Density Coverage-Based Exemplar Selection for Incremental SAR Automatic Target Recognition

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

Combination of global and local filters for robust SAR target recognition under various extended operating conditions

Synthetic aperture radar automatic target recognition (SAR-ATR) typically consists of 3 main stages: preprocessing(also known as prescreening), feature extraction, and classification. For high-dimensional feature space, the computation time required to construct it by sequential programming is considerably long. In this study, parts of an ATR system, in particular the feature extraction stage, were implemented on Graphics Processing Unit (GPU) for speed up. For Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, the 3-stage ATR process constructing a 28-dimension feature space using 2987 samples performed over 6 times faster running a GPU implemented code than that of a sequential code on average.

In this paper, a novel classification method path-based similarity with instance-level constrains for SemiBoost, PBS-SB in short is proposed, and we exploit it for synthetic aperture radar automatic target recognition (SAR-ATR). Different from traditional SemiBoost method that uses the Gaussian kernel similarity, PBS-SB utilizes the path-based similarity, which considers the global consistence of data clusters. Besides, the instance-level constraints are integrated into the similarity measurement to construct the semi-supervised similarity, which provides the local consistence information. The experiments on 5 different data sets and MSTAR (Moving and Stationary Target Acquisition and Recognition) database demonstrate that the proposed method has superior classification performance with respect to competitive methods.

In recent years, convolutional neural network (CNN) has been increasingly considered as a promising technology for military and homeland security applications. The fusion of CNN and Support vector machine (SVM), a popular traditional machine learning approach, has received intensive attention in the field of synthetic aperture radar (SAR) automatic target recognition (ATR). This paper, firstly, discusses the effects of some preprocessing and image enhancement methods on the performance of SAR ATR, starting with the pre-trained AlexNet in a transfer-learning based approach. Secondly, the architecture of AlexNet is modified to form a new model suitable for SAR ATR. Finally, we propose a hybrid model associated with the success of the learning feature of our CNN model and the ability of SVM to process high-dimensional dataset effectively. To evaluate the proposed method, experiments are performed on the Moving and Stationary Target Acquisition and Recognition (MSTAR) public database. The comparative results demonstrate that these preprocessing and enhancement methods prior to the deep-learning process are not necessary since the feature representation ability of AlexNet is already powerful. Furthermore, experimental results on the benchmark MSTAR dataset illustrate the effectiveness of the proposed new model. On classification of ten-class targets, the commonly used translation augmentation for training data has been performed. By combining the CNN and SVM, the classification accuracy percentages can be slightly improved for our proposed new model.

DARPA/Air Force Research Laboratory Moving and Stationary Target Acquisition and Recognition (MSTAR) program is developing state-of-the-art model based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The model-based approach requires using off-line developed target models in an on-line hypothesize-and-test manner to compare predicted target signatures with image data and output target reports. Central to this model-based ATR is the PEMS (Predict-Extract-Match-Search) subsystem. The Search module is critical to PEMS by providing intelligent control to traverse the hypothesis feature space. A major MSTAR goal is to demonstrate robust ATR for variations in targets including partially hidden targets. This paper will provide an update on the technology being developed under MSTAR and the status of this model based ATR research, specifically concentrating on the Search Module.

In the field of synthetic aperture radar (SAR) automatic target recognition (ATR), deep learning-driven methods perform well when numerous training samples are available. However, in practical SAR application scenarios, the number of available training samples is often scarce due to the limitation of observation conditions, which leads to major challenges for deep learning-driven methods in real-world deployment. Currently, the problem of ATR with only a few training samples has attracted much attention in the SAR field. In this article, we put forward an ATR method called azimuth-guided feature embedding network with dual inference mechanism (AGFEN-DIM) to achieve fewshot SAR target recognition. To be specific, the feature extraction model, i.e. azimuth-guided feature embedding network (AGFEN) is composed of the azimuth embedding module (AEM) and the dynamic feature embedding module (DFEN). Among them, AEM resorts to a set of azimuth-parameterized convolution kernels, aiming to make full use of information relevant to the current radar imaging environment. The proposed DFEN is capable of dynamically extracting the discriminative features of the target according to the input image under the guidance of azimuth-parameterized convolutional kernels. The dual inference mechanism (DIM) effectively integrates the inference results of improved prototype classification and label propagation strategy to boost the reliability and robustness of the recognition model for few-shot SAR target recognition tasks. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate that the proposed AGFEN-DIM surpasses many state-of-the-art SAR ATR methods in various application scenarios.

