InSAR-based scene matching navigation is a cutting-edge autonomous navigation scheme for GNSS-denied environments. However, due to the inherent speckle noise of SAR systems and texture differences between real-time and reference interferograms, the extracted matching feature points inevitably contain observation noise and outliers. Meanwhile, current mainstream platform localization inversion primarily relies on simplified airborne SAR imaging geometric models. Lacking error suppression mechanisms, these models cause the matching observation errors to directly propagate and amplify into platform positioning errors. To address these issues, this paper proposes a robust localization estimation model named Inv-RD. By incorporating time-dependent payload orbital equations, the inherently underdetermined Range-Doppler (RD) inversion problem is reframed into an overdetermined nonlinear optimization problem based on redundant observations. Subsequently, the Levenberg-Marquardt (L-M) algorithm is employed for global optimization, which significantly mitigates the impact of matching noise on localization accuracy. Experiments using measured flight data demonstrate that, even in the presence of matching errors, the proposed Inv-RD model significantly outperforms traditional geometric models in terms of positioning precision.

Classification of hypersaline water bodies, e.g., salt fields and salt lakes, presents unique challenges due to the similar spectral and scattering characteristics of various saline water bodies. To address this issue, we propose an innovative classification method tailored for such environments, integrating Sentinel-1 multitemporal polarimetric synthetic aperture radar (PolSAR) data with Landsat multispectral imagery. The method introduces a novel PolSAR-based feature, termed scattering mechanism entropy, to quantify variations in salt crystal precipitation processes. Additionally, the blue band from multispectral imagery is leveraged to represent ion concentrations in hypersaline water bodies. By deriving the statistical relationship between scattering mechanism entropy and blue band data for each pixel, we amplify the separability of salt features and mitigate the influence of spectral similarity. These derived features are then concatenated into a Chernoff distance-based classifier for improved classification performance. To validate the robustness and effectiveness of this method, we apply it to the classification of salt fields and salt lakes on four major salt lake sites in China: Qarhan salt lake (2018–2020), Yiliping salt lake (2021–2023), Taijnar salt lake (2019–2023), and Gasikule salt lake (2019–2023). The proposed approach achieves classification accuracies of 90.91%, 92.73%, 97.40%, and 97.65%, respectively, significantly outperforming existing water body classification methods.

Polarimetric synthetic aperture radar (PolSAR) can obtain rich information of ground objects through different polarization combinations, and is widely used in terrain classification. The time-varying feature of multi-temporal polarimetric SAR data is a useful supplement, which contains information that is not available in single polarimetric data. This paper aims to introduce time-varying analysis into Sentinel-1 data, so as to effectively combine the information of both time and polarization dimensions. In this way, the accuracy of crop classification using dual-polarimetric data is improved. This paper used Sentinel-1 data, firstly we constructed the dual-polarimetric coherence (DC) based on C2matrices, and analyzed the DC to find optimal time by using feature importance ranking in Random Forest model. Then, the polarimetric features and DC of the selected time are combined. Finally, the spatial correlation of MRF was utilized to classify. Compared to using only polarimetric features alone, the overall accuracy is improved.

Qarhan Salt Lake is located in the Qaidam Basin in northwest China, containing abundant salt mineral resources such as sodium, potassium, and magnesium. It is the largest salt lake and one of the most important salt lake industry bases in China. The changes and development of the salt crust are of great significance for understanding the ecological environmental change of the Qarhan Salt Lake and promoting sustainable production of salt lakes. However, the polarimetric scattering features are extremely similar between different types of salt crusts basically composed of dominant surface scattering with some volume and surface scattering, so the redundancy problem between features is particularly serious. The purpose of this paper is to select 7 polarimetric features with a classification accuracy of more than 95% from statistical and textural similarity, respectively, using the similarity metrics SSFSM for different salt shell polarized features, achieving a classification accuracy similar to that of all features.

Compact Polarimetric (CP) SAR has a unique advantage in marine target observation, which can obtain rich polarization information and maintain a large observation width. However, due to the Doppler effect, moving ship targets are prone to ghost during the imaging process. Since CP data lose some scattering information, it is more difficult to distinguish the target from interference. This paper proposes a multi-feature collaboration and enhancement method for removing ghosts from the CP SAR ship target. The ship and ghost interference features are enhanced by multi-feature collaborations, then the contrast between ship and ghost interference is enhanced using an extremum separation feature descriptor, and finally, the ghost interference is removed using a signal-to-clutter ratio based Interference Feature Filter (IFF). Given limited CP data for ships with ghost phenomenon, the experiments simulate Circular Transmit and Linear Receive (CTLR) mode data using GF-3 fully polarimetric data, and the results show that this method can remove the ghost around the ship in the CP image better.

