Polarimetric Synthetic Aperture Radar Images Research Articles

A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data.

Unsupervised change detection approaches, which are relatively straightforward and easy to implement and interpret, and which require no human intervention, are widely used in change detection. Polarimetric synthetic aperture radar (PolSAR), which has an all-weather response capability with increased polarimetric information, is a key tool for change detection. However, for PolSAR data, inadequate evaluation of the difference image (DI) map makes the threshold-based algorithms incompatible with the true distribution model, which causes the change detection results to be ineffective and inaccurate. In this paper, to solve these problems, we focus on the generation of the DI map and the selection of the optimal threshold. An omnibus test statistic is used to generate the DI map from multi-temporal PolSAR images, and an improved Kittler and Illingworth algorithm based on either Weibull or gamma distribution is used to obtain the optimal threshold for generating the change detection map. Multi-temporal PolSAR data obtained by the Radarsat-2 sensor over Wuhan in China are used to verify the efficiency of the proposed method. The experimental results using our approach obtained the best performance in East Lake and Yanxi Lake regions with false alarm rates of 1.59% and 1.80%, total errors of 2.73% and 4.33%, overall accuracy of 97.27% and 95.67%, and Kappa coefficients of 0.6486 and 0.6275, respectively. Our results demonstrated that the proposed method is more suitable than the other compared methods for multi-temporal PolSAR data, and it can obtain both effective and accurate results.

Polarimetric SAR image despeckling using bandelet transform based on additive–multiplicative speckle model

Efficient speckle filtering algorithms are required for the effective use of polarimetric synthetic aperture radar (SAR) technology in remote sensing and surveillance applications. Nevertheless many techniques have been proposed over the past two decades to decrease the speckle noise in polarimetric SAR images, they are all based on the multiplicative speckle noise model. In order to fully utilise the advantages of polarimetry of these images, an additive–multiplicative noise model is explored. Coupled with this, bandelet based Bayesian thresholding is used to tap the advantages of transform domain filtering. Here the elements of the covariance matrix are processed differently for diagonal and off-diagonal elements to achieve maximum benefits. The proposed filtering scheme is evaluated using airborne and spaceborne polarimetric images and compared against state-of-the-art techniques. Results indicate that the proposed method reduces the speckle content while retaining the geometrical features in these images.

Coastline detection in polarimetric SAR images using Markov random field segmentation based on mixture Wishart distribution

Coastline detection in polarimetric SAR images using Markov random field segmentation based on mixture Wishart distribution

Extracting impervious surfaces from full polarimetric SAR images in different urban areas

ABSTRACTAccurate mapping of impervious surface in urban areas is of great demand in environmental and socio-economic studies since impervious surface growth is recognized as an indicator of urbanization. To demonstrate the potential of full polarimetric Synthetic Aperture Radar (SAR) in impervious surface detection in different urban areas, this study focused on the exploitation of only SAR data. Three cities with different levels of urbanization – Tehran, Kordkuy, and Arak – have been selected to reduce the effect of input data on achieved results. Advanced Land Observing Satellite/Phased Array L-band Synthetic Aperture Radar (ALOS/PALSAR) images have been classified by support vector machine (SVM) with the help of training data from high-resolution satellite images. Quantitative assessment of classification accuracy revealed that Kordkuy, a not fully developed city (i.e. 84.2%) has the lowest accuracy and Arak, a medium urbanized city, has the highest accuracy (i.e. 90.0%). To further explore the efficiency of full polarimetric SAR, grey level co-occurrence matrix (GLCM) texture of polarized bands has been extracted and put into the classification procedure. The texture information of SAR data provided positive contribution to the impervious surface estimation in three study cases. The improvement is especially noted in dark impervious surface class. All three study areas show an increase of about 6–8% in classification accuracy. The results prove that single use of full polarimetric SAR images holds high potential in identifying impervious surfaces in urban areas. The findings are of great importance in frequent urban impervious surface mapping and monitoring especially in cloud-prone area, where the use of optical data as well as the fusion of optic and SAR data are limited.

