High-resolution Polarimetric Synthetic Aperture Research Articles

BSDSNet: Dual-Stream Feature Extraction Network Based on Segment Anything Model for Synthetic Aperture Radar Land Cover Classification

Land cover classification using high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images obtained from satellites is a challenging task. While deep learning algorithms have been extensively studied for PolSAR image land cover classification, the performance is severely constrained due to the scarcity of labeled PolSAR samples and the limited domain acceptance of models. Recently, the emergence of the Segment Anything Model (SAM) based on the vision transformer (VIT) model has brought about a revolution in the study of specific downstream tasks in computer vision. Benefiting from its millions of parameters and extensive training datasets, SAM demonstrates powerful capabilities in extracting semantic information and generalization. To this end, we propose a dual-stream feature extraction network based on SAM, i.e., BSDSNet. We change the image encoder part of SAM to a dual stream, where the ConvNext image encoder is utilized to extract local information and the VIT image encoder is used to extract global information. BSDSNet achieves an in-depth exploration of semantic and spatial information in PolSAR images. Additionally, to facilitate a fine-grained amalgamation of information, the SA-Gate module is employed to integrate local–global information. Compared to previous deep learning models, BSDSNet’s impressive ability to represent features is akin to a versatile receptive field, making it well suited for classifying PolSAR images across various resolutions. Comprehensive evaluations indicate that BSDSNet achieves excellent results in qualitative and quantitative evaluation when performing classification tasks on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset. Compared to the suboptimal results, our method improves the Kappa metric by 3.68% and 0.44% on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset, respectively.

A Statistical Rule of the Stokes Parameters of Pol-SAR for Identifying Flat Surface in PSR

Finding a flat area is critical for choosing the landing site, especially in the permanently shadowed region (PSR) without reference of optical images. The digital elevation model (DEM) data are not enough to describe the complex lunar topography in the landing mission. High-resolution polarimetric synthetic aperture radar (pol-SAR) can acquire the polarized scattering map of lunar surface. In this paper, Chandrayaan-2 pol-SAR images of flat and rocky regions at non-PSR are selected with assistance of optical image. The statistics of the Stokes parameters can tell the difference between flat and rocky surfaces. Enhanced backscattering with a large variance from rough surfaces with rocks can be distinguished from the smooth and flat areas. Large value of the first Stokes parameter I1 with extendedly distributed probability distribution function is related with the scatterings from rough surface and rocks. A statistics rule of the Stokes parameters is established, and is applied to identifying the flat regions in the PSR of the crater Shoemaker.

MP-ResNet: Multipath Residual Network for the Semantic Segmentation of High-Resolution PolSAR Images

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the inference of speckle noises. The Gaofen contest has provided open access of a high-quality PolSAR semantic segmentation dataset. Taking this chance, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to make the best use of the features learned from its different branches. Ablation studies show that the MPResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, whereas its computational costs are not much increased. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

Polarimetric SAR Image Terrain Classification

In practical applications of automated terrain classification from high-resolution polarimetric synthetic aperture radar (PolSAR) imagery, different terrain types may inherently contain a high level of internal variability, as when a broadly defined class (e.g., “trees”) contains elements arising from multiple subclasses (pine, oak, and willow). In addition, real-world factors such as the time of year of a collection, the moisture content of the scene, the imaging geometry, and the radar system parameters can all increase the variability observed within each class. Such variability challenges the ability of classifiers to maintain a high level of sensitivity in recognizing diverse elements that are within-class, without sacrificing their selectivity in rejecting out-of-class elements. In an effort to gauge the degree to which classifiers respond robustly in the presence of intraclass variability and generalize to untrained scenes and conditions, we compare the performance of a suite of classifiers across six broad terrain categories from a large set of polarimetric synthetic aperture radar (PolSAR) image sets. The main contributions of this article are as follows: 1) an analysis of the robustness of a variety of current state-of-the art classification algorithms to intraclass variability found in PolSAR image sets, and 2) the associated PolSAR image and feature data that Sandia is releasing to the research community with this publication. The analysis of the classification algorithms we provide will serve as a benchmark of performance for the future PolSAR terrain classification algorithm research and development enabled by the image sets and data provided. By sharing our analysis and high-resolution fully polarimetric Sandia data with the research community, we enable others to develop and assess a new generation of robust terrain classification algorithms for PolSAR.