Convolutional neural network(CNN) has achieved great success in optical image recogniton, and has been applied in research of synthetic aperture radar(SAR) automatic target recognition(ATR) recently. However, in real SAR systems, SAR images are usually compressed for transmission due to the limited wireless bandwidth, and few researches have evaluated the influence of image compression on SAR ATR task. In this paper, an efficient CNN architecture based on inception module and batch normalization layer is proposed for SAR ATR tasks, and the impact of image compression on SAR ATR is evaluated based on the proposed model. The experiments are based on MSTAR dataset, and the test images are compressed by Set Partitioning in Hierarchical Trees(SPIHT) algorithm with different compression ratio. Experimental results show that the proposed CNN model achieves a state-of-the-art classification accuracy of 99.29% on original MSTAR dataset, and can still get high classification accuracy above 90% even SAR images in test set are compressed by nearly one hundred times, which reveals that moderate compression of SAR images has little influence on SAR ATR tasks, and this validates the practicability of applying the proposed model to real SAR ATR systems.

Deep Neural Networks (DNNs) based Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems have shown to be highly vulnerable to adversarial perturbations that are deliberately designed yet almost imperceptible but can bias DNN inference when added to targeted objects. This leads to serious safety concerns when applying DNNs to high-stakes SAR ATR applications. Therefore, enhancing the adversarial robustness of DNNs is essential for applying DNNs to modern real-world SAR ATR systems. Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers). The proposed SMGAA consists of two parts: 1) a parametric scattering model and corresponding imaging method and 2) a customized gradient-based optimization algorithm. First, we introduce the effective Attributed Scattering Center Model (ASCM) and a general imaging method to describe the scattering behavior of typical geometric structures in the SAR imaging process. By further devising several strategies to take the domain knowledge of SAR target images into account and relax the greedy search procedure, the proposed method does not need to be prudentially finetuned, and can efficiently find the effective ASCM parameters to fool the SAR classifiers and facilitate the robust model training. Comprehensive evaluations on the MSTAR dataset show that the adversarial scatterers generated by SMGAA are more robust to perturbations and transformations in the SAR processing chain than the currently studied attacks, and are effective to construct a defensive model against the malicious scatterers.

The existing deep learning studies on synthetic aperture radar (SAR) automatic target recognition (ATR) mainly focus on the utilization of the amplitude of SAR image via convolutional neural network (CNN), while the electromagnetic scattering information is rarely considered. Given that scattering centers (SCs) can characterize the target’s electromagnetic scattering characteristics and describe the target’s physical structure information, the SC feature should be helpful for SAR ATR. Therefore, we propose a novel SAR ATR method that combines electromagnetic scattering information and graph convolutional network (GCN) effectively and directly. Specifically, we model each extracted SC as a node to convert the SCs into graph data. The constructed graph is learned via GCN to describe the target’s physical structure information, where the features of different GCN layers are fused to avoid the over-smoothing of GCN. Label smoothing is combined with GCN for the first time to alleviate the overfitting caused by the limited training data. To the best of our knowledge, this study is the first to introduce the GCN for effectively utilizing the SCs, proving that the structural characteristics of the SCs of SAR targets are remarkably beneficial for recognition. Extensive experimental results on the measured moving and stationary target acquisition and recognition (MSTAR) dataset show that our method can obtain superior recognition performance compared with the existing methods.

Deep neural networks have recently demonstrated state-of-the-art accuracy on public Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) benchmark datasets. While attaining competitive accuracy on benchmark datasets is a necessary feature, it is important to characterize other facets of new SAR ATR algorithms. We extend this recent work by demonstrating not only improved state-of-the-art accuracy, but that contemporary deep neural networks can achieve several algorithmic traits beyond competitive accuracy which are necessitated by operational deployment scenarios. First, we employ several saliency map algorithms to provide explainability and insight into understanding black-box classifier decisions. Second, we collect and implement numerous data augmentation routines and training improvements both from the computer vision literature and specific to SAR ATR data in order to further improve model domain adaptation performance from synthetic to measured data, achieving a 99.26% accuracy on SAMPLE validation with a simple network architecture. Finally, we survey model reproducibility and performance variability under domain adaptation from synthetic to measured data, demonstrating potential consequences of training on only synthetic data.