Improved four‐component based polarimetric synthetic aperture radar image decomposition

Scattering mechanism ambiguity, negative power problem, and complete utilisation of coherency matrix elements have been the major challenges of the model-based decomposition methods. In this study, the aforementioned issues are addressed simultaneously with an improved four-component decomposition method. In the proposed method, helix scattering power is obtained conventionally, while helix angle compensation is used parallelly for the pixels where helix scattering power is overestimated. In the next step, volume scattering power is determined through the eigen-decomposition approach. Both steps are performed by ensuring the positive semidefinite attribute of the coherency matrix after subtracting helix and volume scattering contributions. The next two scattering powers of surface and dihedral components are derived through the decomposition of the remainder rank-2 coherency matrix into two rank-1 matrices. The experimental validation of the proposed method is carried out on the urban environment of two Indian cities where one can easily find out the random streets distribution and unplanned population settlement. The experimental analyses on these dense and complex urban areas indicate that with the proposed decomposition methodology, non-negative scattering powers are obtained and scattering mechanism ambiguity is greatly suppressed.

Scatter Matrix Based Domain Adaptation for Bi-Temporal Polarimetric SAR Images

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.

Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding

Feature extraction of an urban area is one of the most important directions of polarimetric synthetic aperture radar (PolSAR) applications. A high-resolution PolSAR image has the characteristics of high dimensions and nonlinearity. Therefore, to find intrinsic features for target recognition, a building area extraction method for PolSAR images based on the Adaptive Neighborhoods selection Neighborhood Preserving Embedding (ANSNPE) algorithm is proposed. First, 52 features are extracted by using the Gray level co-occurrence matrix (GLCM) and five polarization decomposition methods. The feature set is divided into 20 dimensions, 36 dimensions, and 52 dimensions. Next, the ANSNPE algorithm is applied to the training samples, and the projection matrix is obtained for the test image to extract the new features. Lastly, the Support Vector machine (SVM) classifier and post processing are used to extract the building area, and the accuracy is evaluated. Comparative experiments are conducted using Radarsat-2, and the results show that the ANSNPE algorithm could effectively extract the building area and that it had a better generalization ability; the projection matrix is obtained using the training data and could be directly applied to the new sample, and the building area extraction accuracy is above 80%. The combination of polarization and texture features provide a wealth of information that is more conducive to the extraction of building areas.

Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification

Convolutional neural networks (CNNs) have shown good performance in polarimetric synthetic aperture radar (PolSAR) image classification due to the automation of feature engineering. Excellent hand-crafted architectures of CNNs incorporated the wisdom of human experts, which is an important reason for CNN's success. However, the design of the architectures is a difficult problem, which needs a lot of professional knowledge as well as computational resources. Moreover, the architecture designed by hand might be suboptimal, because it is only one of thousands of unobserved but objective existed paths. Considering that the success of deep learning is largely due to its automation of the feature engineering process, how to design automatic architecture searching methods to replace the hand-crafted ones is an interesting topic. In this paper, we explore the application of neural architecture search (NAS) in PolSAR area for the first time. Different from the utilization of existing NAS methods, we propose a differentiable architecture search (DAS) method which is customized for PolSAR classification. The proposed DAS is equipped with a PolSAR tailored search space and an improved one-shot search strategy. By DAS, the weights parameters and architecture parameters (corresponds to the hyperparameters but not the topologies) can be optimized by stochastic gradient descent method during the training. The optimized architecture parameters should be transformed into corresponding CNN architecture and re-train to achieve high-precision PolSAR classification. In addition, complex-valued DAS is developed to take into account the characteristics of PolSAR images so as to further improve the performance. Experiments on three PolSAR benchmark datasets show that the CNNs obtained by searching have better classification performance than the hand-crafted ones.