Unsupervised Hierarchical Land Classification Using Self-Organizing Feature Codebook for Decimeter-Resolution PolSAR

In this paper, we propose a hierarchical polarization feature generation using a self-organizing codebook to realize unsupervised land classification that fully utilizes the detailed polarization information contained in high-resolution polarimetric synthetic aperture radar (PolSAR) data. PolSAR has reached a decimeter-level high resolution. In general, conventional methods lower the resolution of the PolSAR data to 10–20 m in the real-space distance to classify observation regions into land classes such as farm, forest, and town. However, lowering resolution prevents us from discovering new land classes potentially enabled by the resolution enhancement. The hierarchical method we propose here not only classifies observation regions successfully into land classes such as farm, forest, and town that humans can naturally distinguish but also discovers new land subclasses findable only in high-resolution PolSAR data. We explain these two types of our achievements (classification/discovery) through experimental results for Japan Aerospace Exploration Agency’s polarimetric and interferometric airborne SAR-L2 data having decimeter resolution.

Level Set Segmentation Algorithm for High-Resolution Polarimetric SAR Images Based on a Heterogeneous Clutter Model

In this paper, a heterogeneous clutter model named ${\mathcal L}$ distribution is introduced into the level set method for segmentation of high-resolution polarimetric synthetic aperture radar (PolSAR) images. Level set methods are robust and effective techniques for segmentation. However, traditional level set methods for PolSAR data are based on the complex Wishart distribution, which is not an applicable model to high-resolution PolSAR images and heterogeneous regions such as forest and urban areas. The ${\mathcal L}$ distribution is proved to be a highly flexible model for multilook PolSAR data, which is based on the product model with a generalized-gamma-distributed texture component. The ${\mathcal L}$ -model-based level set segmentation method is assessed using C-band, X-band, and L-band PolSAR data acquired by RADARSAT-2, TerraSAR-X, and ESAR sensors, respectively. Experimental results show that the ${\mathcal L}$ -distribution model has a better capacity for characterizing high-resolution PolSAR data, especially for extremely heterogeneous regions. Compared with the Wishart-model-based and Kummer-U-model-based level set methods and Markov random field based methods, it is observed that the proposed level set algorithm can obtain more precise segmentation results.

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Segmentation techniques play an important role in understanding high-resolution polarimetric synthetic aperture radar (PolSAR) images. PolSAR image segmentation is widely used as a preprocessing step for subsequent classification, scene interpretation and extraction of surface parameters. However, speckle noise and rich spatial features of heterogeneous regions lead to blurred boundaries of high-resolution PolSAR image segmentation. A novel segmentation algorithm is proposed in this study in order to address the problem and to obtain accurate and precise segmentation results. This method integrates statistical features into a fractal net evolution algorithm (FNEA) framework, and incorporates polarimetric features into a simple linear iterative clustering (SLIC) superpixel generation algorithm. First, spectral heterogeneity in the traditional FNEA is substituted by the G0 distribution statistical heterogeneity in order to combine the shape and statistical features of PolSAR data. The statistical heterogeneity between two adjacent image objects is measured using a log likelihood function. Second, a modified SLIC algorithm is utilized to generate compact superpixels as the initial samples for the G0 statistical model, which substitutes the polarimetric distance of the Pauli RGB composition for the CIELAB color distance. The segmentation results were obtained by weighting the G0 statistical feature and the shape features, based on the FNEA framework. The validity and applicability of the proposed method was verified with extensive experiments on simulated data and three real-world high-resolution PolSAR images from airborne multi-look ESAR, spaceborne single-look RADARSAT-2, and multi-look TerraSAR-X data sets. The experimental results indicate that the proposed method obtains more accurate and precise segmentation results than the other methods for high-resolution PolSAR images.

Discovery of Semantic Relationships in PolSAR Images Using Latent Dirichlet Allocation

We propose a multilevel semantics discovery approach for bridging the semantic gap when mining high-resolution polarimetric synthetic aperture radar (PolSAR) remote sensing images. First, an Entropy/Anisotropy/Alpha-Wishart classifier is employed to discover low-level semantics as classes representing the physical scattering properties of targets (e.g., low-entropy/surface scattering/high anisotropy). Then, the images are tiled into patches and each patch is modeled as a bag-of-words, a histogram of the class labels. Next, latent Dirichlet allocation is applied to discover their higher level semantics as a set of topics. Our results demonstrate that topic semantics are close to human semantics used for basic land-cover types (e.g., grassland). Therefore, using the topic description (bag-of-topics) of PolSAR images leads to a narrower semantic gap in image mining. In addition, a visual exploration of the topic descriptions helps to find semantic relationships, which can be used for defining new semantic categories (e.g., mixed land-cover types) and designing rule-based categorization schemes.

