A novel group squeeze excitation sparsely connected convolutional networks for SAR target classification

Synthetic Aperture Radar (SAR) images are prone to be contaminated by noise, which makes it very difficult to perform target recognition in SAR images. Inspired by great success of very deep convolutional neural networks (CNNs), this paper proposes a robust feature extraction method for SAR image target classification by adaptively fusing effective features from different CNN layers. First, YOLOv4 network is fine-tuned to detect the targets from the respective MF SAR target images. Second, a very deep CNN is trained from scratch on the moving and stationary target acquisition and recognition (MSTAR) database by using small filters throughout the whole net to reduce the speckle noise. Besides, using small-size convolution filters decreases the number of parameters in each layer and, therefore, reduces computation cost as the CNN goes deeper. The resulting CNN model is capable of extracting very deep features from the target images without performing any noise filtering or pre-processing techniques. Third, our approach proposes to use the multi-canonical correlation analysis (MCCA) to adaptively learn CNN features from different layers such that the resulting representations are highly linearly correlated and therefore can achieve better classification accuracy even if a simple linear support vector machine is used. Experimental results on the MSTAR dataset demonstrate that the proposed method outperforms the state-of-the-art methods.

In this review paper, several studies and researches were surveyed for assisting future researchers to identify available techniques in the field of classification of Synthetic Aperture Radar (SAR) images. SAR images are becoming increasingly important in a variety of remote sensing applications due to the ability of SAR sensors to operate in all types of weather conditions, including day and night remote sensing for long ranges and coverage areas. Its properties of vast planning, search, rescue, mine detection, and target identification make it very attractive for surveillance and observation missions of Earth resources. With the increasing popularity and availability of these images, the need for machines has emerged to enhance the ability to identify and interpret these images effectively. This is due to the fact that SAR image processing requires the formation of an image from the measured radar scatter returns, followed by a treatment to discover and define the image's composition. After reviewing several previous studies that succeeded in achieving a classification of SAR images for specific goals, it became obvious that they could be generalized to all types of SAR images. The most prominent use of Convolutional Neural Networks (CNN) was successful in extracting features from the images and training the neural network to analyze and classify them into classes according to these features. The dataset used in this model was obtained from the Moving and Stationary Target Acquisition and Recognition (MSTAR) database, which consists of a set of SAR images of military vehicles, for which the application of the CNN approach achieved a final accuracy of 97.91% on ten different classes.

This paper proposes an automatic target recognition (ATR) method for synthetic aperture radar (SAR) images based on information-decoupled representation. A typical SAR image of a ground target can be divided into three parts: target region, shadow and background. From the aspect of SAR target recognition, the target region and shadow contain discriminative information. However, they also include some confusing information because of the similarities of different targets. The background mainly contains redundant information, which has little contribution to the target recognition. Because the target segmentation may impair the discriminative information in the target region, the relatively simpler shadow segmentation is performed to separate the shadow region for information decoupling. Then, the information-decoupled representations are generated, i.e., the target image, shadow and original image. The background is retained in the target image, which represents the coupling of target backscattering and background. The original image and generated target image are classified using the sparse representation-based classification (SRC). Then, their classification results are combined by a score-level fusion for target recognition. The shadow image is not used because of its lower discriminability and possible segmentation errors. To evaluate the performance of the proposed method, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under both standard operating condition (SOC) and various extended operating conditions (EOCs). The proposed method can correctly classify 10 classes of targets with the percentage of correct classification (PCC) of 94.88% under SOC. With the PCCs of 93.15% and 75.03% under configuration variance and 45° depression angle, respectively, the superiority of the proposed is demonstrated in comparison with other methods. The robustness of the proposed method to both uniform and nonuniform shadow segmentation errors is validated with the PCCs over 93%. Moreover, with the maximum average precision of 0.9580, the proposed method is more effective than the reference methods on outlier rejection.

Automatic targets recognition (ATR) for synthetic aperture radar (SAR) image is very important. ATR can be used in traffic management, national frontier safety, and so on. Traditional algorithms for SAR ATR is composed of extraction features and training classifier. The features are essential for the classification accuracy. However, choosing good features by hand is a hard task. The deep convolutional neural networks (CNNs) which can learn features automatically have got a great performance in natural images. However, the CNNs have many parameters and need a lot of data to train such networks. The remote-sensing data of SAR is limited. Then, the authors need a simple network which needs not much data and easy to train. The principal component analysis network (PCANet) is a shallow network that performs well in the recognition task and needs no hand features choosing. Though this network has produced a wide application in the natural images, it is rarely used in the SAR images. The experimental result of the moving and stationary target acquisition and recognition (MSTAR) dataset shows that the PCANet can achieve over 99% accuracy on ten-class targets. This result is better than traditional algorithms and is very close to the results of deep-learning methods.

