Moving And Stationary Target Acquisition And Recognition Research Articles

Selecting pseudo supervision for unsupervised domain adaptive SAR target classification

In recent years, deep learning has brought significant progress for the problem of synthetic aperture radar (SAR) target classification. However, SAR image characteristics are highly sensitive to the change of imaging conditions. The inconsistency of imaging parameters (especially the depression angle) leads to the distribution shift between the training and test data and severely deteriorates the classification performance. To address this problem, in this paper we propose an unsupervised domain adaptation method based on selective pseudo-labelling for SAR target classification. Our method directly trains a deep model using the data from the target domain by generating pseudo-labels in the target domain. The key idea is to iteratively select valuable samples from the target domain and optimize the classifier. In each iteration, the breaking ties (BT) criterion is adopted to select the best samples with the highest scores of relative confidence. Besides, to avoid error accumulation in the iterative process, class confusion regularization is used to improve the accuracy of pseudo-labelling. Our method is compared with state-of-the-art methods, including supervised classification and unsupervised domain adaptation methods, over the moving and stationary target acquisition and recognition (MSTAR) dataset. The experimental results demonstrate that the proposed method can achieve better classification performance, especially when the difference of depression angles of the source and target domain images is large. Besides, our method also shows its superiority under limited-sample conditions.

One-vs-All Convolutional Neural Networks for Synthetic Aperture Radar Target Recognition

Abstract Convolutional Neural Networks (CNN) have been widely utilized for Automatic Target Recognition (ATR) in Synthetic Aperture Radar (SAR) images. However, a large number of parameters and a huge training data requirements limit CNN’s use in SAR ATR. While previous works have primarily focused on model compression and structural modification of CNN, this paper employs the One-Vs-All (OVA) technique on CNN to address these issues. OVA-CNN comprises several Binary classifying CNNs (BCNNs) that act as an expert in correctly recognizing a single target. The BCNN that predicts the highest probability for a given target determines the class to which the target belongs. The evaluation of the model using various metrics on the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark dataset illustrates that the OVA-CNN has fewer weight parameters and training sample requirements while exhibiting a high recognition rate.

ST-PN: A Spatial Transformed Prototypical Network for Few-Shot SAR Image Classification

Few-shot learning has achieved great success in computer vision. However, when applied to Synthetic Aperture Radar Automatic Target Recognition (SAR-ATR), it tends to demonstrate a bad performance due to the ignorance of the differences between SAR images and optical ones. What is more, the same transformation on both images may cause different results, even some unexpected noise. In this paper, we propose an improved Prototypical Network (PN) based on Spatial Transformation, also known as ST-PN. Cascaded after the last convolutional layer, a spatial transformer module implements a feature-wise alignment rather than a pixel-wise one, so more semantic information can be exploited. In addition, there is always a huge divergence even for the same target when it comes to pixel-wise alignment. Moreover, it reduces computational cost with fewer parameters of the deeper layer. Here, a rotation transformation is used to reduce the discrepancies caused by different observation angles of the same class. Thefinal comparison of four extra losses indicates that a single cross-entropy loss is good enough to calculate the loss of distances. Our work achieves state-of-the-art performance on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset.

A multi-view SAR target recognition method using feature fusion and joint classification

ABSTRACT To handle synthetic aperture radar (SAR) image target recognition problem, a multi-view method is proposed. For the multi-view SAR images be recognized, they are first clustered based on the correlation coefficients and divided into several view sets. Afterwards, for the view set containing two or more images, the multiset canonical correlation analysis (MCCA) is employed to fuse them as a single feature vector. For the view set with a single image, its corresponding feature vector is directly used. Finally, the joint sparse representation is used to characterize and classify the feature vectors from different view sets and determine the target label of the multi-view SAR images. Experiments and analysis on the moving and stationary target acquisition and recognition (MSTAR) dataset show that the proposed method can achieve an average recognition rate of 99.42% for 10 types of targets under the standard operating condition (SOC). Its performance is also better than several reference methods under the extended operating conditions (EOC) including noise interference and target occlusion.

