Search

Polarimetric Synthetic Aperture Radar (PolSAR) data is inherently characterized by speckle noise, which significantly deteriorates certain aspects of the quality of the PolSAR data processing, including the polarimetric decomposition and target interpretation. With the rapid increase in PolSAR resolution, SAR images in complex natural and artificial scenes exhibit non-homogeneous characteristics, which creates an urgent demand for high-resolution PolSAR filters. To address these issues, a new adaptive PolSAR filter based on joint similarity measure criterion (JSMC) is proposed in this paper. Firstly, a scale-adaptive filtering window is established in order to preserve the texture structure based on a multi-directional ratio edge detector. Secondly, the JSMC is proposed in order to accurately select homogeneous pixels; it describes pixel similarity based on both space distance and polarimetric distance. Thirdly, the homogeneous pixels are filtered based on statistical averaging. Finally, the airborne and spaceborne real data experiment results validate the effectiveness of our proposed method. Compared with other filters, the filter proposed in this paper provides a better outcome for PolSAR data in speckle suppression, edge texture, and the preservation of polarimetric properties. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) is widely used in remote sensing applications due to its ability to obtain full-polarization information. Compared to the quad-pol SAR, the dual-pol SAR mode has a wider observation swath and is more common in most SAR systems. The goal of reconstructing quad-pol SAR data from the dual-pol SAR mode is to learn the contextual information of dual-pol SAR images and the relationships among polarimetric channels. This work is dedicated to addressing this issue, and a multiscale feature aggregation network has been established to achieve the reconstruction task. Firstly, multiscale spatial and polarimetric features are extracted from the dual-pol SAR images using the pretrained VGG16 network. Then, a group-attention module (GAM) is designed to progressively fuse the multiscale features extracted by different layers. The fused feature maps are interpolated and aggregated with dual-pol SAR images to form a compact feature representation, which integrates the high- and low-level information of the network. Finally, a three-layer convolutional neural network (CNN) with a 1 × 1 convolutional kernel is employed to establish the mapping relationship between the feature representation and polarimetric covariance matrices. To evaluate the quad-pol SAR data reconstruction performance, both polarimetric target decomposition and terrain classification are adopted. Experimental studies are conducted on the ALOS/PALSAR and UAVSAR datasets. The qualitative and quantitative experimental results demonstrate the superiority of the proposed method. The reconstructed quad-pol SAR data can better sense buildings' double-bounce scattering changes before and after a disaster. Furthermore, the reconstructed quad-pol SAR data of the proposed method achieve a 97.08% classification accuracy, which is 1.25% higher than that of dual-pol SAR data. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) is an important sensor for earth observation. Multi-temporal PolSAR images obtained by successive observations of the region of interest contain rich polarimetric–temporal–spatial information of the land covers, which has wide applications. Speckle filtering becomes a necessary pre-processing for many subsequent applications. Currently, it is common to filter multi-temporal PolSAR data by directly using a speckle filter developed for single SAR or PolSAR data. The cross-correlation between different time series contains rich information in multi-temporal PolSAR images. How to utilize complete polarimetric–temporal–spatial information becomes a large challenge to achieve more satisfied performances of speckle reduction and details preservation simultaneously. This work dedicates to this issue and develops a novel speckle filtering approach for multi-temporal PolSAR data by multi-dimensional information fusion. The core idea is to establish an adaptive and efficient strategy of similar pixel selection based on the similarity test of multi-temporal polarimetric covariance matrices. This similar pixel selection scheme fuses the complete information of multi-temporal PolSAR data. The sensitivity of the proposed scheme is demonstrated with several typical and challenging texture patterns. Then, an adaptive speckle filter is established specifically for multi-temporal PolSAR data. Intensive comparison studies are carried out with airborne UAVSAR datasets and spaceborne ALOS/PALSAR datasets. Quantitative investigations in terms of the equivalent number of looks (ENL) and the figure of merit (FOM) indexes demonstrate and validate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

A representative general polarimetric model-based decomposition framework was proposed by Chen et al., which implements a simultaneous full-parameter inversion by using complete polarimetric information and solves several limitations in previous decomposition methods. However, there are still shortcomings in Chen's work. Firstly, only the real part of the parameter β in the generalized surface scattering model is considered. Secondly, inappropriate initial input values may lead to local optima in the nonlinear least squares optimization algorithm. Thirdly, the volume scattering component is underestimated in the volume scattering-dominated scene, but overestimated in buildings with large orientation (LOB) areas. Finally, nonlinear optimization is time-consuming computationally. To overcome those issues, an improved generalized polarimetric model-based decomposition method is proposed in this paper. The imaginary part of the parameter β is incorporated into the decomposition framework of the proposed method. Ingeniously utilizing the internal relationship in the generic equations composed of coherent matrix elements, the model parameters can be inversed by simplifying the nonlinear equations to linear equations. Therefore, compared with Chen's method, the proposed method does not rely on the initial input values, and improves the computational efficiency. In addition, a hierarchical decomposition scheme is presented to solve the problem of underestimation or overestimation of volume scattering component mentioned above. The performance and advantages of this method are evaluated with L-band and C-band polarimetric synthetic aperture radar (PolSAR) data sets. Comparison studies are carried out with other model-based decomposition methods, demonstrating that the proposed method can further improve decomposition performance, especially in LOB areas. [ABSTRACT FROM AUTHOR]

In 1978, the SEASAT satellite was launched, carrying the first civilian synthetic aperture radar (SAR). The mission was the monitoring of ocean: application to land was also studied. Despite its short operational time of 105 days, SEASAT-SAR provided a wealth of information on land and sea, and initiated many spaceborne SAR programs using not only the image intensity data, but also new technologies of interferometric SAR (InSAR) and polarimetric SAR (PolSAR). In recent years, artificial intelligence (AI), such as deep learning, has also attracted much attention. In the present article, a review is given on the imaging processes and analyses of oceanic data using SAR, InSAR, PolSAR data and AI. The selected oceanic phenomena described here include ocean waves, internal waves, oil slicks, currents, bathymetry, ship detection and classification, wind, aquaculture, and sea ice. [ABSTRACT FROM AUTHOR]

