propose a tail index estimator. The estimators performance is analyzed in terms convergence, bias and mean squared error. Then we apply these estimators to actual data.

Image processing algorithms require high processing capabilities. Most of these algorithms use linear algebraic operations (BLAS), for instance, through the Combinatorial BLAS [1], and Elemental [2] programming supports. Such operations may require unavailable computer processing resources. CloudArray is funded by Microsoft Azure Research Award, Brazilian National Council for Scientific and Technological Development (CNPq), and Alagoas Research Foundation (FAPEAL).

Synthetic Aperture Radar (SAR) imaging play a central role in Remote Sensing applications due to, among other important features, its ability to provide high-resolution, day-and-night and almost weather-independent images. SAR images are affected from a granular contamination, speckle noise, that can be described by a multiplicative model. Many de-speckling techniques have been proposed in the literature, as well as measure of the quality of the results they provide. Speckle filters provide X, estimator of the true image X̂, based solely on the observed data Z, then an ideal estimator would be the one for which the ratio of the observed image to the filtered one Π = Z/X̂ is only speckle. The quality of the filter can be, then, assessed by its closeness to this hypothesis. We tackle the problem of quantitatively measuring the quality of speckle filters by the criterion of lack of structure in the ratio image they produce. We propose the use of Haralick's textural features for the identification of remaining structures in ratio images. In order to do so, we first analyze the distribution of such features under the null hypothesis (H0) of absence of structure; then we sample from ratio images with barely visible remaining structures.

This work presents the use of stochastic measures of similarities as features with statistical significance for the design of despeckling nonlocal means filters. Assuming that the observations follow a Gamma model with two parameters (mean and number of looks), patches are compared by means of the Kullback-Leibler and Hellinger distances, and by their Shannon entropies. A convolution mask is formed using the p-values of tests that verify if the patches come from the same distribution. The filter performances are assessed using well-known phantoms, three measures of quality, and a Monte Carlo experiment with several factors. The proposed filters are contrasted with the Refined Lee and NL-SAR filters.

Polarimetric Synthetic Aperture Radar (PolSAR) is having an increasingly positive impact in the Remote Sensing community since the launch of the first practical fully polarimetric sensor, AIRSAR, in 1985. The availability and relevance of these data makes it important to offer users state-of-the-art techniques for PolSAR image processing and analysis. One of the most used platforms is PolSARpro, a freely available software which includes tools for data processing, extraction, analysis and visualization. As PolSARpro has not yet incorporated some of the advances stemming from the Information Theory framework, in this work we present the current state of the development of a system which integrates such tools using TerraLib.

After more than a year of serving as Editor-in-Chief, I have collected impressions from authors, reviewers, and Associate Editors about certain patterns that lead to having manuscripts accepted. This Editorial aims at sharing these impressions.

The angle of rotation (θ) of any object about the line of sight (LOS) is known as the polarization orientation angle (OA). The OA is found to be non-zero for undulating terrains and man-made targets oriented away from the radar LOS. This effect is more pronounced at lower frequencies (eg. L- and P-bands). The OA shift is not only induced by azimuthal slope but also by range slope. The OA shift increases the cross-polarization (HV) intensity and subsequently the co-variance or the coherency matrix becomes reflection asymmetric. Compensating this OA prior to any model-based decomposition technique for geophysical parameter estimation or classification is crucial. In this paper a new method has been proposed for OA estimation based on a stochastic distance. The OA is estimated by maximizing the Hellinger distance between the un-rotated and rotated diagonal elements of the coherency matrix.

Motivated by studies of wireless ad hoc networks in obstructed environments, in this work we focus on the problem of establishing connectivity at an intersection of two roads, or streets, surrounded by obstacles. An instance of the problem is defined by four street segments meeting at an intersection point, a street width, a node density at each street segment and a transmission range of the communication nodes. The problem that we focus on consists in computing the probability that there is a communication path connecting all four intersecting street segments. We propose a simplified model that approximates the connectivity properties in this setting and compute a lower bound for the connectivity probability. We compare our result to a Euclidean Line-of-Sight (LoS) model and show that our model provides an accurate approximation, while greatly simplifying the analytical treatment.