Structure Label Matrix Completion for PolSAR Image Classification

Terrain classification is a hot topic in polarimetric synthetic aperture radar (PolSAR) image interpretation that aims at assigning a label to every pixel and forms a label matrix for a PolSAR image. From the perspective of human interpretation, classification is not in terms of pixels, but decomposed perceptual groups and structures. Therefore, a new perspective of label matrix completion is proposed to treat the classification task as a label matrix inversion process. Firstly, a matrix completion framework is built to avoid processing the large-scale PolSAR image data for traditional feature and classifier learning. Secondly, a light network is used to obtain the known labels for the complete task by uniform down-sampling of the entire image that aims to keep the shape of regions in a PolSAR image and reduce the computational complexity. Finally, the zeroth- and first-order label information is proposed as the prior distribution for label matrix completion to keep the structure and texture. The experiments are tested on real PolSAR images, which demonstrates that the proposed method can realize excellent classification results with less computation time and labeled pixels. Classification results with different down-sampling rates in the light network also prove the robustness of this method.

PolSAR Image Classification with Lightweight 3D Convolutional Networks

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.

Dense connection and depthwise separable convolution based CNN for polarimetric SAR image classification

Convolution neural networks (CNN) have achieved great success in natural image processing where large amounts of training data are available. However, for the polarimetric synthetic aperture radar (PolSAR) image classification problem, the number of labeled training samples is typically limited. To improve the performance of CNN on limited training data, we propose a new network, the densely connected and depthwise separable convolutional neural network (DSNet). According to characteristics of PolSAR data, DSNet uses depthwise separable convolution to replace standard convolution, to independently extract features over each channel in PolSAR images. DSNet also introduces dense connections to directly connect non-adjacent layers. With the depthwise separable convolution and dense connections, DSNet can avoid extracting redundant features, reuse the hierarchical feature maps of PolSAR images and reduce the number of training parameters. Compared with normal CNN, DSNet is more lightweight and its training parameters decrease to less than 1/9. We compare DSNet against several popular algorithms on three different data sets, and show that DSNet achieves better results while using less training samples.

A residual convolutional neural network for polarimetric SAR image super-resolution

PolSAR images provide rich polarimetric information, however, due to the limitations of the imaging system, the spatial resolution decreases while the richer polarimetric information is obtained. The lower resolution limits the application, so it is necessary to use super-resolution technology to improve the spatial resolution. In this paper, in response to the low spatial resolution of PolSAR images, a PolSAR super-resolution framework is proposed to improve the spatial resolution by the use of a residual convolutional neural network. Within this framework, deconvolution is used to up-sample the PolSAR images, PReLU is added to maintain the numerical properties. A complex structure block is also designed to accommodate the PolSAR data structure. In addition, prior information on the low-resolution image itself is used to reduce the artifacts. The proposed method shows a superior performance when compared to the traditional methods in both the quantitative evaluation and visual assessment. The proposed method improved the spatial resolution significantly, especially in terms of detail information retention, and it improves the mean PSNR by more than 12% when compared to the traditional methods. By analyzing the phase statistics and polarimetric response, it is shown that the proposed method has a good polarimetric information retention ability, and can obtain a higher classification accuracy.

PolSAR image classification via a novel semi-supervised recurrent complex-valued convolution neural network

Due to that polarimetric synthetic aperture radar (PolSAR) data suffers from missing labeled samples and complex-valued data, this article presents a novel semi-supervised PolSAR terrain classification method named recurrent complex-valued convolution neural network (RCV-CNN) which combines semi-supervised learning and complex-valued convolution neural network (CV-CNN). The proposed method only needs a small number of labeled samples to achieve good classification results. First, a Wishart classifier is used to select some reliable PolSAR samples. Then, two new semi-supervised deep classification model RCV-CNN1 and RCV-CNN2 have been proposed to improve PolSAR image classification accuracy. Moreover, our proposed methods could solve the problem of network overfitting phenomenon to some extend when the number of training samples is too small. Finally, three real PolSAR dataset are applied to verify the effectiveness of our algorithms. Compared with the other five state-of-the-art methods, the proposed RCV-CNN1 and RCV-CNN2 classification models show good performance in accuracy and generalization.