Polarimetric decomposition is an effective way to analyze the scattering mechanism of targets in polarimetric synthetic aperture radar (PolSAR) images. However, the analysis of urban areas is frequently a challenge. Most decomposition methods use a rotated dihedral derived via rotation matrix to model the double-bounce scattering mechanism of buildings. However, according to electromagnetic theory, the existing dihedral model is not accurate, especially when the orientation angle of the dihedral is large. Therefore, the double-bounce scattering contribution in urban areas with large orientation angles will be difficult to extract. To address this problem, based on physical optics (PO) and geometric optics (GO), the interaction process of electromagnetic waves and the rotational dihedral is analyzed, and then a modified rotational dihedral model (MRDM) is proposed for the accurate representation of the rotational double-bounce scattering mechanism. Accordingly, MRDM is introduced to a five-component decomposition method (MRDM-5SD) to analyze the scattering components in an urban area. The validity of MRDM-5SD is demonstrated using several data sets. The experimental results show that the power contributions of double-bounce scattering in urban areas with large orientation angles increase by using MRDM-5SD. Therefore, MRDM can provide support for feature extraction and target detection in urban areas. [ABSTRACT FROM AUTHOR]

The monitoring of ships is of paramount importance for ocean and coastal area surveillance. The synthetic aperture radar is shown to be a key sensor to provide effective and continuous observation of ships due to its unique imaging capabilities. When advanced synthetic aperture radar imaging systems are considered, the full scattering information is available that was demonstrated to be beneficial in developing improved ship detection and classification algorithms. Nonetheless, the capability of polarimetric synthetic aperture radar to observe marine vessels is significantly affected by several imaging and environmental parameters, including the incidence angle. Nonetheless, how changes in the incidence angle affect the scattering of ships still needs to be further investigated since only a sparse analysis, i.e., on different kinds of ships of different sizes observed at multiple incidence angles, has been performed. Hence, in this study, for the first time, the polarimetric scattering of the same ship, i.e., a small fishing trawler, which is imaged multiple times under the same sea state conditions but in a wide range of incidence angles, is analysed. This unique opportunity is provided by a premium L-band UAVSAR airborne dataset that consists of five full-polarimetric synthetic aperture radar scenes collected in the Gulf of Mexico. Experimental results highlight the key role played by the incidence angle on both coherent, i.e., co-polarisation signature and pedestal height, and incoherent, i.e., multi-polarisation and total backscattering power, polarimetric scattering descriptors. Experimental results show that: (1) the polarised scattering component is more sensitive to the incidence angle with respect to the unpolarised one; (2) the co-polarised channel under horizontal polarisation dominated the polarimetric backscattering from the fishing trawler at lower angles of incidence, while both co-polarised channels contribute to the polarimetric backscattering at higher incidence angles; (3) the HV polarisation provides the largest target-to-clutter ratio at lower incidence angles, while the HH polarisation should be preferred at higher angles of incidence. [ABSTRACT FROM AUTHOR]

This paper proposes an improved model-based forest height inversion method for airborne L-band dual-baseline repeat-pass polarimetric synthetic aperture radar interferometry (PolInSAR) collections. A two-layer physical model with various volumetric scattering attenuation and dynamic motion properties is first designed based on the traditional Random Motion over Ground (RMoG) model. Related PolInSAR coherence functions with both volumetric and temporal decorrelations incorporated are derived, where the impacts of homogenous and heterogeneous attenuation and dynamic motion properties on the performance of forest height inversion were investigated by the Linear Volume Attenuation (LVA), Quadratic Volume Attenuation (QVA), Linear Volume Motion (LVM), and Quadratic Volume Motion (QVM) depictions in the volume layer. Dual-baseline PolInSAR data were acquired to increase the degree of freedom (DOF) of the coherence observations and thereby provide extra constraints on the forest parameters to address the underdetermined problem. The experiments were carried out on a boreal forest in Canada and a tropical one in Gabon, where physical models with LVA + QVM (RMSE: 3.56 m) and QVA + LVM (RMSE: 6.83 m) exhibited better performances on the forest height inversion over the boreal and tropical forest sites, respectively. To leverage the advantages of LVA, QVA, LVM, and QVM, a pixel-wise optimization strategy was used to obtain the best forest height inversion performance for the range of attenuation and motion profiles considered. This pixel-wise optimization surpasses the best-performing single model and achieves forest height inversion results with an RMSE of 3.21 m in the boreal forest site and an RMSE of 6.48 m in the tropical forest site. [ABSTRACT FROM AUTHOR]

Wetlands are the "kidneys" of the earth and are crucial to the ecological environment. In this study, we utilized GF-3 quad-polarimetric synthetic aperture radar (QP) images to classify the ground objects (nearshore water, seawater, spartina alterniflora, tamarix, reed, tidal flat, and suaeda salsa) in the Yellow River Delta through convolutional neural networks (CNNs) based on polarimetric features. In this case, four schemes were proposed based on the extracted polarimetric features from the polarization coherency matrix and reflection symmetry decomposition (RSD). Through the well-known CNNs: AlexNet and VGG16 as backbone networks to classify GF-3 QP images. After testing and analysis, 21 total polarimetric features from RSD and the polarization coherency matrix for QP image classification contributed to the highest overall accuracy (OA) of 96.54% and 94.93% on AlexNet and VGG16, respectively. The performance of the polarization coherency matrix and polarimetric power features was similar but better than just using three main diagonals of the polarization coherency matrix. We also conducted noise test experiments. The results indicated that OAs and kappa coefficients decreased in varying degrees after we added 1 to 3 channels of Gaussian random noise, which proved that the polarimetric features are helpful for classification. Thus, higher OAs and kappa coefficients can be acquired when more informative polarimetric features are input CNNs. In addition, the performance of RSD was slightly better than obtained using the polarimetric coherence matrix. Therefore, RSD can help improve the accuracy of polarimetric SAR image classification of wetland objects using CNNs. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) systems are an important remote sensing tool. Such systems can provide high spacial resolution images, but they are contaminated by an interference pattern called multidimensional speckle. This fact requires that PolSAR images receive specialised treatment; particularly, tailored models which are close to PolSAR physical formation are sought. In this paper, we propose two new matrix models which arise from applying the stochastic summation approach to PolSAR, called compound truncated Poisson complex Wishart (CTPCW) and compound geometric complex Wishart (CGCW) distributions. These models offer the unique ability to express multimodal data. Some of their mathematical properties are derived and discussed—characteristic function and Mellin-kind log-cumulants (MLCs). Moreover, maximum likelihood (ML) estimation procedures via expectation maximisation algorithm for CTPCW and CGCW parameters are furnished as well as MLC-based goodness-of-fit graphical tools. Monte Carlo experiment results indicate ML estimates perform at what is asymptotically expected (small bias and mean square error) even for small sample sizes. Finally, our proposals are employed to describe actual PolSAR images, presenting evidence that they can outperform other well-known distributions, such as W m C , G m 0 , and K m . [ABSTRACT FROM AUTHOR]