A wireless sensor network can be used to collect and process environmental data, which is often of multivariate nature. This work proposes a multivariate sampling algorithm based on component analysis techniques in wireless sensor networks. To improve the sampling, the algorithm uses component analysis techniques to rank the data. Once ranked, the most representative data is retained. Simulation results show that our technique reduces the data keeping its representativeness. In addition, the energy consumption and delay to deliver the data on the network are reduced.

The scaled complex Wishart distribution is a widely used model for multilook full polarimetric synthetic aperture radar data whose adequacy is attested in this paper. Classification, segmentation, and image analysis techniques that depend on this model are devised, and many of them employ some type of dissimilarity measure. In this paper, we derive analytic expressions for four stochastic distances between relaxed scaled complex Wishart distributions in their most general form and in important particular cases. Using these distances, inequalities are obtained that lead to new ways of deriving the Bartlett and revised Wishart distances. The expressiveness of the four analytic distances is assessed with respect to the variation of parameters. Such distances are then used for deriving new tests statistics, which are proved to have asymptotic chi-square distribution. Adopting the test size as a comparison criterion, a sensitivity study is performed by means of Monte Carlo experiments suggesting that the Bhattacharyya statistic outperforms all the others. The power of the tests is also assessed. Applications to actual data illustrate the discrimination and homogeneity identification capabilities of these distances.

This paper proposes improved methods for the maximum likelihood (ML) estimation of the equivalent number of looks L. This parameter has a meaningful interpretation in the context of polarimetric synthetic aperture radar (PolSAR) images. Due to the presence of coherent illumination in their processing, PolSAR systems generate images which present a granular noise called speckle. As a potential solution for reducing such interference, the parameter L controls the signal-noise ratio. Thus, the proposal of efficient estimation methodologies for L has been sought. To that end, we consider first that a PolSAR image is well described by the scaled complex Wishart distribution. In recent years, Anfinsen have derived and analyzed estimation methods based on the ML and on trace statistical moments for obtaining the parameter L of the unscaled version of such probability law. This paper generalizes that approach. We present the second-order bias expression proposed by Cox and Snell for the ML estimator of this parameter. Moreover, the formula of the profile likelihood modified by Barndorff-Nielsen in terms of L is discussed. Such derivations yield two new ML estimators for the parameter L, which are compared to the estimators proposed by Anfinsen The performance of these estimators is assessed by means of Monte Carlo experiments, adopting three statistical measures as comparison criterion: the mean square error, the bias, and the coefficient of variation. Equivalently to the simulation study, an application to actual PolSAR data concludes that the proposed estimators outperform all the others in homogeneous scenarios.

The use of topological features, more specifically, the importance of an element related to its structural position, is a subject widely studied in the literature. For instance, the theory of complex networks provides centrality measures that have been applied to a large variety of fields (e.g., social sciences and biology). In this work, we propose a new topological measure, the Sink Betweenness (SBet), which stems from the theory of complex networks but is adapted to Wireless Sensor Networks (WSNs) to capture relevant information for this kind of network. We also provide a distributed algorithm to calculate it, and show its applicability to two different scenarios. The first one is focused on data fusion applications for event-driven WSNs, where we devise a tree-based data collection algorithm that takes advantage of node centrality to improve the data fusion efficiency. The second scenario is focused on energy balancing problems, more specifically in a problem called energy hole , where nodes closer to the sink are more likely to relay a larger number of packets than those that are further. This phenomenon is strongly related to the topology induced by the deployment of nodes along the sensor field, and it can be effectively captured by the SBet metric. Thus, we devise a data collection algorithm that is able to distribute the relay task more evenly. Simulation results show that the SBet metric can be satisfactorily used in both scenarios. We compare the proposed approach with some of the most efficient available data fusion algorithms, and show that the proposed algorithm generates consistently good-quality data collection infrastructures which require significantly smaller overhead. The use of SBet allows to alleviate the energy-hole effects by evenly balancing the relay load, and thus increasing the network lifetime. These two applications illustrate how the topology awareness can be used to improve different network functions in a WSN.