A New Parallel Dual-Channel Fully Convolutional Network Via Semi-Supervised FCM for PolSAR Image Classification

Convolutional neural network (CNN) has achieved remarkable success in polarimetric synthetic aperture radar (PolSAR) image classification. However, the PolSAR image classification is a pixelwise prediction assignment. The disadvantages of repeated calculation, memory occupation, and inadequate labeled pixels make that CNN is less efficient when classifying PolSAR images. Compared to CNN, fully convolutional network (FCN) has obvious merits for PolSAR image classification: take arbitrary-size images as input; output a 3-D dense class map to maintain the structure of the input; settle PolSAR image classification tasks with efficient dense learning, which avoids repeated calculation and memory occupation. In view of accuracy, efficiency, and insufficient labeled pixels, our method proposes a new parallel dual-channel dilated fully convolutional network (DCDFCN) for PolSAR image classification. First, limited by insufficient labeled samples, the semi-supervised fuzzy c-means clustering algorithm is exploited to enlarge the labeled samples set. Then, to improve the density of output feature maps, we design a new FCN variant named dilated FCN (DFCN) by introducing a dilated convolution block to FCN. Finally, we use two similar DFCN frameworks in parallel with different convolutional kernels to design a new DCDFCN model, which can extract more discriminate features of PolSAR images. Experimental results on three PolSAR images demonstrate that the performance of our approach is superior to several state-of-the-art methods for PolSAR image classification.

Polarimetric SAR Image Semantic Segmentation With 3D Discrete Wavelet Transform and Markov Random Field

Polarimetric synthetic aperture radar (PolSAR) image segmentation is currently of great importance in image processing for remote sensing applications. However, it is a challenging task due to two main reasons. Firstly, the label information is difficult to acquire due to high annotation costs. Secondly, the speckle effect embedded in the PolSAR imaging process remarkably degrades the segmentation performance. To address these two issues, we present a contextual PolSAR image semantic segmentation method in this paper.With a newly defined channelwise consistent feature set as input, the three-dimensional discrete wavelet transform (3D-DWT) technique is employed to extract discriminative multi-scale features that are robust to speckle noise. Then Markov random field (MRF) is further applied to enforce label smoothness spatially during segmentation. By simultaneously utilizing 3D-DWT features and MRF priors for the first time, contextual information is fully integrated during the segmentation to ensure accurate and smooth segmentation. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on three real benchmark PolSAR image data sets. Experimental results indicate that the proposed method achieves promising segmentation accuracy and preferable spatial consistency using a minimal number of labeled pixels.

A Novel Multi-Feature Joint Learning Method for Fast Polarimetric SAR Terrain Classification

Polarimetric synthetic aperture radar (PolSAR) image classification is one of the most important study areas for PolSAR image processing. Many kinds of PolSAR features can be extracted for PolSAR image classification, such as the scattering, polarimetric or image features. However, it is difficult to improve the classification accuracy of PolSAR images by using all these low-level features directly, since they may conflict with each other for classification. Hence, how to joint learn these low-level features to obtain high-level discriminating features is a challenging task. To solve this problem, a novel fast multi-feature joint learning method(fMF-JLC) is proposed for PolSAR image classification. The proposed method extract three kinds of low-level features of PolSAR data at first. Then, a multi-feature joint sparse representation model(MF-JSR) is proposed by designing joint sparse constraints on the extracted features above. Moreover, the joint sparse features are further compressed to overcome the dimension curse and acquire semantic features by the topic model. By this way, the low-level features are fused and discriminating high-level features are acquired. However, the pixel-wise feature learning method is time consuming. To speed the proposed method, a superpixel-based fast learning method is designed by involving the contextual relationship. Experiments are taken on three sets of real PolSAR data with different sensors and bands, and several compared methods are used to verify the effectiveness of the proposed method. The experimental results illustrate that the proposed method can obtain better performance than the state-of-art methods, especially for the heterogenous areas.