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a key role in remote-sensing tasks, such as ship detection and land-cover classification. However, the existing methods cannot directly generate multi-scale superpixels in a hierarchical style and they will take a long time when multi-scale segmentation is executed separately. In this article, we propose an effective and accurate hierarchical superpixel segmentation method, by introducing a minimum spanning tree (MST) algorithm called the Boruvka algorithm. To accurately measure the difference between neighboring pixels, we obtain the scattering mechanism information derived from the model-based refined 5-component decomposition (RFCD) and construct a comprehensive dissimilarity measure. In addition, the edge strength map and homogeneity measurement are considered to make use of the structural and spatial distribution information in the PolSAR image. On this basis, we can generate superpixels using the distance metric along with the MST framework. The proposed method can maintain good segmentation accuracy at multiple scales, and it generates superpixels in real time. According to the experimental results on the ESAR and AIRSAR datasets, our method is faster than the current state-of-the-art algorithms and preserves somewhat more image details in different segmentation scales. [ABSTRACT FROM AUTHOR]

Superpixel segmentation is widely used in polarimetric synthetic aperture radar (PolSAR) image classification. However, the classification method using simple majority voting cannot easily handle evidence conflicts in a single superpixel. At present, there is no method to evaluate the quality of superpixel classification. To solve the above problems, this paper proposes a hybrid classification model based on superpixel entropy discrimination (SED), and constructs a two-level cascade classifier. Firstly, a light gradient boosting machine (LGBM) was used to process large-dimensional input features, and simple linear iterative clustering (SLIC) was integrated to obtain the primary classification results based on superpixels. Secondly, information entropy was introduced to evaluate the quality of superpixel classification, and a complex-valued convolutional neural network (CV-CNN) was used to reclassify the high-entropy superpixels to obtain the secondary classification results. Experiments with two measured PolSAR datasets show that the overall accuracy of both classification methods exceeded 97%. This method suppressed the evidence conflict in a single superpixel and the inaccuracy of superpixel segmentation. The test time of our proposed method was shorter than that of CV-CNN, and using only 55% of CV-CNN test data could achieve the same accuracy as using CV-CNN for the whole image. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification is a pixel-wise issue, which has become increasingly prevalent in recent years. As a variant of the Convolutional Neural Network (CNN), the Fully Convolutional Network (FCN), which is designed for pixel-to-pixel tasks, has obtained enormous success in semantic segmentation. Therefore, effectively using the FCN model combined with polarimetric characteristics for PolSAR image classification is quite promising. This paper proposes a novel FCN model by adopting complex-valued domain stacked-dilated convolution (CV-SDFCN). Firstly, a stacked-dilated convolution layer with different dilation rates is constructed to capture multi-scale features of PolSAR image; meanwhile, the sharing weight is employed to reduce the calculation burden. Unfortunately, the labeled training samples of PolSAR image are usually limited. Then, the encoder–decoder structure of the original FCN is reconstructed with a U-net model. Finally, in view of the significance of the phase information for PolSAR images, the proposed model is trained in the complex-valued domain rather than the real-valued domain. The experiment results show that the classification performance of the proposed method is better than several state-of-the-art PolSAR image classification methods. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) data can be acquired at all times and are not impacted by weather conditions. They can efficiently capture geometrical and geographical structures on the ground. However, due to the complexity of the data and the difficulty of data availability, PolSAR image scene classification remains a challenging task. To this end, in this paper, a low-rank constrained multimodal tensor representation method (LR-MTR) is proposed to integrate PolSAR data in multimodal representations. To preserve the multimodal polarimetric information simultaneously, the target decompositions in a scene from multiple spaces (e.g., Freeman, H/A/ α , Pauli, etc.) are exploited to provide multiple pseudo-color images. Furthermore, a representation tensor is constructed via the representation matrices and constrained by the low-rank norm to keep the cross-information from multiple spaces. A projection matrix is also calculated by minimizing the differences between the whole cascaded data set and the features in the corresponding space. It also reduces the redundancy of those multiple spaces and solves the out-of-sample problem in the large-scale data set. To support the experiments, two new PolSAR image data sets are built via ALOS-2 full polarization data, covering the areas of Shanghai, China, and Tokyo, Japan. Compared with state-of-the-art (SOTA) dimension reduction algorithms, the proposed method achieves the best quantitative performance and demonstrates superiority in fusing multimodal PolSAR features for image scene classification. [ABSTRACT FROM AUTHOR]

