Robust ensemble classifier for advanced synthetic aperture radar target classification in diverse operational conditions

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

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.

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.

Automatic target recognition (ATR) of synthetic aperture radar (SAR) images is performed on either global or local features. The global features can be extracted and classified with high efficiency. However, they lack the reasoning capability thus can hardly work well under the extended operation conditions (EOCs). The local features are often more difficult to extract and classify but they provide reasoning capability for EOC target recognition. To combine the efficiency and robustness in an ATR system, a hierarchical fusion of the global and local features is proposed for SAR ATR in this paper. As the global features, the random projection features can be efficiently extracted and effectively classified by sparse representation-based classification (SRC). The physically relevant local descriptors, i.e., attributed scattering centers (ASCs), are employed for local reasoning to handle various EOCs like noise corruption, resolution variance, and partial occlusion. A one-to-one correspondence between the test and template ASC sets is built by the Hungarian algorithm. Then, the local reasoning is performed by evaluating individual matched pairs as well as the false alarms and missing alarms. For the test image to be recognized, it is first classified by the global classifier, i.e., SRC. Once a reliable decision is made, the whole recognition process terminates. When the decision is not reliable enough, it is passed to the local classifier, where a further classification by ASC matching is carried out. Therefore, by the hierarchical fusion strategy, the efficiency of global features and the robustness of local descriptors to various EOCs can be maintained jointly in the ATR system. Extensive experiments on the moving and stationary target acquisition and recognition data set demonstrate that the proposed method achieves superior effectiveness and robustness under both SOC and typical EOCs, i.e., noise corruption, resolution variance, and partial occlusion, compared with some other SAR ATR methods.

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.

In recent years, deep learning has significantly improved the performance of Synthetic Aperture Radar Automatic Target Recognition (SAR-ATR), but the lack of large-scale labelled training data limits the further development of deep neural networks in this field. Traditionally, annotating SAR data requires manual labour by experts with specialized domain knowledge, which is costly and makes it difficult to obtain a large amount of labelled data. Semi-supervised learning (SSL) algorithms can effectively leverage unlabelled data for training, improving model performance. However, improper use of pseudo-labels can lead to error accumulation and result in performance degradation. This paper proposes an SSL algorithm for SAR image recognition that employs the following strategies to mitigate error accumulation and enhance performance: First, by combining pseudo-labelling and consistency-regularization methods, unlabelled data with different augmentations are compared in terms of classification predictions and feature vectors, improving the model representation capacity. Second, a weighted distance metric combining labelled and unlabelled data is designed to estimate model loss, guiding the model towards intra-class aggregation and inter-class dispersion in terms of data distribution. Experiments conducted on the MSTAR and OpenSARShip datasets demonstrate that the algorithm achieves superior performance in limited labelled sample scenarios, with an accuracy of over 99% when only 30 labelled data points (approximately 10%) per class are available, and an accuracy of over 85% with extremely scarce samples (only 5 labelled samples per class) on the MSTAR dataset.

Deep neural network-based synthetic aperture radar (SAR) automatic target recognition (ATR) systems are susceptible to attack by adversarial examples, which leads to misclassification by the SAR ATR system, resulting in theoretical model robustness problems and security problems in practice. Inspired by optical images, current SAR ATR adversarial example generation is performed in the image domain. However, the imaging principle of SAR images is based on the imaging of the echo signals interacting between the SAR and objects. Generating adversarial examples only in the image domain cannot change the physical world to achieve adversarial attacks. To solve these problems, this article proposes a framework for generating SAR adversarial examples in a 3D physical scene. First, adversarial attacks are implemented in the 2D image space, and the perturbation in the image space is converted into simulated rays that constitute SAR images through backpropagation optimization methods. The mapping between the simulated rays constituting SAR images and the 3D model is established through coordinate transformation, and point correspondence to triangular faces and intensity values to texture parameters are established. Thus, the simulated rays constituting SAR images are mapped to the 3D model, and the perturbation in the 2D image space is converted back to the 3D physical space to obtain the position and intensity of the perturbation in the 3D physical space, thereby achieving physical adversarial attacks. The experimental results show that our attack method can effectively perform SAR adversarial attacks in the physical world. In the digital world, we achieved an average fooling rate of up to 99.02% for three objects in six classification networks. In the physical world, we achieved an average fooling rate of up to 97.87% for these objects, with a certain degree of transferability across the six different network architectures. To the best of our knowledge, this is the first work to implement physical attacks in a full physical simulation condition. Our research establishes a theoretical foundation for the future concealment of SAR targets in practical settings and offers valuable insights for enhancing the attack and defense capabilities of subsequent DNNs in SAR ATR systems.

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 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.

