Polarimetric Synthetic Aperture Radar Features Research Articles

A multi-view ensemble model based on semi-supervised feature learning for small sample classification of PolSAR images

ABSTRACT Classification with a few samples of training set has been a long-standing issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. In fact, one of the most important challenges of the PolSAR image classification task is the number of labelled samples. In essence, training network by utilizing just few numbers of training samples cannot be led to the reliable result since the neural network is so sensitive to the number of training samples. In addition, in the real PolSAR image classification task, the huge number of training samples is not accessible. On the other hand, classification performance using just small number of labelled samples is not an accurate result. So, in this paper, aiming at the small number of training samples of the PolSAR image classification task, a novel ensemble self-supervised feature-learning (ESSFL) model is designed. The designed ESSFL can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, to utilize the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet-B0 is presented and utilized as the main section of the deep learning (DL) model to extract DL features of PolSAR data. Then, using an optimization function that constrains the cross-correlation matrix of various distortions of each sample to the identity matrix, the designed deep learning model can obtain the effective features of homogeneous samples gathering together and heterogeneous samples separating from each other in a self-supervised manner. Moreover, two ensemble learning (EL) models, feature-level and view-level ensemble, are proposed to increase the feature extraction capability and classification result by jointly using spatial features at different scales and polarimetric information at different bands. Finally, the stack of the obtained features and the main polarimetric information of PolSAR data can be input into classifier for the classification of PolSAR data. In this paper we use two different classifiers, the first one is the Random Forest (RF) classifier and the second one is the Support Vector Machine (SVM) classifier. The advantages of SVM include that it can be used to avoid the difficulties of using linear functions in the high-dimensional feature space, and the optimization problem is transformed into dual convex quadratic programs that are so usable for an actual image classification task. In addition, among all the available classification methods, random forests provide one of the highest accuracies. The random forest technique can also handle big data with numerous variables running into thousands. In fact, it can automatically balance data sets when a class is more infrequent than other classes in the data that is so important for a real PolSAR image classification task. Experimental results on three well-known PolSAR data sets illustrate that the designed ESSFL can extract more discriminant features using the designed deep learning model. In the end, the experiments prove that the designed ESSFL has a significant classification performance compared with different deep learning models in the case of small number of training samples, and also it can achieve a better result in the case of large number of training samples by comparison with the most of the deep learning models.

A novel self‐supervised ensemble learning framework for land use and land cover classification of polarimetric synthetic aperture radar images

AbstractClassification with a few samples of training set has been a longstanding issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. Aiming at the small number of training samples of the PolSAR image classification task, a novel Self‐Supervised Ensemble Learning Framework (SSELF) is designed. The designed SSELF can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, utilise the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet‐B0 is presented and utilised as the main section of the Deep Learning (DL) model to extract DL features of PolSAR data. Then, using an optimisation function that constrains the cross‐correlation matrix of various distortions of each sample to the identity matrix, the designed DL model can obtain the effective features of homogeneous samples gathering and heterogeneous samples separating from each other in a self‐supervised manner. Moreover, following the great success of curriculum learning in the area of machine learning, a novel deep curriculum‐learning model is proposed, entitled Deep Curriculum Learning (DCL), to train the DL network in our self‐supervised model. The proposed DCL utilises the entropy‐alpha target decomposition to estimate the degree of complexity of each PolSAR image patch before applying it to the EfficientNet‐B0. Also, an accumulative mini‐batch pacing function is used to introduce more difficult patches to EfficientNet‐B0 in the training process of the designed self‐supervised model. Furthermore, two EL models, feature‐level and view‐level ensemble, are proposed to increase the feature extraction capability and classification result of PolSAR data by jointly using spatial features at different scales and polarimetric information at different bands. In fact, in the proposed feature‐level ensemble strategy, to improve the classification result, the extracted features of the different scales are used as the input of the designed feature fusion algorithm. Therefore, the extracted features are mapped to the new space with lower dimension. In general, in the proposed view‐level ensemble strategy, first, the Mutual Information (MI) between each feature and the other features calculates, and then based‐on the calculated MI, different group of features are selected as various views. Next, the final classification result of the PolSAR image classification is obtained by using the designed majority vote of the result in each view. It should be noted that unlike existing traditional methods, both amplitude and phase information of SAR images to devolve the training process of the proposed model are used. In addition, all of the parameters of the proposed network are developed to a complex domain. In addition, a complex backpropagation algorithm by using the gradient‐based model is used for training the network. Finally, experimental results on three well‐known PolSAR data sets illustrate that the designed SSELF can extract more discriminant features using the designed DL model and can achieve better classification results than the other six novel DL models in terms of small training samples and adequate labelled samples.