Learning From Reliable Unlabeled Samples for Semi-Supervised SAR ATR

Synthetic aperture radar automatic target recognition (SAR ATR) has been suffering from the insufficient labeled samples as the annotation of SAR data is time-consuming. Thus, adding unlabeled samples into training has attracted the attention of researchers. In this letter, a semi-supervised method based on consistency criterion, domain adaptation and Top-k loss is proposed to alleviate the need for labeled samples. According to consistency criterion that samples generated by the weak and strong augmentations from the same sample belong to the same category, we use the weak and strong augmented unlabeled samples to predict pseudo labels and train the model respectively. Then, to overcome the issue caused by the domain discrepancy between labeled and unlabeled samples especially when labeled samples concentrate on a narrow azimuth range, a domain adaptation component is designed to reduce their discrepancy. Besides, considering the incorrect pseudo labels will hamper the model training, the Top-k loss is adopted for unlabeled samples to mitigate the negative effects. The experimental results on Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate the superiority of our method in semi-supervised SAR ATR. Specifically, we achieve about a 14.29% improvement in recognition accuracy compared to the state-of-the-art when the labeled samples concentrate on a narrow azimuth range.

Novel Loss Function in CNN for Small Sample Target Recognition in SAR Images

Studying synthetic aperture radar automatic target recognition (SAR-ATR) under small samples can get rid of the sample dependence and improve the practicality of the deep learning model. However, the deep learning model trained with small samples is prone to overfitting. In order to solve the above problem of SAR-ATR, a novel loss function called limited data loss function (LDLF) is proposed in this letter, which organically combines the cross-entropy loss function and the contrastive loss function. The LDLF supervises the convolutional neural network (CNN) to learn strong generalization performance features. Then, for simplifying the training and testing of CNN based on LDLF, a feature-combined module is proposed. This module makes up for the limitation that the model input must be image pairs and simplifies the testing process of CNN. Experiments on moving and stationary target acquisition and recognition (MSTAR) datasets show that the proposed loss function is better than the cross-entropy loss function and superior to the existing methods in synthetic aperture radar (SAR) image target recognition using small samples data.

SAR Target Classification Using the Multikernel-Size Feature Fusion-Based Convolutional Neural Network

It is well-known that the convolutional neural network (CNN) is an effective method for synthetic aperture radar (SAR) target classification. In the convolutional layer of CNN, convolutional kernels of different sizes can extract different feature information of the target. The small-size kernel can extract the local texture feature information, and the large-size kernel can extract the global contour feature information. Traditional CNN methods usually use fixed-size kernels for convolution, and they generally lose part of the target’s feature information, resulting in the inaccurate classification of the SAR targets. This article proposes a novel CNN model based on multikernel-size feature fusion (MKSFF-CNN) for SAR target classification. MKSFF-CNN designs a convolutional methodology with a multichannel parallel topology, it uses convolutional kernels of different sizes to extract the multikernel-size deep features of the SAR target, and then, these features are fused in an optimal way to acquire the lowest loss. Moreover, MKSFF-CNN concatenates the fused features extracted by the convolutional layers of different dimensions to achieve the finest classification. MKSFF-CNN greatly elevates the feature representation completeness of the SAR targets so that more useful feature information can be exploited for SAR target classification. Undoubtedly, MKSFF-CNN can achieve a better classification performance compared with traditional CNN models with a fixed kernel size. The superiority of MKSFF-CNN is validated on the moving and stationary target acquisition and recognition (MSTAR) dataset with the detailed objective and subjective evaluation.

Target Region Segmentation in SAR Vehicle Chip Image With ACM Net

Target region segmentation of synthetic aperture radar (SAR) images is one of the challenging problems in SAR image interpretation. The existing conventional segmentation methods rely on parameter selection in different backgrounds. Compared with traditional methods, the deep-learning-based methods can reduce the dependency on parameters and achieve more accurate results. However, lacking annotation data limits the application of the deep-learning-based methods in SAR chip image segmentation aspect. To solve these problems, a refined network structure for SAR vehicle image semantic segmentation, namely, All-Convolutional networks (A-ConvNets)-based Mask (ACM) net, is proposed. The mask in the training dataset of the network is extracted from image reconstruction using the Attribute Scattering Center (ASC) model, which can solve the problem of the lack of manual annotation in the segmentation methods based on deep learning. The proposed ACM Net consists of a modified A-ConvNets-based backbone and two decoupled head branches which achieve target segmentation and label prediction results, respectively. Experiments on moving and stationary target acquisition and recognition (MSTAR) dataset show that the comprehensive segmentation performance of ACM Net is better than both traditional segmentation methods and deep-learning-based segmentation methods. The classification results outperform other instance or semantic segmentation methods with the state-of-the-art recognition accuracy.