The detection of ships on the open sea is an important issue for both military and civilian fields. As an active microwave imaging sensor, synthetic aperture radar (SAR) is a useful device in marine supervision. To extract small and weak ships precisely in the marine areas, polarimetric synthetic aperture radar (PolSAR) data have been used more and more widely. We propose a new PolSAR ship detection method which is based on a keypoint detector, referred to as a PolSAR-SIFT keypoint detector, and a patch variation indicator in this paper. The PolSAR-SIFT keypoint detector proposed in this paper is inspired by the SAR-SIFT keypoint detector. We improve the gradient definition in the SAR-SIFT keypoint detector to adapt to the properties of PolSAR data by defining a new gradient based on the distance measurement of polarimetric covariance matrices. We present the application of PolSAR-SIFT keypoint detector to the detection of ship targets in PolSAR data by combining the PolSAR-SIFT keypoint detector with the patch variation indicator we proposed before. The keypoints extracted by the PolSAR-SIFT keypoint detector are usually located in regions with corner structures, which are likely to be ship regions. Then, the patch variation indicator is used to characterize the context information of the extracted keypoints, and the keypoints located on the sea area are filtered out by setting a constant false alarm rate threshold for the patch variation indicator. Finally, a patch centered on each filtered keypoint is selected. Then, the detection statistics in the patch are calculated. The detection statistics are binarized according to the local threshold set by the detection statistic value of the keypoint to complete the ship detection. Experiments on three data sets obtained from the RADARSAT-2 and AIRSAR quad-polarization data demonstrate that the proposed detector is effective for ship detection. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification has achieved great progress, but there still exist some obstacles. On the one hand, a large amount of PolSAR data is captured. Nevertheless, most of them are not labeled with land cover categories, which cannot be fully utilized. On the other hand, annotating PolSAR images relies more on domain knowledge and manpower, which makes pixel-level annotation harder. To alleviate the above problems, by integrating contrastive learning and transformer, we propose a novel patch-level PolSAR image classification, i.e., two-staged contrastive learning and sub-patch attention based network (TCSPANet). Firstly, the two-staged contrastive learning based network (TCNet) is designed for learning the representation information of PolSAR images without supervision, and obtaining the discrimination and comparability for actual land covers. Then, resorting to transformer, we construct the sub-patch attention encoder (SPAE) for modelling the context within patch samples. For training the TCSPANet, two patch-level datasets are built up based on unsupervised and semi-supervised methods. When predicting, the classification algorithm, classifying or splitting, is put forward to realise non-overlapping and coarse-to-fine patch-level classification. The classification results of multi-PolSAR images with one trained model suggests that our proposed model is superior to the compared methods. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a refined three-stage inversion algorithm (TSIA) for forest height estimation using polarimetric interferometric synthetic aperture radar (PolInSAR). Specifically, the iterative extraction of the boundary of the coherence region (IEBCR) and iterative look-up table (ILUT) are proposed to improve the efficiency of traditional TSIA. A class of refined TSIA utilizes the boundary of the coherence region (BCR) to alleviate the underestimation phenomenon in forest height estimation. Given many eigendecompositions in the extraction of BCR (EBCR), we analyze the relationship of eigenvectors between the adjacent points on the BCR and propose the IEBCR utilizing the power methods. In the final inversion stage of TSIA, the look-up table (LUT) uses the exhaustive search method to minimize the loss function in the 2-D grid with defined step sizes and thus costs high computational complexity. To alleviate the deficiency, we define the random volume over ground (RVoG) function based on the RVoG model and prove its monotonicity and convergence from the analytical and numerical points of view. After analyzing the relationship between the RVoG function and the loss function, we propose the ILUT for the inversion stage. The simulation and experiments based on the BioSAR 2008 campaign data illustrate that the IEBCR and ILUT greatly improve the computational efficiency almost without compromising on accuracy. [ABSTRACT FROM AUTHOR]

The radiometric terrain correction (RTC) is an essential processing step for supervised classification applications of polarimetric synthetic aperture radar (PolSAR) over mountainous areas. However, the current angular variation effect (AVE) correction methods of three-step RTC processing are difficult to apply to PolSAR supervised classification because of the problem of interdependence between AVE correction and classification. To address this issue, based on the three-step semi-empirical RTC approach, we propose an improved AVE correction method suitable for the supervised classification of PolSAR. We make full use of the prior knowledge required for supervised classification and RTC processing, that is, samples and elevation data, to calculate the parameters of AVE correction by constructing a weight coefficient matrix. GaoFen-3 QPSI (C-band, quad-polarization) data were used to verify the proposed method. Experimental results showed that the proposed method is available and effective for PolSAR supervised classification. The new method can effectively remove the AVE effect in the PolSAR image, and the overall accuracy of PolSAR supervised classification can be improved about 9% compared to that without AVE correction. For the fine classification of forest types, the AVE correction can improve the classification accuracy by about 20%. [ABSTRACT FROM AUTHOR]

The automatic detection and analysis of ocean eddies has become a popular research topic in physical oceanography during the last few decades. Compact polarimetric synthetic aperture radar (CP SAR), an emerging polarimetric SAR system, can simultaneously acquire richer polarization information of the target and achieve large bandwidth observations. It has inherent advantages in ocean observation and is bound to become an ideal data source for ocean eddy observation and research. In this study, we simulated the CP data with L-band ALOS PALSAR fully polarimetric data. We assessed the detection and classification potential of ocean eddies from CP SAR by analyzing 50 CP features for 2 types of ocean eddies ("black"and "white") based on the Euclidean distance and further carried out eddy detection and eddy information extraction experiments. The results showed that among the 50 CP features, the dihedral component power (Pd), shannon entropy (SEI), double bounce (Dbl), Stokes parameters (g0 and g3), eigenvalue (l1), lambda, RVoG parameter (ms), shannon entropy (SE), surface scattering component (Ps), and σ H H all performed better for detecting "white" eddies. Moreover, the H-A combination parameter (1mHA), entropy, shannon entropy (SEP, SEI, and SE), probability (p2), polarization degree (m), anisotropy, probability (p1), double bounce (Dbl), H-A combination parameter (H1mA), circular polarization ratio (CPR), and σ V V were better CP features for detecting "black" eddies. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) has attracted lots of attention from remote sensing scientists because of its various advantages, e.g., all-weather, all-time, penetrating capability, and multi-polarimetry. The three-component scattering model proposed by Freeman and Durden (FDD) has bridged the data and observed target with physical scattering model, whose simplicity and practicality have advanced remote sensing applications. However, the three-component scattering model also has some disadvantages, such as negative powers and a scattering model unfitted to observed target, which can be improved by adaptive methods. In this paper, we propose a novel adaptive decomposition approach in which we established a dipole aggregation model to fit every pixel in PolSAR image to an independent volume scattering mechanism, resulting in a reduction of negative powers and an improved adaptive capability of decomposition models. Compared with existing adaptive methods, the proposed approach is fast because it does not utilize any time-consuming algorithm of iterative optimization, is simple because it does not complicate the original three-component scattering model, and is clear for each model being fitted to explicit physical meaning, i.e., the determined adaptive parameter responds to the scattering mechanism of observed target. The simulation results indicated that this novel approach reduced the possibility of the occurrence of negative powers. The experiments on ALOS-2 and RADARSAT-2 PolSAR images showed that the increasing of adaptive parameter reflected more effective scatterers aggregating at the 45° direction corresponding to high cross-polarized property, which always appeared in the 45° oriented buildings. Moreover, the random volume scattering model used in the FDD could be expressed by the novel dipole aggregation model with an adaptive parameter equal to one that always appeared in the forest area. [ABSTRACT FROM AUTHOR]