Compact Polarimetric (CP) SAR has a larger imaging bandwidth compared to full-polarimetric SAR and more polarization information than dual-polarimetric SAR, which has significant potential in maritime ship detection. The non-uniform scale of ship targets and complex backgrounds present detection challenges. This paper proposes an improvement to YOLOv8 by employing deformable convolutions in the backbone network and adding attention mechanisms in the network neck. Deformable convolutions excel at extracting multi-scale features of ships with strong expressive capability, while attention mechanisms suppress the learning of background features. The paper utilizes a CP SAR dataset constructed by using high-information-content SPAN images and augments the dataset. In comparison with the experimental results of the standard YOLOv8 model, our method demonstrates an improvement of 3.2% in recall, 3.6% in precision, and 1.5% in mAP. The results indicate the effectiveness of our approach in the task of ship detection using CP SAR.

Multi-temporal PolSAR data captures the temporal variations in polarization parameters, enabling more accurate land cover classification. Most existing multi-temporal PolSAR features rely on comparing only two-time points. These approaches can be limited in capturing cumulative changes over a longer period. To better represent the cumulative changes of land cover in the entire time-series, this paper proposes a multi-temporal PolSAR feature, namely time correlation entropy. We first extract the dominant scattering mechanism of targets from the polarization covariance matrices using matrix decomposition. Then the time correlation matrix is constructed by comparing all dominant scattering mechanism pairs in the time series. From the Shannon entropy, the entropy of the time correlation matrix, i.e., time correlation entropy, is derived to indicate the degree of changes in the land cover during the observation period. Finally, the maximum entropy principle is further applied to prove that this entropy conforms to a normal distribution. Following this corollary, a classification method based on the interval estimation of distribution parameters is proposed. We evaluate the proposed feature and classification on the salt lake classification application in Qarhan Salt Lake and Gasikule Salt Lake using Sentinel-1 images. Compared to common PolSAR features and classification methods, our method gains the best results. Besides, its results also have better regional consistency and noise resistance.

Traditional absolute radiometric calibration methods for synthetic aperture radar (SAR) face challenges in terms of flexibility, maintenance, and calibration frequency. In contrast, radiometric cross calibration can achieve rapid and timely calibration by utilizing the calibrated SAR satellites to illuminate the same ground targets. However, there are still two factors limiting the accuracy of cross calibration. First, two satellites used for cross calibration often have different incidence angles, whereas the existing methods for correcting incidence angle differences have poor performance in scene adaptation and overcorrection. Second, the stability of ground targets plays a critical role in effective cross calibration, but in practice, not all targets possess the same stability. To address the first issue, this article proposes a novel scene-driven incidence angle difference correction method. It leverages the historical information about the target scenes to determine the evaluation threshold for data blocks. Moreover, it incorporates the adaptive exponential cosine model to correct the scattering variations caused by the difference in incidence angle. To address the second issue, an uncertainty analysis method is employed to calculate the uncertainty of each data block. Then, these uncertainties are utilized to calculate weight coefficients, and the calibration constant is determined using a weighted least squares (WLS) model. Cross-calibration experimental results on the Sentinel-1A/B demonstrate an average reduction of 21.6% in the relative calibration error and 18.6% in the root-mean-square error (RMSE) compared with the traditional method, validating the effectiveness of the proposed method.

The multi-temporal polarimetric SAR data provides the difference of scattering characteristics in time dimension for terrain classification, hence it could reflect the time-variant characteristics of the same scene. Based on this advantage, crop classification is one of the important applications of multi-temporal polarimetric SAR data. However, the features of time and polarization dimension used for classification basically are from the data at each certain time, which lack the interpretation of the variant characteristics between multi-temporal data. To solve the problem, based on the specific data representation models for multi-temporal polarimetric SAR data, this paper extracts new time variant scattering features, including the change type as well as the change direction (increase or decrease). Time series Radarsat-2 data is applied for scattering change interpretation. By using the proposed features to classify crops, it is proved that the method can effectively improve the classification accuracy, and the classification performance of difference data representation models is compared.

Multi-temporal polarimertic SAR is considered to be very effective in crop classification and cultivated land detection, which has received much attention from researchers. Currently, for most multi-temporal polarimetric SAR data classification methods, the simultaneous temporal-polarimetric-spatial feature extraction capability has not been exploited sufficiently. Also, the diversity of different time and different polarimetric features has not been taken into account sufficiently. In this paper, we propose a classification model that combines a dual-stream network as a temporal-polarimetric-spatial feature extraction module with Vision Transformer(ViT) called Temporal-Polarimetric-Spatial Transformer(TSPT) to address the above problems. Secondly, a 3 dimension(3D) convolutional attention module that enables the network to weight the temporal dimension, polarimetric feature dimension and spatial dimension is developed, according to their importance. Experimental results on both UAVSAR and RADARSAT-2 datasets show that the proposed method outperforms ResNet.