Optimal Target Classification Using Frequency-Based Radar Waveform Design

In this article, we introduce a frequency-based waveform design to maximize binary target classification. The optimization problems can be solved via optimal solvers available in the literature. The presented formulation is applicable to the classification scenarios where the extended target frequency responses (TFRs) are complex, random, and normally distributed with unequal mean vectors. However, their covariance matrices are either identical or different. For the former, i.e., identical covariance matrices, the optimization problem consists of a cost function that has been obtained by deriving a closed-form expression of the probability of misclassification. For the latter, i.e., different covariance matrices, we present an optimization problem where the cost function has been obtained via the Fisher separation function. For this, we also present a closed-form expression for an approximate solution to the optimization problem. We show that the proposed solution achieves performance levels comparable to the exact solution of the optimization problem obtained via state-of-the-art optimization solvers while incurring low computational complexity. We expand on the two main scenarios by introducing clutter (i.e., signal-dependent interference) in the signal model and studying possible closed-form designs in extreme waveform energy levels. Simulations are conducted using synthetically generated data in addition to the civilian vehicle data from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, in order to validate the proposed method.

Threshold Filtering Semi-Supervised Learning Method for SAR Target Recognition

The semi-supervised deep learning technology driven by a small part of labeled data and a large amount of unlabeled data has achieved excellent performance in the field of image processing. However, the existing semi-supervised learning techniques are all carried out under the assumption that the labeled data and the unlabeled data are in the same distribution, and its performance is mainly due to the two being in the same distribution state. When there is out-of-class data in unlabeled data, its performance will be affected. In practical applications, it is difficult to ensure that unlabeled data does not contain out-of-category data, especially in the field of Synthetic Aperture Radar (SAR) image recognition. In order to solve the problem that the unlabeled data contains out-of-class data which affects the performance of the model, this paper proposes a semi-supervised learning method of threshold filtering. In the training process, through the two selections of data by the model, unlabeled data outside the category is filtered out to optimize the performance of the model. Experiments were conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and compared with existing several state-of-the-art semi-supervised classification approaches, the superiority of our method was confirmed, especially when the unlabeled data contained a large amount of out-of-category data.

Multiscale CNN Based on Component Analysis for SAR ATR

This article proposes a multiscale convolutional neural network (CNN) based on component analysis (CA-MCNN) for synthetic aperture radar (SAR) automatic target recognition (ATR). The component information of a target is robust to the local variations of the target, which is not made the best of by traditional CNN-based methods. For learning the component information, we use the attributed scattering centers (ASCs) extracted from the target echoes as the components of the target for SAR ATR, which divides the SAR target according to the geometric scattering types of ASCs and can not only make the division results more robust but also accurately characterize the electromagnetic scattering characteristics of the target. Since the global information provided by the whole image is also important for SAR ATR, CA-MCNN combines the global information with component information to learn a more efficient and robust target feature representation. In addition, considering that the feature maps of the shallower layer in CNN focus on local and fine-grained information while the feature maps in the deeper layer focus on global and coarse-grained information, we fuse the multiscale feature maps obtained from different layers to enhance the feature description ability. Extensive experiments conducted on the moving and stationary target acquisition and recognition (MSTAR) data set prove the superior performance of CA-MCNN.

SAR Target Recognition Based on Task-Driven Domain Adaptation Using Simulated Data

Synthetic aperture radar (SAR) images are highly susceptible to imaging conditions. However, the majority of deep learning (DL) models in SAR automatic target recognition (ATR) adopt enhanced network structures similar to those in dealing with optical image classification tasks, which is obviously unreasonable since the huge gap of the imaging conditions between training and testing data severely deteriorates the recognition performance. The main idea of the framework is to introduce SAR imaging condition information into the DL training stage to eliminate domain discrepancies between training and testing data. Based on this framework, we propose a task-driven domain adaptation (TDDA) transfer learning method, which can alleviate the degradation of recognition caused by the variance of depression angle between training and testing data. In order to introduce the prior imaging information into the method, simulated SAR data is first obtained by adding a simulated object radar reflectivity to a terrain model of individual point scatters using the known training and testing SAR imaging parameters. Then a domain confusion metric and a supervised classification loss are calculated on simulated data and source training data, respectively, to learn a representation that is semantically meaningful and domain invariant. Comparative experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate that the proposed method can obtain better recognition performance than the other methods.

Label Noise Modeling and Correction via Loss Curve Fitting for SAR ATR

The success of deep learning in synthetic aperture radar (SAR) automatic target recognition (ATR) relies on a large number of labeled samples; however, there are often wrong (noisy) labels in a large-scale dataset. In this article, we propose a loss curve-fitting-based method, which can identify the noisy labels and train the classification network effectively. We propose to model label noise by unsupervised clustering via fitting loss curve to identify whether the sample’s label is clean or noisy. Then, we train the network using augmented samples with clean labels to correct noisy labels further. The experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset prove that our proposed method can deal with the situation when training a network with different ratios of noisy labels and correct noisy labels effectively. When the noise ratio is small (40%) in the training dataset, our method can correct 97.9% of noisy labels and train the classification network with 98.8% classification accuracy. While the noise ratio is large (80%), our method can correct 78.1% of noisy labels and train the classification network with 79.6% classification accuracy.

Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition

Synthetic aperture radar (SAR) target recognition faces the challenge that there are very little labeled data. Although few-shot learning methods are developed to extract more information from a small amount of labeled data to avoid overfitting problems, recent few-shot or limited-data SAR target recognition algorithms overlook the unique SAR imaging mechanism. Domain knowledge-powered two-stream deep network (DKTS-N) is proposed in this study, which incorporates SAR domain knowledge related to the azimuth angle, the amplitude, and the phase data of vehicles, making it a pioneering work in few-shot SAR vehicle recognition. The two-stream deep network, extracting the features of the entire image and image patches, is proposed for more effective use of the SAR domain knowledge. To measure the structural information distance between the global and local features of vehicles, the deep Earth mover’s distance is improved to cope with the features from a two-stream deep network. Considering the sensitivity of the azimuth angle in SAR vehicle recognition, the nearest neighbor classifier replaces the structured fully connected layer for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -shot classification. All experiments are conducted under the configuration that the SARSIM and the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset work as a source and target task, respectively. Our proposed DKTS-N achieved 49.26% and 96.15% under ten-way one-shot and ten-way 25-shot, whose labeled samples are randomly selected from the training set. In standard operating condition (SOC) as well as three extended operating conditions (EOCs), DKTS-N demonstrated overwhelming advantages in accuracy and time consumption compared with other few-shot learning methods in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -shot recognition tasks.

SAR Target Recognition With Modified Convolutional Random Vector Functional Link Network

Deep learning models have achieved remarkable performance in synthetic aperture radar (SAR) target recognition. However, the accuracy of these methods is sensitive to the hyper-parameters and the traditional backpropagation is time consuming. In this letter, we proposed a modified convolutional random vector functional link (IntCRVFL) network for SAR target recognition, which can simplify the SAR target recognition system. The convolutional random vector functional link network consists of a convolutional neural network and a random vector functional link (RVFL) network. First, the fixed convolutional layers with randomly initialized parameters extract SAR image features and then the RVFL network performs target recognition. Especially, inspired by hyperdimensional computing, the activations of the hidden layer are obtained through a new encoding manner. Besides, only the connections between hidden and output layers need to train by a closed-form solution for the ultimately precise target recognition. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set demonstrate the proposed IntCRVFL network can obtain a satisfying accuracy with a faster speed.

Land-Sea Target Detection and Recognition in SAR Image Based on Non-Local Channel Attention Network

Synthetic aperture radar (SAR) target recognition is essential for SAR image interpretation. It has been widely used in national defense and national economy. At present, the SAR image detection and recognition methods based on convolutional neural network (CNN) have problems such as insufficient extraction of the feature information of SAR image targets, false targets caused by the interference of complex backgrounds, and low detection performance. The main reason is that the feature extraction of CNN is a local operation in space and time, which ignores the correlation between pixels and regions and the dependencies between channels in SAR images. In this paper, a non-local channel attention network (NLCANet) SAR image target recognition method is proposed based on the GoogLeNet structure combined with asymmetric pyramid non-local block (APNB) and squeeze-and-excitation block (SEB). APNB is added to the GoogLeNet framework to capture more context information and enhance the correlation between pixels and regions. SEB is added to the Inception structure to become Inception-SEB (ISEB), through which channel dependencies based on the fusion of different scale features can be obtained. The experimental results based on the moving and stationary target acquisition and recognition (MSTAR) dataset and the SAR ship detection dataset (SSDD) show that the proposed method improves the detection ability of targets in complex backgrounds and achieves better land-sea target recognition performance.