Optimizing Soil Moisture Retrieval: Utilizing Compact Polarimetric Features with Advanced Machine Learning Techniques

Soil moisture plays a crucial role in various environmental processes and is essential for agricultural management, hydrological modeling, and climate studies. Synthetic Aperture Radar (SAR) remote sensing presents significant potential for estimating soil moisture due to its ability to operate in all weather conditions and provide day-and-night imaging capabilities. Among the SAR configurations, the Compact Polarimetric (CP) mode has gained increasing interest as it relaxes system constraints, improves coverage, and enhances target information compared to conventional dual polarimetric SAR systems. This paper introduces a novel approach for soil moisture retrieval utilizing machine learning algorithms and CP SAR features. The CP SAR features are derived from a series of RADARSAT Constellation Mission (RCM) CP SAR imagery acquired over Canadian experimental sites equipped with Real-Time In Situ Soil Monitoring for Agriculture (RISMA) stations. This study employs a diverse dataset of compact polarimetric SAR features and corresponding ground truth soil moisture measurements for training and validation purposes. The results of our study achieved a Root Mean Square Error (RMSE) of 6.88% with a coefficient of determination R2 equal to 0.60, which corresponds to a correlation R between true and predicted soil moisture values of 0.75, using optimized Ensemble Learning Regression (ELR) with a decision-tree-based model. These results improved, yielding an RMSE of 5.67% and an R2 equal to 0.73 (R = 0.85), using an optimized Gaussian Process Regression (GPR) model.

Feature fusion method based on local binary graph for PolSAR image classification

AbstractThe goal of this paper is to propose a method to achieve a higher classification rate in Polarimetric Synthetic Aperture Radar (PolSAR) image classification. In our work, PolSAR features are extracted from Convolutional Neural Networks (CNNs) and also Graph Convolutional Networks (GCNs). Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a substantial computational cost, particularly in large‐scale remote sensing (RS) problems. To this end, first of all, we propose a new mini‐batch GCN (called Mini‐GCN), which allows to train large‐scale GCNs in a mini‐batch fashion. More significantly, our designed mini‐GCN is capable of inferring out‐of‐sample data without re‐training networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of PolSAR features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since mini‐GCNs can perform batch‐wise network training (enabling the combination of CNNs and GCNs), we can use the feature fusion strategy. Therefore, in this paper, a local graph‐based fusion method is proposed to couple dimension reduction and feature fusion of the information extracted from the designed CNN and Mini‐GCN. Experimental results on real PolSAR data are very encouraging. Compared to the methods using only single feature and stacking all the features together, the proposed feature fusion method improves the overall classification accuracy on the real PolSAR data sets for more than 5%. Moreover, the experiments conducted on PolSAR datasets, demonstrate the advantages of the used mini‐GCNs over the traditional GCNs and the superiority of the proposed feature fusion method with regards to the single CNN or GCN models.

Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) images contain useful information, which can lead to extensive land cover interpretation and a variety of output products. In contrast to optical imagery, there are several challenges in extracting beneficial features from PolSAR data. Deep learning (DL) methods can provide solutions to address PolSAR feature extraction challenges. The convolutional neural networks (CNNs) and graph convolutional networks (GCNs) can drive PolSAR image characteristics by deploying kernel abilities in considering neighborhood (local) information and graphs in considering long-range similarities. A novel dual-branch fusion of CNN and mini-GCN is proposed in this study for PolSAR image classification. To fully utilize the PolSAR image capacity, different spatial-based and polarimetric-based features are incorporated into CNN and mini-GCN branches of the proposed model. The performance of the proposed method is verified by comparing the classification results to multiple state-of-the-art approaches on the airborne synthetic aperture radar (AIRSAR) dataset of Flevoland and San Francisco. The proposed approach showed 1.3% and 2.7% improvements in overall accuracy compared to conventional methods with these AIRSAR datasets. Meanwhile, it enhanced its one-branch version by 0.73% and 1.82%. Analyses over Flevoland data further indicated the effectiveness of the dual-branch model using varied training sampling ratios, leading to a promising overall accuracy of 99.9% with a 10% sampling ratio.