During Synthetic Aperture Radar (SAR) imaging, the presence of ghost is frequently observed on SAR images of maritime scenes due to the finite pulse repetition frequency and non-ideal antenna pattern. In Polarimetric Synthetic Aperture Radar (PolSAR) images of ships, the ship movement makes the dispersion of span which is called ghost interference. This problem leads to high false alarm rates and measurement errors. To solve this problem, we propose a method applied to full-polarimetric SAR data. Firstly, we use multi-feature combination to enhance the scattering mechanism of the targets. Secondly, based on this method, using the Rank-1 and generalized similarity parameter (GSP) to improve the contrast between the sea and the ships. Finally, interference feature filter (IFF) is used to get the image with interference removed. We use the GaoFen-3 (GF-3) full-polarimetric SAR data for experiments. The results show that this method effectively removes the ghost interference, and then we will perform a target detection to prove that it can reduce the false alarm rate.

Crop classification is one of the most important applications of polarimetric SAR images. Time-series polarimetric SAR images have the characteristics of reflecting the changes of various scattering characteristics of crops in different growth periods. However, since time-series polarimetric SAR needs to combine multiple single polarimetric SAR images, the redundancy between features is multiplied. In this paper, aiming at the problem of feature redundancy, the method of similarity measurement is used to select features from two dimensions of space and time respectively to reduce feature redundancy. Since the sample size of SAR feature images applied in supervised classification is small, it's not suitable for multiple downsampling in CNN, and a suitable classifier based on Transformer is designed. Preliminary experiments on the full polarimetric data verified the effectiveness of the proposed method.

Rapid and accurate extraction of water body information is fundamental to disaster assessment. However, in SAR images, shadows often appear similar to the water regions, so the commonly threshold-based water detection methods easily confuse them. The purpose of this paper is to use Sentinel-1 polarimetric SAR data to find a simpler and more effective method to identify shadow areas out of water bodies. Considering a strong dependence on intensity of Wishart classifier, the weak backscattered regions on the SAR images will be categorized into the same class. We firstly use$H/\overline{\alpha}$Wishart to roughly classify the PolSAR data to obtain a relatively complete experimental study area. Then, we further discriminate the shadow regions from the study area based on the difference of the entropy between the water body regions and the surrounding environment. The experimental results based on Sentinel-1 measured data prove the effectiveness of this method.

This paper proposes a generalized feature extraction framework for one-dimensional(1D) remote sensing data. This approach streamlines the processing for extracting features by eliminating the need for some preprocessing, such as data normalization, data filtering, and spectrogram generation, which explicitly encode domain-specific knowledge of the tasks. The main component of the new framework, called Shifted-Grad Transformer(SGT), includes the Shift module, Grad module, Smooth module, Raw embedding module, Transformer encoder module, and additional essential module. Extensive experiments on data sets such as Hyperspectral image data, Magnetic signal data, and other 1D data have demonstrated that the SGT performs significantly better than existing methods and provides a new solution to the 1D data processing problem. Our Training code and data are available at https://github.com/wfnian/SGT.

As flood occurs unpredictably, there is not enough time to label the data in practice. The use of clustering inside flood detection deep networks can reduce their demand for labeled data. However, existing clustering algorithms aim at assigning a unique cluster for each pixel. This leads to the fact that clustering process is non-differentiable to the inputs, hindering their incorporation into deep networks. In this study, we introduce a new assignment strategy for single-polarization SAR images to make the clustering differentiable, named “soft association.” Here, each pixel is assigned to various clusters with different probabilities. The greater the probability value, the more likely the pixel will be finally assigned to the cluster. Based on this, an end-to-end trainable semi-supervised clustering network for SAR flood detection is established. Compared with the existing state-of-the-art semi-supervised methods, it can achieve similar performance with fewer labeled samples.

Polarimetric features extracted from the polarimetric synthetic aperture radar data contain a wealth of target scattering information, but usually lead to the problems, such as network learning burden and high computational consumption. A multichannel fusion convolutional neural network based on scattering mechanisms was presented in this letter. First, the polarimetric features were divided into three categories according to their corresponding scattering mechanisms, and put into three network channels, respectively. Second, a new feature output was constructed based on the fusion of three-channel output features. Third, the four output features were cascaded through two fully connected layers and the Softmax classifier to get the classification result. Moreover, a new loss function was defined, combining cross entropy and average cross entropy to prevent network overfitting. Experimental results on airborne synthetic aperture radar (AIRSAR) and GF-3 data set verified the effectiveness of the proposed method in the aspect of classification accuracy and small sample.