Icebergs represent hazards to ships and maritime activities and therefore their detection is essential. Synthetic Aperture Radar (SAR) satellites are very useful for this, due to their capability to acquire data under cloud cover and during day and night passes. In this work, we compared six state-of-the-art polarimetric target detectors to test their performance and ability to detect small-sized icebergs <120 m in four locations in Greenland. We used four single-look complex (SLC) ALOS-2 quad-polarimetric images from JAXA for quad-polarimetric detection and we compared with dual-polarimetric detectors using only the channels HH and HV. We also compared these detectors with single-polarimetric intensity channels and we tested using two scenarios: open ocean and sea ice. Our results show that the multi-look polarimetric whitening filter (MPWF) and the optimal polarimetric detector (OPD) provide the most optimal performance in quad- and dual-polarimetric mode detection. The analysis shows that, overall, quad-polarimetric detectors provide the best detection performance. When the false alarm rate (PF) is fixed to 10−5, the probabilities of detection (PD) are 0.99 in open ocean and 0.90 in sea ice. Dual-polarimetric or single-polarimetric detectors show an overall reduction in performance (the ROC curves show a decrease), but this degradation is not very large (<0.1) when the value of false alarms is relatively high (i.e., we are interested in bigger icebergs with a brighter backscattering >120 m, as they are easier to detect). However, the differences between quad- and dual- or single-polarimetric detectors became much more evident when the PF value was fixed to low detection probabilities 10−6 (i.e., smaller icebergs). In the single-polarimetric mode, the HV channel showed PD values of 0.62 for open ocean and 0.26 for sea ice, compared to values of 0.81 (open ocean) and 0.77 (sea ice) obtained with quad-polarimetric detectors. [ABSTRACT FROM AUTHOR]

Marine oil spill detection is vital for strengthening the emergency commands of oil spill accidents and repairing the marine environment after a disaster. Polarimetric Synthetic Aperture Radar (Pol-SAR) can obtain abundant information of the targets by measuring their complex scattering matrices, which is conducive to analyze and interpret the scattering mechanism of oil slicks, look-alikes, and seawater and realize the extraction and detection of oil slicks. The polarimetric features of quad-pol SAR have now been extended to oil spill detection. Inspired by this advancement, we proposed a set of improved polarimetric feature combination based on polarimetric scattering entropy H and the improved anisotropy A12–H_A12. The objective of this study was to improve the distinguishability between oil slicks, look-alikes, and background seawater. First, the oil spill detection capability of the H_A12 combination was observed to be superior than that obtained using the traditional H_A combination; therefore, it can be adopted as an alternate oil spill detection strategy to the latter. Second, H(1 − A12) combination can enhance the scattering randomness of the oil spill target, which outperformed the remaining types of polarimetric feature parameters in different oil spill scenarios, including in respect to the relative thickness information of oil slicks, oil slicks and look-alikes, and different types of oil slicks. The evaluations and comparisons showed that the proposed polarimetric features can indicate the oil slick information and effectively suppress the sea clutter and look-alike information. [ABSTRACT FROM AUTHOR]

The presence of speckles and the absence of discriminative features make it difficult for the pixel-level polarimetric synthetic aperture radar (PolSAR) image classification to achieve more accurate and coherent interpretation results, especially in the case of limited available training samples. To this end, this paper presents a composite kernel-based elastic net classifier (CK-ENC) for better PolSAR image classification. First, based on superpixel segmentation of different scales, three types of features are extracted to consider more discriminative information, thereby effectively suppressing the interference of speckles and achieving better target contour preservation. Then, a composite kernel (CK) is constructed to map these features and effectively implement feature fusion under the kernel framework. The CK exploits the correlation and diversity between different features to improve the representation and discrimination capabilities of features. Finally, an ENC integrated with CK (CK-ENC) is proposed to achieve better PolSAR image classification performance with limited training samples. Experimental results on airborne and spaceborne PolSAR datasets demonstrate that the proposed CK-ENC can achieve better visual coherence and yield higher classification accuracies than other state-of-art methods, especially in the case of limited training samples. [ABSTRACT FROM AUTHOR]

Forest canopy height is a basic metric characterizing forest growth and carbon sink capacity. Based on full-polarized Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR) data, this study used Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) technology to estimate forest canopy height. In total the four methods of differential DEM (digital elevation model) algorithm, coherent amplitude algorithm, coherent phase-amplitude algorithm and three-stage random volume over ground algorithm (RVoG_3) were proposed to obtain canopy height and their accuracy was compared in consideration of the impacts of coherence coefficient and range slope levels. The influence of the statistical window size on the coherence coefficient was analyzed to improve the estimation accuracy. On the basis of traditional algorithms, time decoherence was performed on ALOS/PALSAR data by introducing the change rate of Landsat NDVI (Normalized Difference Vegetation Index). The slope in range direction was calculated based on SRTM (Shuttle Radar Topography Mission) DEM data and then introduced into the s-RVoG (sloped-Random Volume over Ground) model to optimize the canopy height estimation model and improve the accuracy. The results indicated that the differential DEM algorithm underestimated the canopy height significantly, while the coherent amplitude algorithm overestimated the canopy height. After removing the systematic coherence, the overestimation of the RVoG_3 model was restrained, and the absolute error decreased from 23.68 m to 4.86 m. With further time decoherence, the determination coefficient increased to 0.2439. With the introduction of range slope, the s-RVoG model shows improvement compared to the RVoG model. Our results will provide a reference for the appropriate algorithm selection and optimization for forest canopy height estimation using full-polarized L-band synthetic aperture radar (SAR) data for forest ecosystem monitoring and management. [ABSTRACT FROM AUTHOR]