A Runway Detection Method Based on Classification Using Optimized Polarimetric Features and HOG Features for PolSAR Images

A novel runway detection algorithm for PolSAR (Polarimetric Synthetic Aperture Radar) images based on optimized polarimetric features and local spatial information is proposed. Existing methods for runway detection for PolSAR images always utilize the parallel line as the primary feature. However, many other ground objects such as rivers and roads also have parallel structures thus affect the performance of these detection methods. The proposed method is based on two stages of classification with polarimetric features and the HOG (Histogram of Oriented Gradient) feature, while avoiding the interference due to the similar morphological features among different ground objects. An FCBF (Fast Correlation Based Filter) is firstly used for optimizing and selecting of the ground objects' polarimetric features of ground targets. Then RF (Random Forest) classifier is employed for extracting ROIs (Region of Interest) which may contain runways. Then HOG features are extracted from these ROIs for further classification with SVM (Support Vector Machines) to detect the runway area. Experimental results with the measured PolSAR data provided by NASA UAVSAR project show that the proposed method can detect runway regions effectively without using the parallel line. Comparative analysis is also conducted on parallel line pattern based algorithms. And the results suggest the effectiveness and performance enhancement of this method.

Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification

Terrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing and interpretation. A novel PolSAR classification method based on the three-channel convolutional neural network (Tc-CNN) is proposed and this method can effectively take the advantage of unlabeled samples to improve the performance of classification with a small number of labeled samples. Several strategies are included in the proposed method. First, in order to take the advantage of unlabeled samples, a data enhancement method based on the neighborhood nearest neighbor propagation method is proposed to enlarge the number of labeled samples. Second, to increase the role of central pixel in convolutional neural network classification based on the pixel, a spatial weighted method is proposed to increase the weight of central pixel features and weak the weight of other types of pixel features. Third, a specific deep model for PolSAR image classification (named Tc-CNN) is proposed, which can obtain more scale and deep polarization information to improve the classification results. The experimental results show that the proposed method achieves a much better performance than the existing classification methods when the number of labeled samples is few.

SSCV-GANs: Semi-Supervised Complex-Valued GANs for PolSAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification has been widely applied in many fields, such as agriculture, meteorology and military. However, some problems, such as the deficiency of labeled data and the underutilization of data information, are always the challenges that can not be ignored in PolSAR image classification. In this paper, a semi-supervised complex-valued generative adversarial networks (SSCV-GANs) is proposed for the first time to address the two issues mentioned above simultaneously. On the one hand, the complex-valued model conforms with the physical mechanism of PolSAR data and it plays an important role for retaining and utilizing amplitude and phase information of PolSAR data. On the other hand, we also present a new complex-valued GANs together with semi-supervised learning to alleviate the problem of insufficient labeled data. Specifically, our complex-valued GANs expands the training data set by generating fake data. Flevoland data and San Francisco data are used to validate the effectiveness of our model. Experimental results show that our model outperforms existing state-of-the-art models in terms of classification accuracy, especially for conditions with fewer labeled data. In particular, the analysis of the statistical distribution of the generated fake data and the real data further demonstrate the effectiveness of the proposed SSCV-GANs.

A Modified Four-Component Decomposition Method With Refined Volume Scattering Models

In this article, a modified four-component decomposition method with refined volume scattering models is proposed for polarimetric synthetic aperture radar (SAR) image processing. In the new decomposition method, after the orientation angle compensation, the orientation angle is placed in the probability density functions. General forms of the volume scattering models and branch conditions can be obtained. Similar to the four-component scattering power decomposition with extended volume scattering model (S4R) proposed by Sato et al. , refined volume scattering models can be used for various land covers based on the criteria. Since the orientation angles are contained in the refined volume scattering models, the oriented buildings can be discriminated from the vegetation areas and the overestimation problem of volume scattering is substantially overcome. In this article, the performance of the proposed method is evaluated by the spaceborne C-band Gaofen-3 data and airborne L-band E-SAR data. Several approaches are employed as a comparison of the proposed methods. Experimental results show that, compared with the existing decomposition methods, the proposed method can effectively represent the scattering characteristics of the ambiguous regions, and the double-bounce scattering contributions over the urban areas can be substantially enhanced.