Time-series polarimetric synthetic aperture radar (PolSAR) has been proven to be an effective technique for crop classification and agricultural activity monitoring. However, the characterization and utilization of time-series PolSAR data by existing methods are still inadequate. They are unable to extract and utilize time-varying features, which can describe the dynamic changes of crop polarimetric information. In this paper, we propose a tensor form to comprehensively describe the information of time-series PolSAR data, including spatial context information, polarimetric scattering information, and temporal context information. And we define a novel similarity value for the tensors (TSV), which can simultaneously consider distance and shape similarity of tensors. Then, we construct a tensor-based graph representation to capture the global similarity information of time-series PolSAR data. Finally, we propose a tensor-based graph convolutional network (Tensor-GCN) to extract deep features of graph node tensors for crop classification. Experimental results and analysis on two time-series PolSAR data firmly demonstrate the superiority of the proposed Tensor-GCN to other state-of-the-art methods.

Convolutional neural networks (CNNs) have demonstrated impressive ability to achieve promising results in PolSAR image classification. However, the traditional CNN performs convolution on local square regions with fixed sizes. The selection of these local square regions (patches) cannot fully take advantage of the boundary information of land covers and cannot search optimal neighborhoods in the whole image. To overcome these shortcomings, we propose a superpixel-based graph convolutional network (SP-GCN) for PolSAR image classification. SP-GCN utilizes superpixels as graph nodes, which makes full use of boundary information of superpixels and significantly reduces the computational cost of GCN, making it possible to apply GCN to large-scale PolSAR image classification. To reduce the impact of superpixel scale on classification results, we further propose a multiscale superpixel-based graph convolutional network (MSSP-GCN) based on the SP-GCN. Experimental results on three PolSAR datasets firmly demonstrate the superiority of the proposed SP-GCN and MSSP-GCN to other state-of-the-art methods.

In existing superpixel-wise segmentation algorithms, superpixel generation most often is an isolated preprocessing step. The segmentation performance is determined to a certain extent by the accuracy of superpixels. However, it is still a challenge to develop a stable superpixel generation method. In this article, we attempt to incorporate the superpixel generation and merging steps into an end-to-end trainable deep network. First, we employ a recently proposed differentiable superpixel generation method to over-segment the single-polarization synthetic aperture radar (SAR) image. It outputs the statistical likelihood that each pixel belongs to different superpixels. In superpixel merging part, as one of our main contributions, we propose a superpixel-wise statistical dissimilarity measure method for converting the soft superpixels set into a self-connected weighted graph. More importantly, inspired by the concept of the number of walks in graph theory, we define the$k$-order connectivity of each vertex. This definition can intelligently indicate the potential soft cluster centers and class assignments in graph. This merging method is differentiable, computationally simple, and free of empirical parameters. The superpixel generation and merging phases can be implemented under a unified deep network. The benefit is that our method can iteratively adjust the shapes of the superpixels according to the boundaries and segmentation results during training, until the satisfactory segmentation results are captured. Experimental results on real SAR images demonstrate that the segmentation precision of our proposed method is superior to other state-of-the-art methods in terms of precision and computational efficiency.

Since the number of superpixels is lower than that of pixels, superpixels can substantially speed up subsequent processing steps and have been widely used in synthetic aperture radar (SAR) image segmentation. However, in most of the existing superpixel-wise segmentation algorithms, superpixel prediction is an isolated preprocessing step and is independent of the segmentation task. The performance of the segmentation results is determined by the accuracy of superpixels. Once superpixels are generated, their shape cannot be changed in the following segmentation stage, even if the same superpixels contain pixels of different landcovers. To address this, we propose an end-to-end trainable superpixel-wise segmentation method for single-polarization SAR images. First, we design a differentiable boundary-ware clustering method for estimating task-specific superpixels. Instead of the hard association between pixels and superpixels in the existing superpixel algorithms, this method introduces the soft association map to make the clustering differentiable. Hence, it can be implemented using a simple deep fully convolutional network. In the segmentation part, we propose a novel soft graph convolution network (Soft-GCN), which takes the association map as input and performs superpixel-wise segmentation. The advantage of our method is that superpixel generation and graph convolution parts can be trained under a unified framework, until two parts obtain the optimum parameters. In the training process, it can adaptively adjust the shape of the superpixels according to the segmentation results, ensuring the superpixels correctly adhere the boundaries. Experimental results with simulated and real SAR images demonstrate that our method outperforms other state-of-the-art segmentation algorithms, while also being faster.