The Potts model is a commonplace in Bayesian image analysis since its introduction as a convenient image prior. It is able to describe the distribution of classes, yielding a regularization term in the cost function to be minimized in many classification problems. The simplest isotropic version depends on a scalar smoothness parameter; its value controls the relative influence of the regularization with respect to the data. This work analyzes the performance of two pseudolike-lihood estimation procedures of the smoothness parameter of the Potts model: the classical one, which employs the map of classes, and a new estimator based on the posterior distribution, which also incorporates the evidence provided by the observed data. Our simulation study shows that the combination of prior information and observation data gives accurate β estimations when true data is provided. We also discuss its influence in the classification results when comparing contextual ICM (Iterated Conditional Modes) classification experiments with multispectral optical imagery, estimating the scalar parameter β with our estimator and the classical one. Our experiment shows promising results, since ICM with our estimator is able to distinguish image features that the classical ICM does not.

We analyze the information content in COSMO-SkyMed data with different acquisition modes and polarizations. A set of discrimination problems ranging from difficult to simple using samples from different land cover types is presented. Several separability measures, i.e. stochastic distances and their derived hypothesis tests, are applied to pairs of samples, and their ability to discriminate is assessed. From the studied modes, class separability of water, pasture, forest and urban is enhanced if the lowest resolution mode is used. Both, ascending and left looking acquisition geometry yield better classification results. Distance measurement tests between samples of the same class give better results for HH polarization than for VV polarization suggesting that the analyzed cover properties are better described by that microwave configuration.

Images obtained from coherent illumination processes are contaminated with speckle noise, with polarimetric synthetic aperture radar (PolSAR) imagery as a prominent example. With adequacy widely attested in the literature, the scaled complex Wishart distribution is an acceptable model for PolSAR data. In this perspective, we derive analytical expressions for the Shannon, Rényi, and restricted Tsallis entropy measurements under this model. Relationships between the derived measures and the parameters of the scaled Wishart law (i.e., the equivalent number of looks and the covariance matrix) are discussed. In addition, we obtain the asymptotic variances of the Shannon and Rényi entropy measurements when replacing distribution parameters by maximum-likelihood estimators. As a consequence, confidence intervals based on the Shannon and Rényi entropy measurements are also derived and proposed as new ways of capturing contrast. New hypothesis tests are additionally proposed using these results, and their performance is assessed using simulated and real data. In general terms, the test based on the Shannon entropy outperforms those based on Rényi entropy.

Video streaming capabilities over Vehicular Ad Hoc Networks (VANETs) are crucial to the development of interesting and valuable services. However, VANETs are a challenging environment to this kind of communication due to the dispersion and movement of vehicles. In this work, we present a feasible solution to this problem. The VIdeo Reactive Tracking-based UnicaSt protocol (VIRTUS) is a receiving-based solution that uses vehicles' current and future location for a selection policy of relaying nodes. It fulfills video streaming requirements without incurring into an excessive number of transmissions. Besides that, it outperforms other baseline solutions.

This work presents a region based classifier for Polarimetric SAR (PolSAR) images. The classifier uses the stochastic distances derived from the complex Wishart Model, obtained from the h-φ family of divergences. Adittionaly, a hypothesis test derived from the stochastic distance is also employed in the classification process. The region based classifier, using the Bhattacharyya distance, was applied to a polarimetric SIR-C image from an agricultural area in northeastern Brazil. The region based classification result significantly overperformed the a pixel based/contextual PolSAR classification based on the Maximum Likelihood/Iterated Conditional Modes. Such evidence lead us to conclude that the region based stochastic distance and hypothesis test classifier offers a good potential at identifying the land cover classes on a PolSAR image.