Deep learning can archive state-of-the-art performance in polarimetric synthetic aperture radar (PolSAR) image classification with plenty of labeled data. However, obtaining large number of accurately labeled samples of PolSAR data is very hard, which limits the practical use of deep learning. Therefore, unsupervised PolSAR image classification is worthy of further investigation that is based on deep learning. Inspired by the superior performance of deep mutual information in natural image feature learning and clustering, an end-to-end Convolutional Long Short Term Memory (ConvLSTM) network is used in order to learn the deep mutual information of polarimetric coherent matrices in the rotation domain with different polarimetric orientation angles (POAs) for unsupervised PolSAR image classification. First, for each pixel, paired "POA-spatio" samples are generated from the polarimetric coherent matrices with different POAs. Second, a special designed ConvLSTM network, along with deep mutual information losses, is used in order to learn the discriminative deep mutual information feature representation of the paired data. Finally, the classification results can be output directly from the trained network model. The proposed method is trained in an end-to-end manner and does not have cumbersome pipelines. Experiments on four real PolSAR datasets show that the performance of proposed method surpasses some state-of-the-art deep learning unsupervised classification methods. [ABSTRACT FROM AUTHOR]

The information extraction of polarimetric synthetic aperture radar (PolSAR) images typically requires a great number of training samples; however, the training samples from historical images are less reusable due to the distribution differences. Consequently, there is a significant manual cost to collecting training samples when processing new images. In this paper, to address this problem, we propose a novel active transfer learning method, which combines active learning and the deep forest model to perform transfer learning. The main idea of the proposed method is to gradually improve the performance of the model in target domain tasks with the increase of the levels of the cascade structure. More specifically, in the growing stage, a new active learning strategy is used to iteratively add the most informative target domain samples to the training set, and the augmented features generated by the representation learning capability of the deep forest model are used to improve the cross-domain representational capabilities of the feature space. In the filtering stage, an effective stopping criterion is used to adaptively control the complexity of the model, and two filtering strategies are used to accelerate the convergence of the model. We conducted experiments using three sets of PolSAR images, and the results were compared with those of four existing transfer learning algorithms. Overall, the experimental results fully demonstrated the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) is an established remote sensing technique that can robustly provide high-resolution imagery of the Earth's surface. However, current space-borne SAR systems are limited, as a matter of principle, in achieving high azimuth resolution and a large swath width at the same time. Digital beamforming (DBF) has been identified as a key technology for resolving this limitation and provides various other advantages, such as an improved signal-to-noise ratio (SNR) or the adaptive suppression of radio interference (RFI). Airborne SAR sensors with digital beamforming capabilities are essential tools to research and validate this important technology for later implementation on a satellite. Currently, the Microwaves and Radar Institute of the German Aerospace Center (DLR) is developing a new advanced high-resolution airborne SAR system with digital beamforming capabilities, the so-called DBFSAR, which is planned to supplement its operational F-SAR system in near future. It is operating at X-band and features 12 simultaneous receive and 4 sequential transmit channels with 1.8 GHz bandwidth each, flexible DBF antenna setups and is equipped with a high-precision navigation and positioning unit. This paper aims to present the DBFSAR sensor development, including its radar front-end, its digital back-end, the foreseen DBF antenna configuration and the intended calibration strategy. To analyse the status, performance, and calibration quality of the DBFSAR system, this paper also includes some first in-flight results in interferometric and multi-channel marine configurations. They demonstrate the excellent performance of the DBFSAR system during its first flight campaigns. [ABSTRACT FROM AUTHOR]

Recently, classification methods based on deep learning have attained sound results for the classification of Polarimetric synthetic aperture radar (PolSAR) data. However, they generally require a great deal of labeled data to train their models, which limits their potential real-world applications. This paper proposes a novel semi-supervised deep metric learning network (SSDMLN) for feature learning and classification of PolSAR data. Inspired by distance metric learning, we construct a network, which transforms the linear mapping of metric learning into the non-linear projection in the layer-by-layer learning. With the prior knowledge of the sample categories, the network also learns a distance metric under which all pairs of similarly labeled samples are closer and dissimilar samples have larger relative distances. Moreover, we introduce a new manifold regularization to reduce the distance between neighboring samples since they are more likely to be homogeneous. The categorizing is achieved by using a simple classifier. Several experiments on both synthetic and real-world PolSAR data from different sensors are conducted and they demonstrate the effectiveness of SSDMLN with limited labeled samples, and SSDMLN is superior to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The Gaussian vertical backscatter (GVB) model has a pivotal role in describing the forest vertical structure more accurately, which is reflected by P-band polarimetric interferometric synthetic aperture radar (Pol-InSAR) with strong penetrability. The model uses a three-dimensional parameter space (forest height, Gaussian mean representing the strongest backscattered power elevation, and the corresponding standard deviation) to interpret the forest vertical structure. This paper establishes a two-dimensional GVB model by simplifying the three-dimensional one. Specifically, the two-dimensional GVB model includes the following three cases: the Gaussian mean is located at the bottom of the canopy, the Gaussian mean is located at the top of the canopy, as well as a constant volume profile. In the first two cases, only the forest height and the Gaussian standard deviation are variable. The above approximation operation generates a two-dimensional volume only coherence solution space on the complex plane. Based on the established two-dimensional GVB model, the three-baseline inversion is achieved without the null ground-to-volume ratio assumption. The proposed method improves the performance by 18.62% compared to the three-baseline Random Volume over Ground (RVoG) model inversion. In particular, in the area where the radar incidence angle is less than 0.6 rad, the proposed method improves the inversion accuracy by 34.71%. It suggests that the two-dimensional GVB model reduces the GVB model complexity while maintaining a strong description ability. [ABSTRACT FROM AUTHOR]