Synthetic aperture RADAR (SAR) is an emerging technology primarily used for high resolution ground mapping. SAR's capability to perform under adverse weather conditions, day or night makes it advantageous for many civilian and military applications. It is an active imaging system and inherently suffers from speckle noise, which is multiplicative in nature. Speckle noise originates from the interferen'ce of the coherent wave fronts associated with the reflected signal. The quality of SAR images is significantly degraded by this interference. Conventional intensity-based image processing techniques do not perform well for SAR images because of multiplicative nature of speckle. A variety of suggested image segmentation techniques suitable for SAR images have been analysed in this paper. The paper performs comparative analysis of image segmentation techniques that are based on different features of the images and are specialized to perform on SAR images. Experiments are performed on synthetically generated images and real SAR images obtained from Moving and Stationary Target Acquisition and Recognition (MSTAR) public database.

Thanks to the availability of large-scale data, deep Convolutional Neural Networks (CNNs) have witnessed success in various applications of computer vision. However, the performance of CNNs on Synthetic Aperture Radar (SAR) image classification is unsatisfactory due to the lack of well-labeled SAR data, as well as the differences in imaging mechanisms between SAR images and optical images. Therefore, this paper addresses the problem of SAR image classification by employing the Generative Adversarial Network (GAN) to produce more labeled SAR data. We propose special GANs for generating SAR images to be used in the training process. First, we incorporate the quadratic operation into the GAN, extending the convolution to make the discriminator better represent the SAR data; second, the statistical characteristics of SAR images are integrated into the GAN to make its value function more reasonable; finally, two types of parallel connected GANs are designed, one of which we call PWGAN, combining the Deep Convolutional GAN (DCGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP) together in the structure, and the other, which we call CNN-PGAN, applying a pre-trained CNN as a discriminator to the parallel GAN. Both PWGAN and CNN-PGAN consist of a number of discriminators and generators according to the number of target categories. Experimental results on the TerraSAR-X single polarization dataset demonstrate the effectiveness of the proposed method.

Images from different aspect views for one target, known as multiple views, are widely applied to improve synthetic aperture radar (SAR) target recognition. However, most of existing multi-view methods have strict constraint on the angle interval among multiple views. In this paper, a new multiview fusion method free from interval limitation using expectation maximization (EM) is explored for SAR image classification. Firstly, we apply convolutional neural network (CNN) to extract features effectively owning to its powerful ability of feature learning and then obtain the classification probability. Secondly, Multi-view Label Set (MLS) is automatically constructed from multiple views according to the probability and finally we use EM algorithm to classify SAR images intelligently. It is worth noting that the proposed method can be used flexibly according to the number of perspectives obtained and without angle interval constraint among multiple views. Experiments demonstrate that the proposed method has better recognition performance than some state-of-the-art methods on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset.

Synthetic aperture radar (SAR) image target detection and recognition (SAR-TDR) tasks have become research hot spots in the remote sensing application. These targets include ships, vehicles, aircraft, oil tanks, bridges, and so on. However, with the rapid development of SAR technology and increasingly complex electromagnetic environment, complex characteristics of SAR images bring severe challenges to the accurate SAR-TDR via traditional physical models or manual feature-extraction-based machine learning methods. In recent years, deep learning (DL), as a powerful automatic feature extraction algorithm, has been widely used in the computer vision domain. More specifically, DL has also been introduced into the SAR-TDR tasks and has effectively achieved good performance in terms of accuracy, real-time processing, etc. With the rapid development of DL, SAR image processing, and practical requirements of SAR-TDR in civilian and military domains, it is crucial to conduct a systematic survey on SAR-TDR in the past few years. In this survey article, we mainly conduct a systematic overview of DL-based SAR-TDR literature on two tasks, i.e., target recognition (e.g., ground vehicles, ships, and aircraft) and target detection (e.g., ships, aircraft, change detection, sea surface oil spills, and oil tanks). More specifically, our related works about these topics are also presented to verify the effectiveness of DL-based methods. First, several DL methods (e.g., convolutional neural networks, recurrent neural networks, autoencoders, and generative adversarial networks), commonly used in SAR-TDR, are briefly introduced. Then, a systematic review of DL-based SAR-TDR (including our related works) is presented. Finally, the current challenges and future possible research directions are deeply analyzed and discussed.

Convolutional Neural Network (CNN) has shown great potential for structural information extraction, however, Synthetic Aperture Radar (SAR) image interpretation via CNN, is still a challenging task due to the pixel- to- pixel variation nature of SAR signal. In this paper, a pattern strengthened deep model for SAR image classification is presented. The main idea underlying this method is to strengthen (or sharpen) the salient patterns contained in SAR image while attenuate the random variation, so as to leverage the enormous potential of deep model. To achieve this goal, max pooling is elaborately designed to form a pattern strengthened deep model. The experimental results on two SAR datasets show that the proposed method increases the classification accuracy by 4.91% and 4.64% compared with the typical CNN, and indicate our innovative attempt is promising for SAR image classification in the case of limited training data.