Event detection is a topic widely discussed in the wireless sensor network (WSN) community. The goal of this process is to identify when the collected data represents an event occurrence. The lack of uniformity when approaching this problem, such as the modeling of the data collected by sensors, is an obstacle to the comparison among the different proposals. In this work, we present an extension of the Diffuse framework for scenarios regarding event detection, while considering settings with inaccurate and fault-susceptible measurements made by non-ideal sensing devices in a noisy environment. Based on that framework, we compare a new proposed algorithm with a method based on the literature, obtaining hit rates of event detection above 72% in settings with 30% of sensor faults.

Connectivity properties of wireless networks in open space are typically modeled using geometric random graphs and have been analyzed in depth in different studies. Such scenarios, however, do not often represent situations encountered in practice, like urban environments or indoor spaces, which are deeply affected by obstacles. In this work, we present a model for obstructed wireless ad hoc networks consisting of a set of n nodes, deployed at random in a lattice square of size g×g, with a common transmission range r. For positioning the nodes in the field, all segments are considered as one-dimensional, but for communication purposes, we add a parameter µ to model the segments' width. Our model can be used to study the structure of obstructed networks analytically, as well as to simulate and evaluate a variety of node deployment strategies and the resulting network topologies. We derive analytical forms for the probability of existing crossing links between parallel and perpendicular segments sharing an intersection, toward a first topological characterization of our model. Moreover, we compute a lower bound for the probability of connectivity at intersections between segments, and apply percolation theory to derivate the Critical Transmission Range for connectivity in the overall network, i.e., the minimum transmission range that generates communication graphs that are connected with high probability.

Given the different nature of optical and radar data, it is reasonable the idea that each type of data can contribute in complementary ways for different applications. This paper aims at analyzing the potential joint usage of optical and Synthetic Aperture Radar (SAR) data for land use and land cover classification in a region located in the Brazilian Amazon. To achieve this objective, we evaluated region-based classifications using separated and fused optical and SAR data. Data were images from the Landsat 5/TM sensor and amplitude multipolarized images from the ALOS/PALSAR sensor. The images were classified using a region-based classifier based on the Bhattacharyya distance between Gaussian distributions. The TM data alone is better for classify land cover classes with occurrence of trees or shrubs, while SAR data contribute to improve the classification results in low vegetated areas.

Synthetic aperture radar (SAR), ultrasound-B, laser, and sonar imagery are contaminated with speckle noise. The statistical modelling of such contamination is well described by the multiplicative model, which yields the G0distribution. In particular, reliable image contrast measures are sought in order to discriminate targets. To that end, we present statistical methods based on stochastic divergences and on the Kolmogorov-Smirnov distance for G0data. Their performance is quantified according to their test sizes and powers. A robustness analysis is also presented for several degrees of contamination. We show that the proposed tests based on triangular and arithmetic-geometric measures outperform the Kolmogorov-Smirnov distance.

Images obtained with coherent illumination, as is the case of sonar, ultrasound-B, laser, and synthetic aperture radar, are affected by speckle noise which reduces the ability to extract information from the data. Specialized techniques are required to deal with such imagery, which has been modeled by the${\cal G}^{0}$distribution and, under which, regions with different degrees of roughness and mean brightness can be characterized by two parameters; a third parameter, which is the number of looks, is related to the overall signal-to-noise ratio. Assessing distances between samples is an important step in image analysis; they provide grounds of the separability and, therefore, of the performance of classification procedures. This paper derives and compares eight stochastic distances and assesses the performance of hypothesis tests that employ them and maximum likelihood estimation. We conclude that tests based on the triangular distance have the closest empirical size to the theoretical one, while those based on the arithmetic–geometric distances have the best power. Since the power of tests based on the triangular distance is close to optimum, we conclude that the safest choice is using this distance for hypothesis testing, even when compared with classical distances as Kullback–Leibler and Bhattacharyya.

This paper presents a comparison between two types of initializations for multilook polarimetric SAR image segmentation: a random partition and a sample quantile partition. These are the inputs of a stochastic expectation-maximization algorithm that uses a mixture of G0Pdistributions to describe the data. The parameters are unknown, and estimated by the moments method. The G0Plaw is able to describe different type of targets, like urban areas, vegetation and pasture. The experimental results on real PolSAR data are reported, showing that the use of G0Pmodel with quantile partition inicialization provide good segmentation results with few iterations.