Hybrid quadrature polarimetric (hybrid quad-pol) synthetic aperture radar (SAR) is proposed as a potential candidate for the full-polarimetric SAR mode. It allows balanced range ambiguity performance and simplified system structure. System based on hybrid-pol SAR mode can also implement the conventional quad-pol mode and the compact-pol mode via few adjustments. However, the azimuth ambiguity performance in cross-pol channels is proved deteriorated in hybrid quad-pol mode due to the lopsided energy distribution of ambiguities. As are generally called "ghost" targets, azimuth ambiguities usually influence the recognition of the targets in SAR imaging. This letter describes how to remove the false targets that arise from azimuth ambiguities by means of waveform diversity and dual-focus post-processing (DFPP) technique. The proposed method exploits the feature of azimuth ambiguity and yields improved image quality in cross-pol channels with strong co-pol azimuth ambiguities removed in hybrid quad-pol SAR at a low system cost. Furthermore, it offers remarkable benefits for target detecting and recognition with strong false targets removed. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Rradar (SAR) provides rich ground information for remote sensing survey and can be used all time and in all weather conditions. Polarimetric SAR (PolSAR) can further reveal surface scattering difference and improve radar's application ability. Most existing classification methods for PolSAR imagery are based on manual features, such methods with fixed pattern has poor data adaptability and low feature utilization, if directly input to the classifier. Therefore, combining PolSAR data characteristics and deep network with auto-feature learning ability forms a new breakthrough direction. In fact, feature learning of deep network is to realize function approximation from data to label, through multi-layer accumulation, but finite layers limit the network's mapping ability. According to manifold hypothesis, high-dimensional data exists in potential low-dimensional manifold and different types of data locates in different manifolds. Manifold learning can model core variables of the target, and separate different data's manifold as much as possible, so as to complete data classification better. Therefore, taking manifold hypothesis as a starting point, nonlinear manifold learning integrated with fully convolutional networks for PolSAR image classification method is proposed in this paper. Firstly, high-dimensional polarized features are extracted based on scattering matrix and coherence matrix of original PolSAR data, whose compact representation is mined by manifold learning. Meanwhile, drawing on transfer learning, pre-trained Fully Convolutional Networks (FCN) model is utilized to learn deep spatial features of PolSAR imagery. Considering complementary advantages, weighted strategy is adopted to embed manifold representation into deep spatial features, which are input into support vector machine (SVM) classifier for final classification. A series of experiments on three PolSAR datasets have verified effectiveness and superiority of the proposed classification algorithm. [ABSTRACT FROM AUTHOR]

Time series analysis (TSA) based on multi-temporal polarimetric synthetic aperture radar (PolSAR) images can deeply mine the scattering characteristics of objects in different stages and improve the interpretation effect, or help to extract the range of surface changes. However, as far as classification is concerned, it is difficult to directly generate the classification map for a new temporal image, by the use of conventional TSA or change detection methods. Once some labeled samples exist in historical temporal images, semi-supervised domain adaptation (DA) is able to use historical label information to infer the categories of pixels in the new image, which is a potential solution to the above problem. In this paper, a novel semi-supervised DA algorithm is proposed, which inherits the merits of maximum margin criterion and principal component analysis in the DA learning scenario. Using a kernel mapping function established on the statistical distribution of PolSAR data, the proposed algorithm aims to find an optimal subspace for eliminating domain influence and keeping the key information of bi-temporal images. Experiments on both UAVSAR and Radarsat-2 multi-temporal datasets show that, superior classification results with the average accuracy of about 80% can be obtained by a simple classifier trained with historical labeled samples in the learned low- dimensional subspaces. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data expresses the structure information of objects. This special data representation makes 3D convolution which explicitly modeling the relationship between polarimetric channels perform better in the task of PolSAR image classification. However, the development of deep 3D-CNNs will cause a huge number of model parameters and expensive computational costs, which not only leads to the decrease of the interpretation speed during testing, but also greatly increases the risk of over-fitting. To alleviate this problem, a lightweight 3D-CNN framework that compresses 3D-CNNs from two aspects is proposed in this paper. Lightweight convolution operations, i.e., pseudo-3D and 3D-depthwise separable convolutions, are considered as low-latency replacements for vanilla 3D convolution. Further, fully connected layers are replaced by global average pooling to reduce the number of model parameters so as to save the memory. Under the specific classification task, the proposed methods can reduce up to 69.83% of the model parameters in convolution layers of the 3D-CNN as well as almost all the model parameters in fully connected layers, which ensures the fast PolSAR interpretation. Experiments on three PolSAR benchmark datasets, i.e., AIRSAR Flevoland, ESAR Oberpfaffenhofen, EMISAR Foulum, show that the proposed lightweight architectures can not only maintain but also slightly improve the accuracy under various criteria. [ABSTRACT FROM AUTHOR]

The detection of small fishing ships is very important for maritime fishery supervision. However, it is difficult to detect small ships using synthetic aperture radar (SAR), due to the weak target scattering and very small number of pixels. Polarimetric synthetic aperture radar (PolSAR) has been widely used in maritime ship detection due to its abundant target scattering information. In the present paper, a new ship detector, named ΛM, is developed based on the analysis of polarization scattering differences between ship and sea, then combined with the two-parameter constant false alarm rate method (TP-CFAR) algorithm to conduct ship detection. The goals of the detector construction are to fully consider the ship's depolarization effect, and further amplify it through sliding window processing. First, the signal-to-clutter ratio (SCR) enhancement performance of ΛM for ships with different lengths ranging from 8 to 230 m under 90 different combinations of windows are analyzed in detail using three set of RADARSAT-2 quad-polarization data, then the appropriate window size is determined. In addition, the SCR enlargement between ΛM and some typical polarization features is compared. Among these, for ships of length greater than 35 m, the average contrast of ΛM is 33.7 dB, which is 20 dB greater than that of the HV channel. For small vessels of length less than 16 m, the average contrast of ΛM is 16 dB higher than that of HV channel on average. Finally, the RADARSAT-2 data including nonmetallic small vessels are used to perform ship detection tests, and the detection ability for conventional and small ships of some classic algorithms are compared and analyzed. For large vessels of length greater than 35 m, the method proposed in this paper is able to obtain a superior detection result, maintain the ship contour well, and suppress false alarms caused by the cross side lobe in the SAR image. For small vessels of length less than 16 m, the method proposed in this paper can reduce the number of missed targets, while also obtaining superior detection results, especially for small nonmetallic vessels. [ABSTRACT FROM AUTHOR]