Decades of research have been dedicated to overcoming the obstacles inherent in synthetic aperture radar (SAR) automatic target recognition (ATR). The rise of deep learning technologies has brought a wave of new possibilities, demonstrating significant progress in the field. However, challenges like the susceptibility of SAR images to noise, the requirement for large-scale training datasets, and the often protracted duration of model training still persist. This paper introduces a novel data augmentation strategy to address these issues. Our method involves the intentional addition and subsequent removal of speckle noise to artificially enlarge the scope of training data through noise perturbation. Furthermore, we propose a modified network architecture named weighted ResNet, which incorporates residual strain controls for enhanced performance. This network is designed to be computationally efficient and to minimize the amount of training data required. Through rigorous experimental analysis, our research confirms that the proposed data augmentation method, when used in conjunction with the weighted ResNet model, significantly reduces the time needed for training. It also improves the SAR ATR capabilities. Compared to existing models and methods tested, the combination of our data augmentation scheme and the weighted ResNet framework achieves higher computational efficiency and better recognition accuracy in SAR ATR applications. This suggests that our approach could be a valuable advancement in the field of SAR image analysis.

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

The traditional multi-view synthetic aperture radar (SAR) automatic target recognition (ATR) is based on the assumption of viewpoint integrity of the dataset, requiring that the viewpoint information of all samples participating in the recognition is complete. To address the problem that SAR ATR is difficult under the training condition of an incomplete view sample set, a new cross-view SAR target recognition method based on view correlation extension and multi-task learning is proposed. To mine the complementary information between multi-view SAR images, the training datasets are clustered into subsets of different views based on the correlation coefficient. To improve the accuracy of cross-view recognition, we adopt the strategy of multi-view subsets corresponding to multi-task kernel sparse representation. For the decision values of each view subset, the fusion error is obtained by linear weighting. Finally, the total reconstruction errors accumulated from all tasks are identified. Experimental results on the MSTAR database in cross-view conditions show that our method outperforms the widely-used SAR ATR methods in several performance indicators.

Deep learning algorithms have found extensive utility in Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR). Despite this, conventional deep learning-based ATR models often lack in their performance when subjected to Extended Operating Conditions (EOCs). Significant variations in depression, noise interference, limited training data, and partial occlusion are primary factors in EOCs. In this paper, we proposed a deep neural network-based technique to recognize SAR targets for Standard Operating Conditions (SOC) and Extended Operating Conditions (EOC). The proposed approach comprises an encoder and decoder network. The encoder network integrates multiple dilated convolutions to address noise-induced recognition challenges for extracting multi-scale features. Furthermore, a feature refinement module is integrated within the multi-scale channels to enhance the extraction of discriminative and resilient features. Feature refinement selectively emphasizes informative features while suppressing irrelevant ones. Additionally, a salient attention block and a spatial feature learning module are introduced for feature selection. Selected features are then utilized in the top-level network layer of the encoder network to preserve spatial relationships among diverse features. This spatial feature learning module aids in recognition performance, particularly when training data is scarce. The decoder network consists of stacked transposed convolution layers, facilitating the encoder network's acquisition of discriminative image features. Experimental evaluations were conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset to validate the efficacy of the proposed methodology.

Synthetic Aperture Radar (SAR) target classification is an important branch of SAR image interpretation. The deep learning based SAR target classification algorithms have made remarkable achievements. But the acquisition and annotation of SAR target images are time-consuming and laborious, and it is difficult to obtain sufficient training data in many cases. The insufficient training data can make deep learning based models suffering from over-fitting, which will severely limit their wide application in SAR target classification. Motivated by the above problem, this paper employs transfer-learning to transfer the prior knowledge learned from a simulated SAR dataset to a real SAR dataset. To overcome the sample restriction problem caused by the poor feature discriminability for real SAR data. A simple and effective sample spectral regularization method is proposed, which can regularize the singular values of each SAR image feature to improve the feature discriminability. Based on the proposed regularization method, we design a transfer-learning pipeline to leverage the simulated SAR data as well as acquire better feature discriminability. The experimental results indicate that the proposed method is feasible for the sample restriction problem in SAR target classification. Furthermore, the proposed method can improve the classification accuracy when relatively sufficient training data is available, and it can be plugged into any convolutional neural network (CNN) based SAR classification models.

The traditional Synthetic Aperture Radar Automatic Target Recognition (SAR/ATR) algorithm can train a sufficient number of known class samples and classify the samples in the test set. However, if the old model is trained only with the new class samples, the old class samples’ knowledge is easily forgotten by the new model, which is called catastrophic forgetting. The reason is that the model only fits the distribution of current training samples, so training the whole data set is necessary. Due to the limitation of storage resources, it is often not feasible to retain the whole data set. In order to avoid this phenomenon, a small number of old class samples can be kept to train with the new class samples. Therefore, how to select the old class samples becomes the key point. In this paper, the Density Coverage-Based Exemplar Selection (DCBES) is proposed to choose the key samples of the old class. DCBES selects samples based on the metric learning theory and the set covering theory. First, the metric learning theory is used to measure the similarity between samples and to obtain the density range of samples. Then the exemplar selection problem is considered a set covering problem, to select a fixed number of exemplars to achieve the maximum coverage of the class density range. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our method is superior to other exemplar selection methods and achieves the best results.