Recognition Rate Versus Substitution Rate Curve: An Objective Utility Assessment Criterion of Simulated Training Data

Data augmentation is beneficial when the measured training data are insufficient to train a robust deep model. One of the promising techniques is to use simulated data generated by physics-based engines. For example, few-shot learning of synthetic aperture radar (SAR) targets could be benefited from simulated SAR images. However, the characteristics of the simulated training data significantly affect the performance of the trained model. Therefore, it is of great significance to evaluate the utility of simulated data objectively and effectively. A recognition rate versus substitution rate curve (RSC)-based assessment criterion is proposed, consisting of substitution rate (SR)-based dataset allocation stage and RSC-based evaluation stage. First, the differential dataset allocation is performed under a progressive SR to obtain paired reference and comparison training sets. Then, the reference and comparison classifiers are trained under different SRs using the same network and parameter configuration in the RSC criterion-based evaluation stage. AconvNet and AlexNet are selected as the backbones of the evaluation network. Especially, k-fold cross-validation is applied to alleviate selection bias. The difference between the integrals of RSCs is defined as the RSC score for the simulated dataset. Experiments conducted on the measured and simulated moving and stationary target acquisition and recognition (MSTAR) database demonstrate the rationality and validity of the proposed RSC criterion. Specifically, multisource simulated datasets are adopted, including the adversarial autoencoder-generated and electromagnetic simulation datasets. The proposed RSC criterion shows promising utility evaluation ability, flexibility, and extensibility compared with traditional full-reference image-quality assessment criteria.

Few-Shot SAR Target Classification via Metalearning

The state-of-the-art deep neural networks have made a great breakthrough in remote sensing image classification. However, the heavy dependence on large-scale data sets limits the application of the deep learning to synthetic aperture radar (SAR) automatic target recognition (ATR) field where the target sample set is generally small. In this work, a metalearning framework named MSAR, consisting of a metalearner and a base-learner, is proposed to solve the sample restriction problem, which can learn a good initialization as well as a proper update strategy. After training, MSAR can implement fast adaptation with a few training images on new tasks. To the best of our knowledge, this is the first study to solve a few-shot SAR target classification via metalearning. In particular, the few-task problem is defined by analyzing the effect of available training classes on the performance of metalearning models. In order to reduce the metalearning difficulties caused by the few-task problem, three transfer-learning methods are employed, which can leverage the prior knowledge from the pretraining phase. Besides, we design a hard task mining method for effective metalearning. Based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, a specialized data set named NIST-SAR is devised to train and evaluate the proposed method. The experiments on NIST-SAR have shown that the proposed method yields better performances with the largest absolute improvements of 1.7% and 2.3% for 1-shot and 5-shot, respectively, over the next best, which indicates that the proposed method is promising and metalearning is a feasible solution for few-shot SAR ATR.

SAR Target Classification Based on Multiscale Attention Super-Class Network

The convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features. On the other hand, conventional CNN approaches only assign fine-class labels to SAR targets, ignoring the high-level semantics information of similar categories, which reduces the feature differences between categories and the generalization ability of the model. Therefore, this paper proposes a multi-scale attention super-class CNN (MSA-SCNN) for SAR target classification. Firstly, MSA-SCNN combines multi-scale feature fusion with the attention module to improve the integrity of SAR target feature representation. The attention module includes channel and spatial attention modules, which realize the weighted enhancement of different scale features. Additionally, MSA-SCNN introduces super-class labels to increase the feature difference between categories. The classification stage consists of a fine-class branch and a super-class branch, and the features trained on the super-class branch are fused to the fine-class branch to improve the network's fine classification ability. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the FUSAR-Ship dataset show that the proposed MSA-SCNN outperforms many current existing state-of-the-art methods.

A Trimodel SAR Semisupervised Recognition Method Based on Attention-Augmented Convolutional Networks

Semi-supervised learning (SSL) in synthetic aperture radars (SAR) is one of the research hotspots in the field of radar-image automatic target recognition (ATR). It can efficiently deal with challenging environments where there are insufficient labeled samples and large unlabeled samples in the SAR dataset. In recent years, consistency regularization methods in semi-supervised learning have shown considerable improvement in recognition accuracy and efficiency. Current consistency regularization approaches suffer from two main shortcomings: firstly, extracting all of the relevant information in the image target is difficult owing to the inability of conventional convolutional neural networks (CNN) to capture global relational information,; secondly, the standard teacher-student regularization methodology causes confirmation biases due to the high coupling between teacher and student models. This work adopts an innovative tri-model semi-supervised method based on attention-augmented convolutional networks to address the aforementioned obstacles. Specifically, we develop an attention mechanism incorporating a novel positional embedding method based on recurrent neural networks (RNN), and integrate this with a standard convolutional network as a feature extractor, to improve the network's ability to extract global feature information from images. Further, we address the confirmation bias problem by introducing a classmate model to the standard teacher-student structure and utilise the model to impose a weak consistency constraint (WCC) designed on the student to weaken the strong-coupling between the teacher and the student. Comparative experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our method outperforms state-of-the-art semi-supervised methods in terms of recognition accuracy, demonstrating its potential as a new benchmark approach for the deep learning and SAR research community.