Radio frequency interference (RFI) is a well-known problem in microwave radiometry (MWR). Any undesired signal overlapping the MWR protected frequency bands introduces a bias in the measurements, which can corrupt the retrieved geophysical parameters. This paper presents a literature review of RFI detection and mitigation techniques for microwave radiometry from space. The reviewed techniques are divided between real aperture and aperture synthesis. A discussion and assessment of the application of RFI mitigation techniques is presented for each type of radiometer. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification is a recent technology with great practical value in the field of remote sensing. However, due to the time-consuming and labor-intensive data collection, there are few labeled datasets available. Furthermore, most available state-of-the-art classification methods heavily suffer from the speckle noise. To solve these problems, in this paper, a novel semi-supervised algorithm based on self-training and superpixels is proposed. First, the Pauli-RGB image is over-segmented into superpixels to obtain a large number of homogeneous areas. Then, features that can mitigate the effects of the speckle noise are obtained using spatial weighting in the same superpixel. Next, the training set is expanded iteratively utilizing a semi-supervised unlabeled sample selection strategy that elaborately makes use of spatial relations provided by superpixels. In addition, a stacked sparse auto-encoder is self-trained using the expanded training set to obtain classification results. Experiments on two typical PolSAR datasets verified its capability of suppressing the speckle noise and showed excellent classification performance with limited labeled data. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in various PolSAR image application. And many pixel-wise, region-based classification methods have been proposed for PolSAR images. However, most of the pixel-wise methods can not model local spatial relationship of pixels due to negative effects of speckle noise, and most of the region-based methods fail to figure out the regions with the similar polarimetric features. Considering that color features can provide good visual expression and perform well for image interpretation, in this work, based on the PolSAR pseudo-color image over Pauli decomposition, we propose a supervised PolSAR image classification approach combining learned superpixels and quaternion convolutional neural network (QCNN). First, the PolSAR RGB pseudo-color image is formed under Pauli decomposition. Second, we train QCNN with quaternion PolSAR data converted by RGB channels to extract deep color features and obtain pixel-wise classification map. QCNN treats color channels as a quaternion matrix excavating the relationship among the color channels effectively and avoiding information loss. Third, pixel affinity network (PAN) is utilized to generate the learned superpixels of PolSAR pseudo-color image. The learned superpixels allow the local information exploitation available in the presence of speckle noise. Finally, we fuse the pixel-wise classification result and superpixels to acquire the ultimate pixel-wise PolSAR image classification map. Experiments on three real PolSAR data sets show that the proposed approach can obtain 96.56%, 95.59%, and 92.55% accuracy for Flevoland, San Francisco and Oberpfaffenhofen data set, respectively. And compared with state-of-the-art PolSAR image classification methods, the proposed algorithm can obtained competitive classification results. [ABSTRACT FROM AUTHOR]

This study proposes a workflow for land use and land cover (LULC) classification of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) images of the Brazilian tropical savanna (Cerrado) biome. The following LULC classes were considered: forestlands; shrublands; grasslands; reforestations; croplands; pasturelands; bare soils/straws; urban areas; and water reservoirs. The proposed approach combines polarimetric attributes, image segmentation, and machine-learning procedures. A set of 125 attributes was generated using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl, Freeman–Durden, Yamaguchi, and Cloude–Pottier target decomposition components, incoherent polarimetric parameters (biomass indices and polarization ratios), and HH-, HV-, VH-, and VV-polarized amplitude images. These attributes were classified using the Naive Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms. The RF, MLP, and SVM classifiers presented the most accurate performances. NB and DT J48 classifiers showed a lower performance in relation to the RF, MLP, and SVM. The DT J48 classifier was the most suitable algorithm for discriminating urban areas and natural vegetation cover. The proposed workflow can be replicated for other SAR images with different acquisition modes or for other types of vegetation domains. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the potential of polarimetric Synthetic Aperture Radar (SAR) tomography (Pol-TomoSAR) in urban applications. TomoSAR exploits the amplitude and phase of the received data and offers the possibility to resolve multiple scatters lying in the same range–azimuth resolution cell. In urban environments, this issue is very important since layover causes multiple coherent scatterers to be mapped in the same range–azimuth image pixel. To achieve reliable and accurate results, TomoSAR requires a large number of multi-baseline acquisitions which, for satellite-borne SAR systems, are collected with long time intervals. Then, accurate tomographic reconstructions would require multiple scatterers to remain stable between all the acquisitions. In this paper, an extension of a generalized likelihood ratio test (GLRT)-based tomographic approach, denoted as Fast-Sup-GLRT, to the polarimetric data case is introduced, with the purpose of investigating if, in urban applications, the use of polarimetric channels allows for reduction of the number of baselines required to achieve a given scatterer's detection performance. The results presented show that the use of dual polarization data allows the proposed detector to work in an equivalent or better way than use of a double number of independent single polarization channels. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification has become more and more popular in recent years. As we all know, PolSAR image classification is actually a dense prediction problem. Fortunately, the recently proposed fully convolutional network (FCN) model can be used to solve the dense prediction problem, which means that FCN has great potential in PolSAR image classification. However, there are some problems to be solved in PolSAR image classification by FCN. Therefore, we propose sliding window fully convolutional network and sparse coding (SFCN-SC) for PolSAR image classification. The merit of our method is twofold: (1) Compared with convolutional neural network (CNN), SFCN-SC can avoid repeated calculation and memory occupation; (2) Sparse coding is used to reduce the computation burden and memory occupation, and meanwhile the image integrity can be maintained in the maximum extent. We use three PolSAR images to test the performance of SFCN-SC. Compared with several state-of-the-art methods, SFCN-SC achieves promising results in PolSAR image classification. [ABSTRACT FROM AUTHOR]