PolSAR Scene Classification via Low-Rank Constrained Multimodal Tensor Representation

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.

Deep Triplet Complex-Valued Network for PolSAR Image Classification

Recently, convolutional neural network (CNN) has proved itself as a successful deep model and has been successfully utilized in polarimetric synthetic aperture radar (PolSAR) image classification. Most CNN-based models, however, concentrate on the correlation between the pixels and the labels in images and have fewer constraints on interclass or intraclass features. For fully utilizing the polarimetric data, we utilized complex-valued (CV) distance to learn the PolSAR features and proposed a PolSAR classification method by CV distance comparisons. First, we proposed a triplet CV network (TCVN) to learn the CV representations from PolSAR data by maximizing the interclass distance and minimizing intraclass distance. It uses the CV convolution and the CV Euclidean to maintain the phase components and applies the CV-dropout and CV <inline-formula> <tex-math notation="LaTeX">$L_{2}$ </tex-math></inline-formula> parameter regularization to reduce the overfitting and further improve the network performance. Subsequently, CV K nearest neighbor (CV-KNN) computes the distance of the CV representations and groups similar pixels. CV-KNN is well coupled with the TCVN because both of them are based on the Euclidean distance in the complex domain. Compared with the CNN-based methods, the proposed deep metric learning model can simultaneously extract the hierarchical features by comparing the polarimetric resolution cells in the complex domain and maintain the phase component by performing CV convolutions. The effectiveness and the superiorities of CV Euclidean distance in TCVN are demonstrated. Experiments on real PolSAR images illustrate that TCVN can deal with PolSAR data more effectively and achieve comparable performance in the PolSAR image classification even with a smaller data set.

Oil Spill Discrimination by Using General Compact Polarimetric SAR Features

Ocean surveillance is one of the important applications of synthetic aperture radar (SAR). Polarimetric SAR provides multi-channel information and shows great potential for monitoring ocean dynamic environments. Oil spills are a form of pollution that can seriously affect the marine ecosystem. Dual-polarimetric SAR systems are usually used for routine ocean surface monitoring. The hybrid dual-pol SAR imaging mode, known as compact polarimetry, can provide more information than the conventional dual-pol imaging modes. However, backscatter measurements of the hybrid dual-pol mode depend on the transmit wave polarization, which results in lacking consistent interpretation for various compact polarimetric (CP) images. In this study, we will explore the capability of different CP modes for oil spill detection and discrimination. Firstly, we introduce the general CP formalism method to formulate an arbitrary CP backscattered wave, such that the target scattering vector is characterized in the same framework for all CP modes. Then, a recently proposed CP decomposition method is investigated to reveal the backscattering properties of oil spills and their look-alikes. Both intensity and polarimetric features are studied to analyze the optimal CP mode for oil spill observation. Spaceborne polarimetric SAR data sets collected over natural oil slicks and experimental biogenic slicks are used to demonstrate the capability of the general CP mode for ocean surface surveillance.

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.

Polarimetric SAR Image Terrain Classification

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

Polar-Spatial Feature Fusion Learning With Variational Generative-Discriminative Network for PolSAR Classification

Feature learning-based polarimetric synthetic aperture radar (PolSAR) classification model will generally suffer from the challenge of deficient labeled pixels. In this paper, we propose a novel generative-discriminative network for PolSAR polar-spatial feature fusion learning and classification, which comprises of a deep generative network and a discriminative network with their bottom layers shared. With this architecture, it enables to make use of both labeled and unlabeled pixels in a PolSAR image for model learning in a semisupervised way. Moreover, the proposed network imposes a Gaussian random field prior and a conditional random field posterior on the learned fusion features and the output label configuration, respectively. Without the need of the complicated recurrent iterations, our network can still efficiently produce the structured fusion feature as well as a smoothed classification map by involving some auxiliary variables, and it is specifically optimized via variational inference within an alternating direction method of multipliers iteration scheme. Extensive experiments on different benchmark PolSAR imageries demonstrate the effectiveness and superiority of the proposed network. Compared with other state-of-the-art algorithms of PolSAR feature learning and classification, our model can achieve a much better performance in terms of the visual quality of the label map and overall classification accuracy, facilitating the much less labeling pixels.