The existing synthetic aperture radar (SAR) automatic target recognition (ATR) methods have shown impressive results in static scenarios, yet the performance drops sharply as new categories of targets are continuously increased. In response to this problem, this letter proposes a novel ATR method named multi-level adaptive knowledge distillation network (MLAKDN) to achieve incremental SAR target recognition. To be specific, an adaptive weighted distillation strategy is first proposed, which can alleviate the model from forgetting the knowledge of old categories by distilling multi-stage soft label information of old categories at the classification level. Then, a feature distillation method based on gradient maximum criterion is developed to filter and distill discriminative features, so as to further recall more knowledge of old categories at the feature level. Meanwhile, a model rebalancing technique is designed to effectively strike the balance of the model on new categories and old categories. Finally, a weighted incremental classification loss is presented to train the whole model. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the synthetic and measured paired labeled experiment (SAMPLE) dataset illustrate that the proposed method is superior to some state-of-the-arts for incremental SAR target recognition tasks.

Some recent articles have revealed that synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep learning are vulnerable to the attacks of adversarial examples and cause security problems. The adversarial attack can make a deep convolutional neural network (CNN)-based SAR-ATR system output the intended wrong label predictions by adding small adversarial perturbations to the SAR images. The existing optimization-based adversarial attack methods generate adversarial examples by minimizing the mean-squared reconstruction error, causing smooth target edge and blurry weak scattering centers in SAR images. In this paper, we build a UNet-generative adversarial network (GAN) to refine the generation of the SAR-ATR models’ adversarial examples. The UNet learns the separable features of the targets and generates the adversarial examples of SAR images. The GAN makes the generated adversarial examples approximate to real SAR images (with sharp target edge and explicit weak scattering centers) and improves the generation efficiency. We carry out abundant experiments using the proposed adversarial attack algorithm to fool the SAR-ATR models based on several advanced CNNs, which are trained on the measured SAR images of the ground vehicle targets. The quantitative and qualitative results demonstrate the high-quality adversarial example generation and excellent attack effectiveness and efficiency improvement.

Many convolution neural networks(CNN) architectures have been proposed to strengthen the performance on synthetic aperture radar automatic target recognition (SAR-ATR) and obtained state-of-art results on targets classification on MSTAR database, but few methods concern about the estimation of depression angle and azimuth angle of targets. To get better effect on learning representation of hierarchies of features on both 10-class target classification task and target posture estimation tasks, we propose a new CNN architecture with spatial pyramid pooling(SPP) which can build high hierarchy of features map by dividing the convolved feature maps from finer to coarser levels to aggregate local features of SAR images. Experimental results on MSTAR database show that the proposed architecture can get high recognition accuracy as 99.57% on 10-class target classification task as the most current state-of-art methods, and also get excellent performance on target posture estimation tasks which pays attention to depression angle variety and azimuth angle variety. What’s more, the results inspire us the application of deep learning on SAR target posture description.

This paper presents an enhanced ensemble classification framework for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) under diverse operational conditions, including Standard Operating Conditions (SOC) and Extended Operating Conditions (EOC). The proposed method integrates the strengths of Residual Neural Networks (ResNet) replacing Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and template matching, leveraging majority voting to combine their complementary capabilities. The ensemble framework achieves improved robustness and classification accuracy across varied scenarios. The methodology employs ResNet, a deep learning architecture known for its superior feature extraction and classification capabilities, replacing AlexNet to address limitations in generalization and consistency. ResNet demonstrated better performance with average accuracies of 92.67% under SOC and 88.9% under EOC, showing consistent results across all six target classes, as compared to the CNN-based ensemble approach with average accuracies of 90.30% under SOC and 87.22% under EOC. The SVM is employed for its robustness in handling overfitting and classifying features extracted from 16 region properties. Template matching is included for its resilience in challenging conditions where deep learning techniques may underperform. Experimental validation using the MSTAR dataset, a standard benchmark for SAR ATR, highlights the effectiveness of this ensemble approach. The results confirm significant improvements in classification accuracy and robustness over individual classifiers, demonstrating the practical applicability of the ensemble approach to real-world SAR ATR challenges. This research advances SAR ATR by addressing critical challenges, including noise, occlusion, and variations in viewing angles while achieving high classification performance under diverse conditions. The integration of ResNet further enhances the framework’s adaptability and reliability.