Adaptive Virtual Environments have been developed aiming at generating 3D environments adapted to user's necessities and interests. Navigation aid techniques and content adaptation improve user interaction in such environments. This article presents a system for supporting real time adaptive virtual environments. A multiagents architecture is used to manage contents updating in the virtual world according to user profile evolution. Its agents utilize the User Model, the Environment Model and a 3D objects database for decision-making on the necessary updating. A manager agent is responsible to accompany the user's actions through the user interface to collect information that may be used to update his/her profile. This agent also controls the communication between agents.

This paper presents the use of a new distribution for fully polarimetric image classification. Several classification strategies are compared in order to assess the importance of a careful statistical modeling of the data and the complementary nature of the information provided by different frequencies. Spatial context, which is relevant in order to obtain good results with noisy data, is described by means of the multiclass Potts model, and an iterated conditional modes classification algorithm that employs pseudolikelihood is proposed. The data are described using multivariate Gaussian laws and fully multilook polarimetric distributions arising from the multiplicative model. L-band, C-band, and both bands are used to assess the influence of dimensionality on the classification. Contextual and pointwise maximum-likelihood classifications are compared using real data. Results show that both context and number of frequencies contribute for better classification products, and that, a careful statistical description of the data leads to improved results.

This paper presents a quantitative comparison of the performance of skin detection techniques for a Web-based system. The procedures under analysis employ dimensionality reduction, with or without color correction. We propose a rule for deciding if an image requires color correction and, if needed, which is the best procedure. Geometric rules, parametric methods and histogram-based techniques are compared in terms of accuracy and performance. With the proposed heuristic for color correction, the best performances are achieved by a classifier based on the mixture of two Gaussian laws applied to data projected with principal component analysis and a by a KDD-based rule that operates on the RGB space.

Virtual environments able to track users actions and adapt to the user's profile are closer to their needs. This article presents a multi-agent architecture for managing virtual reality components, allowing the generation of adaptive virtual environments in real time adapted to the user's cognitive evolution. The agents which act in such architecture, employ a domain ontology to generate 3D virtual world objects and perform queries to a DBMS in order to obtain new objects. Agents need updated information from the user model for the decision process, so user-modelling techniques are also considered in this proposal.

In this work the G/sub A//sup 0/ distribution is assumed as the universal model for amplitude synthetic aperture radar (SAR) imagery data under the multiplicative model. The observed data, therefore, is assumed to obey a G/sub A//sup 0/ (/spl alpha/, /spl gamma/, n) law, where the parameter n is related to the speckle noise, and (/spl alpha/, /spl gamma/) are related to the ground truth, giving information about the background. Therefore, maps generated by the estimation of (/spl alpha/, /spl gamma/) in each coordinate can be used as the input for classification methods. Maximum likelihood estimators are derived and used to form estimated parameter maps. This estimation can be hampered by the presence of corner reflectors, man-made objects used to calibrate SAR images that produce large return values. In order to alleviate this contamination, robust (M) estimators are also derived for the universal model. Gaussian maximum likelihood classification is used to obtain maps using hard-to-deal-with simulated data, and the superiority of robust estimation is quantitatively assessed.

A new class of distributions, G distributions, arising from the multiplicative model is presented, along with their main properties and relations. Their densities are derived for complex and multilook intensity and amplitude data. Classical distributions, such as K, are particular cases of this new class. A special case of this class called G/sup 0/, that has as many parameters as K distributions, is shown able to model extremely heterogeneous clutter, such as that of urban areas, that cannot be properly modeled with K distributions. One of the parameters of this special case is related to the degree of homogeneity, and a limiting case is that of a scaled speckle. The advantage of the G/sup 0/ distribution becomes evident through the analysis of a variety of areas (urban, primary forest and deforested) from two sensors.