Comparative study on the speckle filters for the very high-resolution polarimetric synthetic aperture radar imagery

With the emergence of very high-resolution airborne synthetic aperture radar systems, it is necessary to reinvestigate these proposed methods with respect to their despeckling performances. As for the very high resolution polarimetric synthetic aperture radar (PolSAR) data, the presumption that the resolution cell is much larger than the radar wavelength becomes ineffective. Therefore, some classic and new filters are thoroughly reviewed. For the evaluation of speckle filters, both indicators for polarimetric information and spatial information are listed. The absolute relative bias is introduced, with the purpose of measuring the filtering performance concerning the indicators for polarimetric information. Moreover, the ratio of half power point width is employed to quantitatively assess the degree of point target preservation. A series of experiments are carried out based on the real PolSAR imagery which is obtained from an uninhabited aerial vehicle synthetic aperture radar system. It can be concluded that existing filters can only attain good performance with reference to part of the indicators. As regards very high-resolution PolSAR imagery, it is necessary to conceive more apposite new filters or make improved versions of the existing filters.

A parameter inversion for sea bridge based on high-resolution polarimetric synthetic aperture radar

Each reflection return of a bridge over water is displayed as wide stripe in a high-resolution synthetic aperture radar (SAR) image, which lead to difficulties in a parameter inversion. Therefore, a method of bridge parameter inversion is proposed for high-resolution full polarimetric SAR (PolSAR). First, the single, double and triple-bounce returns from each component of the bridge are distinguished by the polarization scattering features. Then the reasons which lead to the backscatter echoes of the bridge over water being displayed as stripes are analyzed, using a principle of microwave reflection, as well as an extraction method for each reflection return, and a parameter retrieval method is obtained. Finally, the parameters of the bridge, including the height (top and bottom surfaces of the sea bridge), width, thickness, span, and height of the bridge tower, are retrieved using full polarimetric AIRSAR data. When a comparison of the measured data is completed, the results indicate that the proposed method can invert the parameters with a high accuracy, and that the inversion error of the bridge height (bottom surface) is only 1.3%. Moreover, the results also show that for the high-resolution SAR, the C and L-band images have the same ability in regards to parameter retrieval.

Spherical Symmetry of Complex Stochastic Models in Multivariate High-Resolution PolSAR Images

The multiplicative model, expressed as a product between the square root of a scalar positive quantity (texture) and the description of an equivalent homogeneous surface (speckle), is one of the most appropriate and disseminated models used to describe high-resolution polarimetric synthetic aperture radar (PolSAR) clutter. Generally, the texture is assumed polarization independent, which causes PolSAR data to present a spherical symmetry property, allowing for the usage of most of the algorithms present in the literature. Nevertheless, the existence of polarization-dependent clutter has also been reported, for which specific algorithms need to be derived. Therefore, it becomes clear that the first step in SAR data analysis should be the validation of the model employed. Within this context, this paper presents a new methodological framework to assess the conformity of multivariate high-resolution SAR data with respect to the product model in terms of asymptotic statistics. More precisely, spherical symmetry is investigated by applying statistical hypothesis testing on the structure of the quadricovariance matrix. Simulated data, data from the P-band airborne data set acquired by the Office National d'Etudes et de Recherches Aerospatiales (ONERA) over the French Guiana in 2009 in the frame of the European Space Agency campaign TropiSAR and a RAMSES X-band image acquired over Bretigny, France, are taken into consideration to investigate the performance of the derived test. The detection results are qualitatively and quantitatively analyzed, and some important conclusions are drawn regarding the methodology employed in analyzing SAR data.