Currently, deep neural networks have been widely used in the field of SAR target recognition. Many researchers found that deep neural networks have an ability of denoising. In many cases, there is no need to denoise in pre-process. But the denoising ability of deep neural networks can take place of conventional denoising algorithm or not is doubtful. In this article, we explore the effect of image denoising algorithms to SAR target recognition methods based on deep neural networks. Firstly, seven traditional denoising algorithms are selected to process two SAR datasets. And these data are utilized to train two kinds of deep neural networks. After comparing and analyzing the training processes and results, we find that 1) The effect of denoising algorithms is influenced by architectures of neural networks and quality of datasets. It is difficult to find a SAR image denoising algorithm, which can improve the accuracy of any recognition network. Sometimes they even drag down the performance of recognition networks. 2) The deep networks with more layers will have better denoising ability, so the effect of denoising algorithms will decrease. For ResNet, there is no need to add the denoising processing.

Small vessels in synthetic aperture radar (SAR) images usually have weak scattering intensity and occupy only a few numbers of image pixels, resulting in a high miss detection rate during the detection process. Regarding the problem, two solutions were presented in this paper. Firstly, dual-polarimetric SAR data were used and dual-polarimetric features were adaptively fused. Comparing to single-polarization and conventional non-adaptive fusion method, it optimally enhanced the characteristics of small vessels. Secondly, the conventional feature pyramid network (FPN) was enhanced by reducing the downsampling factor, adding spatial attention, and channel attention. The added spatial attention enhanced the significant features of small vessels on the large-scale feature map; the added channel attention filtered out the spliced features maps that were benefiting small vessel detection and reduced feature redundancy. Experimental results on the small vessel data set of Sentinel-1 verified that it not only reduced the miss detection rate but also improved calculation efficiency.

Polarimetric synthetic aperture radar (PolSAR) image classification is an important part of SAR data interpretation and provides more intuitive and detailed SAR polarization information. To bridge the PolSAR data and applications, it is necessary to design a comprehensive PolSAR classification framework to achieve satisfactory results. The deep neural network (DNN) appears to be a solution for the classification issue, in which it outperforms the classical supervised classifiers under the condition of sufficient training data. However, the volume of training data will greatly limit the effectiveness of practical applications. In this article, we try to solve the dependence issue on training data in three different ways: recurrent learning, data augmentation, and postprocessing. First, the long short-term memory (LSTM) network is introduced to achieve pixel sequence learning by taking into account the spatial and polarimetric features. Second, the random neighbor pixel-block (RNPB) method is proposed to increase the number of training samples for sequence learning. Third, the conditional random field (CRF) model is employed to further improve the classification accuracy. In the experiments, three sets of PolSAR data are used to evaluate the small sample performance of the proposed classification method. With only 0.5% labeled pixels for training, the proposed RNPB-LSTM-CRF method can approach 99% overall classification accuracy for all the data sets. Compared with the existing methods, the proposed method can achieve state-of-the-art results for PolSAR image classification under the condition of 1% training samples.

Many deep learning algorithms have been successful applied for synthetic aperture radar automatic target recognition (SAR-ATR), but high recognition accuracy usually relies on large amount of labeled training data. In addition, SAR is active imaging sensor and target characteristics are quite different with varying look angles, which also reduces recognition accuracy. Multi-task learning can improve the performance of main task by learning and sharing useful information from auxiliary tasks. Based on multi-task learning, this paper fully exploits the potential of available SAR data for target classification. Two auxiliary tasks, separating target from shadow and estimating target aspect angle, are designed to obtain auxiliary information and improve the classification accuracy. The MSTAR data set proves the effectiveness of the method, and the results show that the method has good recognition accuracy.

Simultaneous multitask processing is a common requirement in synthetic aperture radar (SAR) automatic target recognition (ATR), e.g., not only the category of the target but also the aspect angle of the target need to be identified at the same time. Moreover, the target recognition network is always expected to have the capability of incremental learning, i.e., acquire the processing capabilities for new tasks while maintaining the processing capabilities for old tasks. In this paper, an incremental multitask learning method based on structured pruning is proposed. The structured pruning, originally proposed for network compression, is used to learn with dominant neuron and release parameter space of convolutional neural network for new tasks. Through iterative pruning and training of new tasks, multitask target recognition is realized in a single convolutional neural network and could simultaneously output recognition results of multiple tasks. The experiments on the MSTAR dataset show that our method can simultaneously recognize the category and aspect angle of target, while does not decrease the corresponding accuracy compared to single-task processing.

Polarimetric Synthetic Aperture Radar (PolSAR) image classification is an essential part of SAR data applications. As one of the image classification methods that can efficiently capture structural information and semantic context, the convolutional neural network (CNN) seems to be a solution for the classification issue in that it outperforms the classical supervised classifiers under the condition of sufficient training data, and it has been used in PolSAR classification widely. Simultaneously, the distance metric learning (DML) is proposed to improve the classification algorithms in performance and even in feature extraction. In this paper, DML with adaptive density discrimination regarded as a loss function, namely Magnet Loss, is applied to the classification of PolSAR images, and k-means++ is realized the clustering process for each category of training samples. Then, different classifiers are executed to replace the softmax function to achieve more accurate classification. Finally, a series of experiments are implemented to prove the effectiveness of the proposed method. Simultaneously, the samples of the coarse label are given and used to analyze the fine-grained classification algorithm by clustering.

