Target Aspect Identification in SAR Image: A Machine Learning Approach

ABSTRACTAutomatic Target Recognition (ATR) based on Synthetic Aperture Radar (SAR) images plays a key role in military applications. However, there are difficulties with this traditional recognition method. Principally, it is a challenge to design robust features and classifiers for different SAR images. Although Convolutional Neural Networks (CNNs) are very successful in many image classification tasks, building a deep network with limited labeled data remains a problem. The topologies of CNNs like the fully connected structure will lead to redundant parameters and the negligence of channel-wise information flow. A novel CNNs approach, called Group Squeeze Excitation Sparsely Connected Convolutional Networks (GSESCNNs), is therefore proposed as a solution. The group squeeze excitation performs dynamic channel-wise feature recalibration with less parameters than squeeze excitation. Sparsely connected convolutional networks are a more efficient way to operate the concatenation of feature maps from different layers. Experimental results on Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR images, demonstrate that this approach achieves, at 99.79%, the best prediction accuracy, outperforming the most common skip connection models, such as Residual Networks and Densely Connected Convolutional Networks, as well as other methods reported in the MSTAR dataset.

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.

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.

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.

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.

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.

The local structure feature of the target in synthetic aperture radar (SAR) image and the inner correlation among multiple SAR images of the same target can effectively improve the recognition performance. In order to utilize these two kinds of information, we propose the multi-view tensor sparse representation (MTSR) model for SAR target recognition. In the proposed model, the SAR image is treated as tensor and represented by the dictionaries on each dimension of the image and corresponding sparse representation coefficient tensor (SRCT). For multi-view SAR images of one target, we design the proposed model by letting the SRCTs of those images have the same structure, which means that the non-zero elements of those SRCTs have the same coordinates. In order to solve the proposed model, we propose the joint tensor orthogonal matching pursuit (JT-OMP) algorithm to calculate the SRCTs of multiple views. JT-OMP ensures that all the SRCTs have the same structure by looking for the atoms of dictionaries that can contribute the total maximum energy for all multi-view tensors in every iteration. To achieve recognition, we construct two dictionaries for each class and compare the total sparse representation error of multi-view SAR images in each class. The experiments conducted on the moving and stationary target acquisition recognition database (MSTAR) verify the performance of the proposed algorithm.

Synthetic aperture radar (SAR) target recognition under extended operating conditions (EOCs) is a challenging problem due to the complex application environment, especially for insufficient target variations and corrupted SAR images in the training samples. This paper proposes a new strategy to solve these problems for target recognition. The SAR images are firstly characterized by multi-scale components of monogenic signal. The generated monogenic features are decomposed to learn a class dictionary and a shared dictionary, which represent the possible intraclass variations information and the common information, respectively. Moreover, a sparse representation of the class dictionary and a dense representation of the shared dictionary are jointly employed to represent a query sample for classification. The validity of the proposed strategy is demonstrated with multiple comparative experiments on moving and stationary target acquisition and recognition (MSTAR) database.

The usage of a hypersonic platform for remote sensing application has promising prospects, especially for hypersonic platform-borne synthetic aperture radar (SAR) imaging. However, the high-speed of hypersonic platform will lead to extreme friction between the platform and air, which will cause the ionization of air. The ionized gas forms the plasma sheath wrapped around the hypersonic platform. The plasma sheath will severely affect the propagation of SAR signal and further affect the SAR imaging. Therefore, hypersonic platform-borne SAR imaging should be studied from a physical perspective. In this paper, hypersonic platform-borne SAR imaging under plasma sheath is analyzed. The SAR signal propagation in plasma sheath is computed using scatter matrix method. The proposed SAR signal model is verified by using a ground experiment system. Moreover, the effect of attenuation caused by plasma sheath on SAR imaging is studied under different SAR parameters and plasma sheath. The result shows that attenuation caused by plasma sheath will degrade the SAR imaging quality and even cause the point and area targets to be submerged into the noise. The real SAR images under plasma sheath also illustrate this phenomenon. Furthermore, by studying imaging results under different SAR and plasma parameters, it can be concluded that the severe degradation of SAR imaging quality appears at condition of high plasma sheath electron density and low SAR carrier frequency. The work in this paper will be beneficial for the study of hypersonic platform-borne SAR imaging and design of hypersonic SAR imaging systems in the future.

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.

Few-shot SAR automatic target recognition based on Conv-BiLSTM prototypical network

Reliable automatic target segmentation in Synthetic Aperture Radar (SAR) imagery has played an important role in the SAR fields. Different from the traditional methods, Spectral Residual (SR) and CFAR detector, with the recent advancements in machine learning theory, new methods based on machine learning show better performance in SAR target segmentation. In this paper, we proposed a deep deformable residual learning network for target segmentation, which attempts to preserve the precise contour of the target. The deformable convolutional layers and residual learning block are applied in this technique, which could extract and preserve the geometric information of the target as much as possible. The proposed method is evaluated based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and the experimental results have shown the superiority of the proposed network for the precise segmentation of the target.

It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.

In general, synthetic aperture radar (SAR) imaging and image processing are two sequential steps in SAR image processing. Due to the large size of SAR images, most image processing algorithms require image segmentation before processing. However, the existence of speckle noise in SAR images, as well as poor contrast and the uneven distribution of gray values in the same target, make SAR images difficult to segment. In order to facilitate the subsequent processing of SAR images, this paper proposes a new method that combines the back-projection algorithm (BPA) and a first-order gradient operator to enhance the edges of SAR images to overcome image segmentation problems. For complex-valued signals, the gradient operator was applied directly to the imaging process. The experimental results of simulated images and real images validate our proposed method. For the simulated scene, the supervised image segmentation evaluation indexes of our method have more than 1.18%, 11.2% and 11.72% improvement on probabilistic Rand index (PRI), variability index (VI), and global consistency error (GCE). The proposed imaging method will make SAR image segmentation and related applications easier.

We propose an algorithm for detecting inshore ship targets in synthetic aperture radar (SAR) images, named MFF-YOLO (You Only Look Once of multivariate feature fusion). On the basis of YOLOv5, the weakly supervised saliency feature module is constructed to enhance the feature texture under the supervision of weakly supervised labels, extract the multi-scale saliency target features, solve the problem that it is difficult to locate potential target regions in the SAR image with insufficient inshore target features, and improve the recall rate by 3.2%; the land–sea feature module is constructed to extract the land–sea distribution features of the image, suppress the land area features, solve the problem of high false alarm rate caused by land clutter in inshore scenes, and improve the precision rate by 3.2%; construct multivariate feature fusion module to fuse the target features, weakly supervised saliency features and land–sea distribution features in multiple scales; and use adaptive thresholding to suppress irrelevant noise to obtain target features enhanced by multivariate features fusion, which solves the problems of insufficient target available information and irrelevant noise interference in SAR images, improves AP0.5 by 3.3%, and improves F1 measure by 2%. This algorithm achieves a precision of 88.3% on the inshore portion of the high-resolution SAR image dataset, a recall of 77.5%, an AP0.5 of 81.6%, and an F1 of 0.825, demonstrating superior detection performance over other comparative algorithms, with good accuracy and robustness.