Marine Oil Spill Detection Based on the Comprehensive Use of Polarimetric SAR Data

As a major marine pollution source, oil spills largely threaten the sustainability of the coastal environment. Polarimetric synthetic aperture radar remote sensing has become a promising approach for marine oil spill detection since it could effectively separate crude oil and biogenic look-alikes. However, on the sea surface, the signal to noise ratio of Synthetic Aperture Radar (SAR) backscatter is usually low, especially for cross-polarized channels. In practice, it is necessary to combine the refined detail of slick-sea boundary derived from the co-polarized channel and the highly accurate crude slick/look-alike classification result obtained based on the polarimetric information. In this paper, the architecture for oil spill detection based on polarimetric SAR is proposed and analyzed. The performance of different polarimetric SAR filters for oil spill classification are compared. Polarimetric SAR features are extracted and taken as the input of Staked Auto Encoder (SAE) to achieve high accurate classification between crude oil, biogenic slicks, and clean sea surface. A post-processing method is proposed to combine the classification result derived from SAE and the refined boundary derived from VV channel power image based on special density thresholding (SDT). Experiments were conducted on spaceborne fully polarimetric SAR images where both crude oil and biogenic slicks were presented on the sea surface.

A contextual-based segmentation of compact PolSAR images using Markov Random Field (MRF) model

ABSTRACTAs the first major step in each object-oriented feature extraction approach, segmentation plays an essential role as a preliminary step towards further and higher levels of image processing. The primary objective of this paper is to illustrate the potential of Polarimetric Synthetic Aperture Radar (PolSAR) features extracted from Compact Polarimetry (CP) SAR data for image segmentation using Markov Random Field (MRF). The proposed method takes advantage of both spectral and spatial information to segment the CP SAR data. In the first step of the proposed method, k-means clustering was applied to over-segment the image using the appropriate features optimally selected using Genetic Algorithm (GA). As a similarity criterion in each cluster, a probabilistic distance was used for an agglomerative hierarchical merging of small clusters into an appropriate number of larger clusters. In the agglomerative clustering approach, the estimation of the appropriate number of clusters using the data log-likelihood algorithm differs depending on the distance criterion used in the algorithm. In particular, the Wishart Chernoff distance which is independent of samples (pixels) tends to provide a higher appropriate number of clusters compared to the Wishart test statistic distance. This is because the Wishart Chernoff distance preserves detailed data information corresponding to small clusters. The probabilistic distance used in this study is Wishart Chernoff distance which evaluates the similarity of clusters by measuring the distance between their complex Wishart probability density functions. The output of this step, as the initial segmentation of the image, is applied to a Markov Random Field model to improve the final segmentation using vicinity information. The method combines Wishart clustering and enhanced initial clusters in order to access the posterior MRF energy function. The contextual image classifier adopts the Iterated Conditional Mode (ICM) approach to converge to a local minimum and represent a good trade-off between segmentation accuracy and computation burden. The results showed that the PolSAR features extracted from CP mode can provide an acceptable overall accuracy in segmentation when compared to the full polarimetry (FP) and Dual Polarimetry (DP) data. Moreover, the results indicated that the proposed algorithm is superior to the existing image segmentation techniques in terms of segmentation accuracy.

Unsupervised Fine Land Classification Using Quaternion Autoencoder-Based Polarization Feature Extraction and Self-Organizing Mapping

We propose an unsupervised polarimetric synthetic aperture radar (PolSAR) land classification system consisting of a series of two unsupervised neural networks, namely, a quaternion autoencoder and a quaternion self-organizing map (SOM). Most of the existing PolSAR land classification systems use a set of feature information that humans designed beforehand. However, such methods will face limitations in the near future when we expect classification into a large number of land categories recognizable to humans. By using a quaternion autoencoder, our proposed system extracts feature information based on the natural distribution of PolSAR features. In this paper, we confirm that the information necessary for land classification is extracted as the features while noise is filtered. Then, we show that the extracted features are classified by the quaternion SOM in an unsupervised manner. As a result, we can discover even new and more detailed land categories. For example, town areas are divided into residential areas and factory sites, and grass areas are subcategorized into furrowed farmlands and flat grass areas. We also examine the realization of topographic mapping of the features in the SOM space.