Generative adversarial network (GAN) is an artificial neural network based on unsupervised learning method. Due to its powerful model representation capabilities, GAN has been introduced to synthesize synthetic aperture radar (SAR) image data, for the real sample is difficult to acquire. Large-scale, high-resolution SAR images play an important role in promoting SAR applications, such as automatic target recognition and image interpretation. However, on account of the difficult training problem of GAN network, especially for SAR images with speckle noise, it is difficult to obtain high-resolution SAR images by simply transfer the net from optical image. Recent studies in other image fields have shown that hierarchical structure is an effective and useful way to decompose a generation task into several smaller subtasks. How to obtain more high-resolution SAR images from limited original samples through GAN is the target of our research. Therefore, in this paper, we introduce a hierarchical GAN network model to generate SAR images, through the multi-stage network, gradually improve the quality of the generated image, and finally obtain high-resolution images. The type and aspect of generated images are determined by the input of condition vectors in the last two stages. In addition, we introduce the triple loss, in which the background loss is used to imitating background clutter noise of SAR image, the condition loss is to make the generated images' type and aspect become controllable, and the global loss for getting higher image generation quality. The generated images show high similarity with the real samples.

In this paper, we improve the Siamese Networks for SAR target few-shot learning. SAR target recognition is an important branch of SAR application. It can efficiently extract target category information from complex SAR images and help humans quickly understand SAR images. However, many successful machine learning methods require large amounts of annotated data. So, few-shot learning is always a topical challenge for machine learning. We apply Siamese Networks to SAR target recognition with limited data and improved it. Our model consists of CNN encoder, similarity discriminator and classifier. Relevantly, it has two inputs and three outputs. CNN encoder is constrained by similarity discriminator and classifier. Furthermore, the larger difference from the Siamese Network is that the target category is outputted by the classifier, not by the similarity discriminator. Our method not only makes use of the advantage of metric learning to improve the accuracy of SAR target recognition with limited data, but also significantly reduces the prediction time consumption for the model based on metric learning. In the ten categories military vehicle classification task, there are only five samples for each category and a total of 2425 testing samples. Our method outperforms A-ConvNet and Siamese Networks by 15.8% and 8.41%. The prediction time consumption of Siamese Networks is 114.832s, while that of our method is 1.172s.

Polarimetric synthetic aperture radar (PolSAR) imagery classification is an important part of SAR data interpretation. The number of available labeled samples limits the applications of supervised classifiers. In order to solve this issue, the representation based classification algorithms have been widely used. Usually, PolSAR image features are extracted by various methods, and their divergence is very significant. In the data representation based methods, the feature divergence is ignored in the distance metric, thus the different features have the same metric contributions. In this letter, we propose a robust weighting nearest regularized subspace (NRS) method, which introduces the robust statistics to construct the weights of distance metric according to the feature divergence. This method can increase the representation ability of the training samples by the weighted calculation of the biasing Tikhonov matrix. The experimental results show that the weighted distance metric can boost the original NRS classifier by 1.5%, and prove that the feature divergence should be taken into account in the data representation process.

Deep convolutional neural network (CNN) is an important branch of deep learning. Due to its strong ability of feature extraction, CNN models have been introduced to solve the problems of synthetic aperture radar automatic target recognition (SAR-ATR). However, labeled SAR images are difficult to acquire. Therefore, how to obtain a good recognition result from a small sample dataset is what we mainly focus on. In theory, a deeper network can bring a better training result. But it also brings more difficulties to the training process, especially with limited labeled training data. The residual learning which proposed in recent years can alleviate this problem effectively. In this paper, we use a deep residual network, and introduce the dropout layer into the building block to alleviate overfitting caused by limited SAR data. In order to improve the training effect, the new loss function center loss is adopted and combined with softmax loss as the supervision signal to train the deep CNN. The experimental results show that our method can achieve the classification accuracy of 99.67% with all training data, without data augmentation or pre-training. When data of the training dataset was reduced to 20%, we can still achieve a recognition result higher than 94%.