A level set method for segmentation of high-resolution polarimetric SAR images using a heterogeneous clutter model

To overcome the problem of strong speckle and texture in high-resolution polarimetric synthetic aperture radar (PolSAR) images, a novel level set segmentation method that uses a heterogeneous clutter model is proposed in this article. Because the KummerU distribution has the capability to describe the statistics of PolSAR imagery in both homogeneous and heterogeneous scenes, it is used to replace the traditional Wishart distribution as the statistical model that defines the energy function for PolSAR images in order to improve the accuracy of the segmentation. Moreover, in order to reduce the computation intensity, an enhanced distance-regularized level set evolution (DRLSE-E) term is applied to improve the computational efficiency. The experimental results obtained using synthetic and real PolSAR images show that the method described has an accuracy 10% better than level set methods based on Wishart distributions. It is also shown that adding the DRLSE-E term reduces the computation time by about a third, thus demonstrating the effectiveness of our method.

Polarimetric Incoherent Target Decomposition by Means of Independent Component Analysis

This paper presents an alternative approach for polarimetric incoherent target decomposition (ICTD) dedicated to the analysis of very high-resolution polarimetric synthetic aperture radar (POLSAR) images. Given the non-Gaussian nature of the heterogeneous POLSAR clutter due to the increase in spatial resolution, the conventional methods based on the eigenvector target decomposition can ensure uncorrelation of the derived backscattering components at most. By introducing the independent component analysis (ICA) in lieu of the eigenvector decomposition, our method is rather deriving statistically independent components. The adopted algorithm, i.e., FastICA, uses the non-Gaussianity of the components as the criterion for their independence. Considering the eigenvector decomposition as being analogs to the principal component analysis (PCA), we propose the generalization of the ICTD methods to the level of the blind source separation (BSS) techniques (comprising both PCA and ICA). The proposed method preserves the invariance properties of the conventional ones, appearing to be robust both with respect to the rotation around the line of sight and to the change of the polarization basis. The efficiency of the method is demonstrated comparatively using POLSAR RAMSES X-band and ALOS L-band data sets. The main differences with respect to the conventional methods are mostly found in the behavior of the second most dominant component, which is not necessarily orthogonal to the first one. The potential of retrieving nonorthogonal mechanisms is moreover demonstrated using synthetic data. On the expense of a negligible entropy increase, the proposed method is capable of retrieving the edge diffraction of an elementary trihedral by recognizing dipole as the second component.

Hierarchical ship detection and recognition with high-resolution polarimetric synthetic aperture radar imagery

Ship surveillance by remote sensing technology has become a valuable tool for protecting marine environments. In recent years, the successful launch of advanced synthetic aperture radar (SAR) sensors that have high resolution and multipolarimetric modes has enabled researchers to use SAR imagery for not only ship detection but also ship category recognition. A hierarchical ship detection and recognition scheme is proposed. The complementary information obtained from multipolarimetric modes is used to improve both the detection pre- cision and the recognition accuracy. In the ship detection stage, a three-class fuzzy c-means clustering algorithm is used to calculate the segmenting threshold for prescreening ship candi- dates. To reduce the false alarm rate (FAR), we use a two-step discrimination strategy. In the first step, we fuse the detection results from multipolarimetric channels to reduce the speckle noise, ambiguities, sidelobes, and other sources of interference. In the second step, we use a binary classifier, which is trained with prior data collected on ships and nonships, to reduce the FAR even further. In the ship category recognition stage, we concatenate texture- based descriptors extracted from multiple polarmetric channels to construct a robust ship representation for category recognition. Furthermore, we construct and release a ship category database with real SAR data. We hope that it can be used to promote investigations of SAR ship recognition in the remote sensing and related academic communities. The proposed method is validated by a comprehensive experimental comparison to the state-of-the-art methods. The validation procedure showed that the proposed method outperforms all of the competing meth- ods by about 5% and 15% in terms of ship detection and recognition, respectively. © 2014 Society

STATISTICAL MID-LEVEL FEATURES FOR BUILDING-UP AREA EXTRACTION FROM FULL POLARIMETRIC SAR IMAGERY

This paper addresses the problem of designing statistical features for the extraction of building-up areas (BAs) from highresolution polarimetric synthetic aperture radar (PolSAR) imagery. The idea is to represent a building-up area by the distribution of its mid-level components, called intermediates, which are statistical patterns unsupervisedly learnt from PolSAR images. More precisely, by analyzing the structural properties and the polarimetric characteristics exhibited in various terrain types, we propose two kinds of midlevel features for small regions: the cluster based statistical feature (CSF) and the scattering mechanism based statistical feature (SMSF). In detail, for the CSF, the intermediates are the K-mean clusters with Wishart distance of the PolSAR images; for the SMSF, the intermediates are the scattering mechanism categories obtained by relying on a four-component decomposition with deorientation of the PolSAR images. In contrast with existing features for describing BAs, the proposed features, i.e., CSF and SMSF, capture more complex context information of BAs. We compare the proposed features with those based on the Gaussian Markov random field (GMRF) models, which have been proven to be suitable for BAs mapping. Experimental results on RADARSAT-2 datasets demonstrate the effectiveness of the proposed features.