Fisher Linear Discriminant Analysis of coherency matrix for wetland classification using PolSAR imagery

Wetlands provide a wide variety of environmental services globally and detailed wetland inventory maps are always necessary to determine the conservation strategies and effectively monitor these productive ecosystems. During the last two decades, satellite remote sensing data have been extensively used for wetland mapping and monitoring worldwide. Polarimetric Synthetic Aperture Radar (PolSAR) imagery is a complex and multi-dimensional data, which has high potential to discriminate different land cover types. However, despite significant improvements to both information content in PolSAR imagery and advanced classification approaches, wetland classification using PolSAR data may not provide acceptable classification accuracy. This is because classification accuracy using PolSAR imagery strongly depends on the polarimetric features that are incorporated into the classification scheme. In this paper, a novel feature weighting method for PolSAR imagery is proposed to increase the classification accuracy of complex land cover. Specifically, a new coefficient is determined for each element of the coherency matrix by integration of Fisher Linear Discriminant Analysis (FLDA) and physical interpretation of the PolSAR data. The proposed methodology was applied to multi-temporal polarimetric C-band RADARSAT-2 data in the Avalon Peninsula, Deer Lake, and Gros Morne pilot sites in Newfoundland and Labrador, Canada. Different combinations of input features, including original PolSAR features, polarimetric decomposition features, and modified coherency matrix were used to evaluate the capacity of the proposed method for improving the classification accuracy using the Random Forest (RF) algorithm. The results demonstrated that the modified coherency matrix obtained by the proposed method, Van Zyl, and Freeman-Durden decomposition features were the most important features for wetland classification. The fine spatial resolution maps obtained in this study illustrate the distribution of terrestrial and aquatic habitats for the three wetland pilot sites in Newfoundland using the modified coherency matrix and other polarimetric features. The classified maps provide valuable baseline data for effectively monitoring climate and land cover changes, and support further scientific research in this area.

An Efficient Marine Oil Spillage Identification Scheme Based on an Improved Active Contour Model Using Fully Polarimetric SAR Imagery

Oil spillage pollution results in damages to marine and coastal environments and ecosystems at all levels. Due to the distinct advantages of fully polarimetric synthetic aperture radar (Pol-SAR), it has been widely employed to improve oil spillage event observations. In this paper, with the aim of enhancing ocean oil spillage identification, an improved scheme was proposed, which was mainly based on an active contour model (ACM), with a special emphases on choosing an optimal initial box boundary for the ACM model, and a noise suppressing process. In this proposed scheme, the ACM initial box boundary was chosen to be the median level contour of the imagined mountain if regarding image grey values as elevations. Meanwhile, following Lee filter operator, a Gaussian smooth operator was hired to further weaken the speckle noise, thereby making the evolution of ACM more stable. Three sets of RADARSAT-2 fully Pol-SAR data were used to test of the proposed method. In addition, the current study achieved the first complete comparison of the identification abilities of the ten most common recently used fully Pol-SAR features for oil spills. The experimental results show: 1) The features of H; v; span; P; ${\text{M}}_{33}$ ; and $\rho $ possessed good distinguishable abilities for oil spillage detection in sea water. Specially, features span and v outperformed other Pol-SAR features with regard to the elaborate distinguishing identifications of small patches of oil spill objects from other small objects, such as oil platforms or ships; 2) An appropriate setting of the initial box boundary of the ACM was able to accelerate the global search, and eventually led to improvements in the accuracy of the oil spill identification, while simultaneously reducing the computational time; 3) The effective noise suppression was confirmed to be very necessary, guaranteeing stability of the ACM evolution. When compared with other traditional methods, the proposed improved scheme was found to be more effective in the overall identification accuracy (99.8%).

Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images

Polarimetric synthetic aperture radar (SAR) remote sensing provides an outstanding tool in oil spill detection and classification, for its advantages in distinguishing mineral oil and biogenic lookalikes. Various features can be extracted from polarimetric SAR data. The large number and correlated nature of polarimetric SAR features make the selection and optimization of these features impact on the performance of oil spill classification algorithms. In this paper, deep learning algorithms such as the stacked autoencoder (SAE) and deep belief network (DBN) are applied to optimize the polarimetric feature sets and reduce the feature dimension through layer-wise unsupervised pre-training. An experiment was conducted on RADARSAT-2 quad-polarimetric SAR image acquired during the Norwegian oil-on-water exercise of 2011, in which verified mineral, emulsions, and biogenic slicks were analyzed. The results show that oil spill classification achieved by deep networks outperformed both support vector machine (SVM) and traditional artificial neural networks (ANN) with similar parameter settings, especially when the number of training data samples is limited.

Ocean Oil Spill Classification with RADARSAT-2 SAR Based on an Optimized Wavelet Neural Network

Oil spill accidents from ship or oil platform cause damage to marine and coastal environment and ecosystems. To monitor such spill events from space, fully polarimetric (Pol-SAR) synthetic aperture radar (SAR) has been greatly used in improving oil spill observation. Aiming to promote ocean oil spill classification accuracy, we developed a new oil spill identification method by combining multiple fully polarimetric SAR features data with an optimized wavelet neural network classifier (WNN). Two sets of RADARSAT-2 fully polarimetric SAR data are applied to test the validity of the developed method. The experimental results show that: (1) the convergence ability of optimized WNN can be enhanced, improving overall classification accuracy of ocean oil spill, in comparison to the classification results based on a common un-optimized WNN classifier; and (2) the joint use of the multiple fully Pol-SAR features as the inputs of the classifier can achieve better classification result than that only with single fully Pol-SAR feature. The developed method can improve classification accuracy by 4.96% and 7.75%, compared with the classification results with un-optimized WNN and only with one single fully polarimetric SAR feature. The classification overall accuracy based on the proposed approach can reach 97.67%. Experimental results have proven that the proposed approach is effective and applicable to classify the ocean oil spill.

Scattering Characteristics of X-, C- and L-Band PolSAR Data Examined for the Tundra Environment of the Tuktoyaktuk Peninsula, Canada

In this study, polarimetric Synthetic Aperture Radar (PolSAR) data at X-, C- and L-Bands, acquired by the satellites: TerraSAR-X (2011), Radarsat-2 (2011), ALOS (2010) and ALOS-2 (2016), were used to characterize the tundra land cover of a test site located close to the town of Tuktoyaktuk, NWT, Canada. Using available in situ ground data collected in 2010 and 2012, we investigate PolSAR scattering characteristics of common tundra land cover classes at X-, C- and L-Bands. Several decomposition features of quad-, co-, and cross-polarized data were compared, the correlation between them was investigated, and the class separability offered by their different feature spaces was analyzed. Certain PolSAR features at each wavelength were sensitive to the land cover and exhibited distinct scattering characteristics. Use of shorter wavelength imagery (X and C) was beneficial for the characterization of wetland and tundra vegetation, while L-Band data highlighted differences of the bare ground classes better. The Kennaugh Matrix decomposition applied in this study provided a unified framework to store, process, and analyze all data consistently, and the matrix offered a favorable feature space for class separation. Of all elements of the quad-polarized Kennaugh Matrix, the intensity based elements K0, K1, K2, K3 and K4 were found to be most valuable for class discrimination. These elements contributed to better class separation as indicated by an increase of the separability metrics squared Jefferys Matusita Distance and Transformed Divergence. The increase in separability was up to 57% for Radarsat-2 and up to 18% for ALOS-2 data.

Polarimetric SAR Feature Extraction With Neighborhood Preservation-Based Deep Learning

As an advanced nonlinear technique, deep learning, which is based on deep neural networks (DNNs), has attracted considerable attentions. In this paper, we propose a novel neighborhood preserved deep neural network (NPDNN) for polarimetric synthetic aperture radar feature extraction and classification. The spatial relation between pixels is exploited by a jointly weighting strategy. Not only the spatial neighbors but also the pixels in the same superpixel are utilized to weight each pixel. This strategy maintains the spatial dependence leading to superior homogeneity of the terrains without extra computational memory. Moreover, a few labeled samples and their nearest neighbors are employed to train the multilayer NPDNN, which preserves the local structure and reduces the number of labeled samples for classification. Experimental results on synthesized and real PolSAR data show that the proposed NPDNN can improve the classification accuracy compared with state-of-the-art DNNs despite a few input samples.