Circular synthetic aperture radar (CSAR) can provide distinctive multi-aspect anisotropic scattering signatures. However, it is impossible to retain the anisotropic signatures in a SAR image that combines all the subapertures coherently or incoherently. In this letter, we propose a polarimetric CSAR anisotropic scattering detection framework to characterize multi-aspect and fully polarimetric SAR signatures of point-like and distributed targets. We applied this framework to quantify and rank media polarimetric scattering dissimilarity over all aspects and to determine whether the most different one shows anisotropy by use of constant false alarm rate (CFAR) detection. Furthermore, we demonstrated the monotonicity of CFAR detection function and incorporated this function to decrease the complexity of the anisotropic scattering test. Our algorithm was validated and applied to a set of airborne P-band fully polarimetric circular SAR data acquired by the Institute of Electronics, Chinese Academy of Science (IECAS). The results indicate the framework can retain anisotropic scattering and extract a series of new multiaspect polarimetric SAR signatures for terrain classification.

The polarimetric features of PolSAR images includes the inherent scattering mechanisms of terrain types, which is important for classification and other earth observation applications. By the use of target decomposition methods, many polarimetric scattering components can be obtained. Besides, the elements of Coherency/Covariance Matrix, as well as polarimetric descriptors such as SPAN, SERD/DERD etc., can also provide characteristic information. However, the computation cost will be very high if all of the polarimetric features are employed as the input of the classification process. In this paper, the effective polarimetric feature combination are studied based on the classification performance of SVM (Support Vector Machine) and NRS (Nearest-Regularized Subspace) machine learning approaches. A fast strategy on basis of correlation coefficient is used to select the features for classification experiments. For the airborne PolSAR data in Flevoland, 10 features have been selected from the total 107 polarimetric features with good classification accuracy up to 93.6%. The experiments on other data sets will be shown.

Circular synthetic aperture radar (CSAR) can provide distinctive multiaspect anisotropic scattering signatures. However, it is impossible to retain the anisotropic signatures in an SAR image that combines all the subapertures coherently or incoherently. In this letter, we propose a polarimetric CSAR anisotropic scattering detection framework to characterize multiaspect and fully polarimetric SAR signatures of pointlike and distributed targets. We applied this framework to quantify and rank media polarimetric scattering dissimilarity over all aspects and to determine whether the most different one shows anisotropy by the use of constant false-alarm rate (CFAR) detection. Furthermore, we demonstrated the monotonicity of CFAR detection function and incorporated this function to decrease the complexity of the anisotropic scattering test. Our algorithm was validated and applied to a set of airborne P-band fully polarimetric circular SAR data acquired by the Institute of Electronics, Chinese Academy of Science. The results indicate that the framework can retain anisotropic scattering and extract a series of new multiaspect polarimetric SAR signatures for terrain classification.

Polarimetric synthetic aperture radar (PolSAR) features have great significance in application of vegetation classification, which can explain the scattering mechanism of the vegetation; in order to make full use of PolSAR features' scattering mechanism explanation, the decision tree classifier is chosen because of its simple and hierarchical classifier structure. Since all the classification methods are composed of two parts: feature selection and classifier selection, this method is established with PolSAR features as selected feature and decision tree as adopted classifier. As decision tree classifier is flexible in discriminant rules, the hierarchical classification process of multi-feature is built under the notion of Fisher Linear Discriminant (FLD); after the classification process, optimization of the branch sequence and boundary algorithms is made to improve the classification accuracy of the specific classes. The experiments of AIRSAR and AgriSAR data illustrate that this method can obtain good classification accuracy; at the same time, it can introduce expert knowledge into the whole framework to help improve the classification accuracy, and extract useful information of features and classifiers from the classification results as new expert knowledge.

Synthetic Aperture Radar(SAR) has been widely used in airborne remote sensing and satellite ocean observation fields to reduce the affect of weather condition and sun illumination. As technology developed, swath and resolution requirements are increased in terrain, which arouse a huge increase in the number of simulated points and simulated pulses and lead to a huge increase in simulated time. With the development of graphics processing unit(GPU), it can parallel simulated points to reduce simulated time. As for increased simulated pulses, they can be paralleled on distributed computers. In the article, we focus on parallel on increased simulated pulses and put forward two frameworks based on message passing libraries (MPI) and cloud computing (Hadoop).

GaoFen-3 is China's first meter-level multi-polarization Synthetic Aperture Radar (SAR) satellite with scientific and commercial applications, which was developed by the China Academy of Space Technology (CAST) and had been launched in August, 2016. The SAR instrument and ground data processing system were developed by the Institute of Electronics, Chinese Academy of Sciences (IECAS). It employs a multi-polarization C-band SAR based on active phased array technology, which allows flexible beam operations in azimuth scanning, range scanning, right looking and left looking. Hence, GaoFen-3 has 12 imaging modes, covering the traditional Stripmap mode, ScanSAR mode, and the emerging Wave mode and Sliding Spotlight mode, and is a SAR satellite with the most abundant imaging modes in the world. In order to evaluate the imaging performance of these modes, the multiple mode SAR raw data simulation is highly demanded. In the paper, the simulation framework, the simulation algorithms and the evaluation strategies will be briefly introduced to expose how the raw data simulation guarantees the development of GaoFen-3 and its processing system.