Optimal Parameter Estimation in Heterogeneous Clutter for High-Resolution Polarimetric SAR Data

This letter presents a new estimation scheme for optimally deriving clutter parameters with high-resolution polarimetric synthetic aperture radar (POLSAR) data. The heterogeneous clutter in POLSAR data is described by the spherically invariant random vector model. Three parameters are introduced for the high-resolution POLSAR data clutter: the span, the normalized texture, and the speckle normalized covariance matrix. The asymptotic distribution of the novel span estimator is investigated. A novel heterogeneity test for the POLSAR clutter is also discussed. The proposed method is tested with airborne POLSAR images provided by the Office National d'Études et de Recherches Aerospatiales Radar Aéroporté Multi-spectral d'Etude des Signatures system.

A Simple Moment Method of Forest Biomass Estimation From Non-Gaussian Texture Information by High-Resolution Polarimetric SAR

A simple method is described to estimate forest biomass by high-resolution polarimetric synthetic aperture radar (SAR). The method is based on the regression analysis between the measured biomass from the ground survey and the second intensity moment of the non-Gaussian texture in the cross-polarized L-band SAR images. The SAR data used in the analysis were acquired by the airborne polarimetric interferometric SAR over the coniferous forest in Hokkaido, Japan. The regression analysis was first carried out, and a model function was derived to relate the intensity moment and the measured biomass in 19 forest stands. Using this model function, the biomass values were estimated and compared with those of 21 different stands with known biomass. The average accuracy of the moment model was found to be 85%, which is similar to that of the previous K -distribution model. The advantage of this method over the distribution-based model is that there is no need to search a specific distribution function which fits best to the image texture.

Building detection from high-resolution PolSAR data at the rectangle level by combining region and edge information

We propose a new approach at the rectangle feature level to extract buildings from high-resolution polarimetric synthetic aperture radar (PolSAR) data, using both region-based and edge-based information. The first step employs low-level detectors to provide raw region and edge information of the scene. In the second step, the rectangle features are initially extracted from the edge detection results, and further optimized to best fit the rough region-based building detection results. In the last step, a novel Markov random field (MRF) framework for rectangles is proposed, in which the data energy term of rectangles is defined from the region information while the smoothness term is defined according to the contextual prior knowledge about the buildings. Under this framework, the building rectangles are identified from the optimized rectangle candidates by minimizing the total energy. The effectiveness of the proposed method is verified using the real fully PolSAR data.

Accuracy of the $K$-Distribution Regression Model for Forest Biomass Estimation by High-Resolution Polarimetric SAR: Comparison of Model Estimation and Field Data

In our previous regression model for estimating forest biomass, it was shown that non-Gaussian amplitude fluctuations in high-resolution polarimetric synthetic aperture radar (SAR) data of coniferous forests can accurately be described by the -distribution and that the order parameter of the -distribution can be useful in estimating the tree biomass of coniferous forests from L-band cross-polarization amplitude images in a wider range than the conventional method using the radar cross section alone. The result was based on the analysis of the ldquoground-truthrdquo biomass data of 19 forest stands and airborne polarimetric interferometric SAR L-band data over the Tomakomai forests in Hokkaido, Japan. From this relation, an empirical regression model was developed to estimate forest biomass from SAR data. In this paper, we report the results on further analyses of this regression model. The validity of the -distribution is first reconfirmed using the Akaike information criterion, followed by the description on the accuracy of the model. To examine model accuracy, we carried out further field measurements on 22 forest stands in 2005, and the ground survey was made in 2006 to find out the causes of several anomalous data. Based on a comparison of the model-based biomass and the ground-truth data, the accuracy of the model was found to be approximately 86%. The regression model was then updated for practical application in estimating the biomass of the Hokkaido forests by including the ground-truth data of all 41 forest stands.