This paper proposes a new approach for Synthetic Aperture Radar (SAR) image segmentation. Segmenting SAR images can be challenging because of the blurry edges and the high speckle. The segmentation proposed is based on a machine learning technique. Gaussian Mixture Models (GMMs) were already used to segment images in the visual field and are here adapted to work with single channel SAR images. The segmentation suggested is designed to be a first step towards feature and model based classification. The recall rate is the most important as the goal is to retain most target's features. A high recall rate of 88%, higher than for other segmentation methods on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, was obtained. The next classification stage is thus not affected by a lack of information while its computation load drops. With this method, the inclusion of disruptive features in models of targets is limited, providing computationally lighter models and a speed up in further classification as the narrower segmented areas foster convergence of models and provide refined features to compare. This segmentation method is hence an asset to template, feature and model based classification methods. Besides this method, a comparison between variants of the GMMs segmentation and a classical segmentation is provided.

Convolutional neural networks (CNNs) have been applied to learn spatial features for high-resolution (HR) synthetic aperture radar (SAR) image classification. However, there has been little work on integrating the unique statistical distributions of SAR images which can reveal physical properties of terrain objects, into CNNs in a supervised feature learning framework. To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features. First, to extract more effective spatial features from SAR images, a new deep spatial context encoder network (DSCEN) is proposed, which is a lightweight structure and can be effectively trained with a small number of samples. Meanwhile, to enhance the diversity of statistics, the nonstationary joint statistical model (NS-JSM) is adopted to form the global statistical features. Specifically, SAR images are transformed into the Gabor wavelet domain and the produced multi-subbands magnitudes and phases are modeled by the log-normal and uniform distribution. The covariance matrix is further utilized to capture the inter-scale and intra-scale nonstationary correlation between the statistical subbands and make the joint statistical features more compact and distinguishable. Considering complementary advantages, a feature fusion network (Fusion-Net) base on group compression and smooth normalization is constructed to embed the statistical features into the spatial features and optimize the fusion feature representation. As a result, our model can learn the discriminative features and improve the final classification performance. Experiments on four HR SAR images validate the superiority of the proposed method over other related algorithms.

The convolutional neural network (CNN) has shown great potential in many fields; however, transferring this potential to synthetic aperture radar (SAR) image interpretation is still a challenging task. The coherent imaging mechanism causes the SAR signal to present strong fluctuations, and this randomness property calls for many degrees of freedom (DoFs) for the SAR image description. In this paper, a statistics learning network (SLN) based on the quadratic form is presented. The statistical features are expected to be fitted in the SLN for SAR image representation. (i) Relying on the quadratic form in linear algebra theory, a quadratic primitive is developed to comprehensively learn the elementary statistical features. This primitive is an extension to the convolutional primitive that involves both nonlinear and linear transformations and provides more flexibility in feature extraction. (ii) With the aid of this quadratic primitive, the SLN is proposed for the classification task. In the SLN, different types of statistics of SAR images are automatically extracted for representation. Experimental results on three datasets show that the SLN outperforms a standard CNN and traditional texture-based methods and has potential for SAR image classification.

In single band and single polarized synthetic aperture radar (SAR) images, the information is limited to intensity and texture only and it is very difficult to interpret such SAR images without any a priori information. For unsupervised classification of SAR images, M-band wavelet decomposition is performed on the SAR image and sub-band selection on the basis of energy levels is applied to improve the classification results since sparse representation of sub-bands degrades the performance of classification. Then, textural features are obtained from selected sub-bands and integrated with intensity features. An adaptive neuro-fuzzy algorithm is used to improve computational efficiency by extracting significant features. K-means classification is performed on the extracted features and land features are labeled. This classification algorithm involves user defined parameters. To remove the user dependency and to obtain maximum achievable classification accuracy, an algorithm is developed in this paper for classification accuracy in terms of the parameters involved in the segmentation process. This is very helpful to develop the automated land-cover monitoring system with SAR, where optimized parameters are to be identified only once and these parameters can be applied to SAR imagery of the same scene obtained year after year. A single band, single polarized SAR image is classified into water, urban and vegetation areas using this method and overall classification accuracy is obtained in the range of 85.92%–93.70% by comparing with ground truth data.

The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms.

Identifying the aspect for a given target is an important issue in synthetic aperture radar (SAR) image interpretation. A new SAR target aspect identification method based on machine learning theory is proposed in this paper. First, the aspect angles of the SAR target are discretized, and the spatial relationships of the neighborhoods of the SAR target samples are established. Then an optimal linear mapping is solved based on the proposed subspace aspect discriminant analysis. The samples will be projected into a low-dimensional space and be of a better aspect identifiability than in their original space. Finally, the projected samples are fed into a multilayer neural network, and the aspects of the SAR targets will be indicated. Experimental results have shown the superiority of the proposed method based on the moving and stationary target acquisition and recognition (MSTAR) data set.