In this study, we investigated the unsupervised terrain classification for hybrid polarimetric (HP) SAR by using the circular polarization ratio (CPR) parameter alone. According to the theoretical deduction based on scattering matrices of ideal polarimetric scattering mechanisms (PSMs), CPR is suggested to be processed with the logarithmic function in order to have a balanced span between the ideal PSMs' CPR values, which in turn can improve the identification of real PSMs. Utilizing one simulated HP dataset, the performance of the proposed logarithmic CPR parameter is first compared with that of classical m and χ parameters, and then assessed with real PSM classes identified by the H-α classification algorithm. Finally, a simple classification scheme of terrains is proposed and validated.

Multi-aspect PolSAR data contains polarimetric properties from different look angle. Multi-aspect polarimetric information can be applied in geometric measurement, target identifying, precise classification. In order to characterize anisotropic target, anisotropic and isotropic scattering need to be separated from the raw data. A detecting-removing-incoherent-adding (DRIA) framework, presented in Li Yang's doctoral dissertation, suggests to remove the anisotropic scattering, gain a removal series and incoherent integrate the reserved data. In this paper, in order to identify anisotropic target, an anisotropic scattering model is raised. An improved detection and feature retrieval method is presented base on DRIA framework. The equivalent number of looks (ENL) used in Li Yang's dissertation is proved to bring measurement error to the result. The anisotropic scattering can be correctly identified after the error is restored. Two kinds of maximum-likelihood ratio are proved to gain the same result in sort. Three features are retrieved from the removal series to describe the anisotropic scattering. The experimental data is circular SAR (CSAR) data acquired by the Institute of Electronics airborne CSAR system at P-band.

PolSAR features have great significance in application of vegetation classification, which can explain the scattering mechanism of the vegetation; the decision tree classifier not only can obtain good classification accuracy, but also can adjust the classification results, as well as make full use of PolSAR features to explain the scattering mechanism of the targets because of its simple and hierarchical classifier structure. Since all the classification methods are composed of two parts: feature selection and classifier selection, this paper established a classification method with PolSAR features as selected feature and decision tree as adopted classifier. As decision tree classifier is flexible in discriminant rules, the expected design of the experimental scheme introduces multiple data sources, multiple features and multiple classifiers into the framework of this classification method. In addition, discussion about how to improve the classification accuracy of the specific target has been made. The experiment of AIRSAR-Flevoland data illustrates the feasibility of this method.

In this letter, an accurate topographical phase is applied to the model-based (odd-bounce, double-bounce, and volume scattering) decomposition of synthetic aperture radar (SAR) interferometry data. The decomposition procedure considered here is a determined nonlinear equation system that can be solved numerically. The accurate topographical phase is first estimated and then used as the initial input parameter to our numerical method. This approach avoids large errors generated by the constant topographical phase in fluctuating forested areas. Additionally, the modified volume scattering model introduced by Yamaguchiet al.is applied to the polarimetric SAR interferometric target decomposition data of forested areas, rather than the purely random volume scattering of Freeman and Durden, to produce the best fit to the measured data. This method retrieves the magnitude associated with each mechanism and their heights. The quality of the decomposition is demonstrated using L-band simulated data created with PolSARproSim software and L-band airborne data (BioSAR 2008) acquired by the DLR E-SAR in the Vindeln Municipality in northern Sweden.

In this paper we apply PolInSAR decomposition techniques to compact-pol SAR Interferometry. The complex cross-correlation matrix of single-baseline polarimetric SAR Interferometry is decomposed into three 2 × 2 scattering matrices corresponding to surface scattering, double scattering and random volume scattering. A numerical method is applied to solve the system of nonlinear equations involved in the decomposition procedure. According to the above decomposition procedure, the power contribution and vertical displacement may be obtained for each of the three scattering mechanisms, from compact-PolInSAR data. Finally we compare the compact-PolInSAR target decomposition results with those of quad-PolInSAR, to assess the ability and accuracy of compact-PolInSAR target decomposition.

In this paper we improve the valid range analysis method in soil inversion models, using entropy/alpha space in the Cloude-Pottier decomposition theory. The ranges in data where inversion models can be applied are called the valid ranges of the inversion models. The improved valid ranges are considered more accurate through the Integral Equation Method (IEM) simulations. General method used to find out valid ranges of inversion models is the Normalized Difference Vegetation Index (NDVI), which shows the areas where the vegetation over soil is not too heavy for inversion models to apply. The proposed method introduces entropy/alpha parameters to the analysis of valid ranges, because these two parameters are closely related to target scattering mechanisms. Experiment results with fully polarimetric AIRSAR data show that the effectiveness of inversion models is increased by adding entropy/alpha space analysis.