Search

The widespread application of virtual reality has made automatic target recognition in environmental space particularly important. However, traditional image recognition methods faced challenges due to the complex and diverse environmental characteristics in virtual reality scenes. It is easily influenced by occlusion, noise, and other factors. To deal with the issue, this paper utilizes the combination of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), and proposes a collaborative neural network-based automatic object recognition method for environmental space under virtual reality scenes. Specifically, CNN is mainly responsible for feature extraction of environmental scene images, while RNN is used to model the spatial relationships of image sequences. Then, a data augmentation method is introduced in virtual reality scenarios, which can generate more training samples on a limited dataset, thereby improving the model's generalization ability. Meanwhile, in order to address issues such as occlusion and noise, a multi-scale feature fusion strategy is further developed to improve the robustness of target recognition by multiscale feature fusion. Through experimental verification using actual data collected in virtual reality scenes, the results show that the proposed method has achieved excellent performance and strong adaptability compared with traditional methods. [ABSTRACT FROM AUTHOR]

Nowadays, deep learning techniques are extensively applied in the field of automatic target recognition (ATR) for radar images. However, existing data-driven approaches frequently ignore prior knowledge of the target, leading to a lack of interpretability and poor performance of trained models. To address this issue, we first integrate the knowledge of structural attributes into the training process of an ATR model, providing both category and structural information at the dataset level. Specifically, we propose a Structural Attribute Injection (SAI) module that can be flexibly inserted into any framework constructed based on neural networks for radar image recognition. Our proposed method can encode the structural attributes to provide structural information and category correlation of the target and can further apply the proposed SAI module to map the structural attributes to something high-dimensional and align them with samples, effectively assisting in target recognition. It should be noted that our proposed SAI module can be regarded as a prior feature enhancement method, which means that it can be inserted into all downstream target recognition methods on the same dataset with only a single training session. We evaluated the proposed method using two types of radar image datasets under the conditions of few and sufficient samples. The experimental results demonstrate that our application of our proposed SAI module can significantly improve the recognition accuracy of the baseline models, which is equivalent to the existing state-of-the-art (SOTA) ATR approaches and outperforms the SOTA approaches in terms of resource consumption. Specifically, with the SAI module, our approach can achieve substantial accuracy improvements of 3.48%, 18.22%, 1.52%, and 15.03% over traditional networks in four scenarios while requiring 1/5 of the parameter count and just 1/14 of the FLOPs on average. [ABSTRACT FROM AUTHOR]

Automatic Target Recognition (ATR) from Synthetic Aperture Radar (SAR) data covers a wide range of applications. SAR ATR helps to detect and track vehicles and other objects, e.g. in disaster relief and surveillance operations. Aircraft classification covers a significant part of this research area, which differs from other SAR-based ATR tasks, such as ship and ground vehicle detection and classification, in that aircrafts are usually a static target, often remaining at the same location and in a given orientation for longer time frames. Today, there is a significant mismatch between the abundance of deep learning-based aircraft classification models and the availability of corresponding datasets. This mismatch has led to models with improved classification performance on specific datasets, but the challenge of generalizing to conditions not present in the training data (which are expected to occur in operational conditions) has not yet been satisfactorily analyzed. This paper aims to evaluate how classification performance and generalization capabilities of deep learning models are influenced by the diversity of the training dataset. Our goal is to understand the model's competence and the conditions under which it can achieve proficiency in aircraft classification tasks for high-resolution SAR images while demonstrating generalization capabilities when confronted with novel data that include different geographic locations, environmental conditions, and geometric variations. We address this gap by using manually annotated high-resolution SAR data from TerraSAR-X and TanDEM-X and show how the classification performance changes for different application scenarios requiring different training and evaluation setups. We find that, as expected, the type of aircraft plays a crucial role in the classification problem, since it will vary in shape and dimension. However, these aspects are secondary to how the SAR image is acquired, with the acquisition geometry playing the primary role. Therefore, we find that the characteristics of the acquisition are much more relevant for generalization than the complex geometry of the target. We show this for various models selected among the standard classification algorithms. • Performance of different dataset in DL models for SAR aircraft classification. • Generalization capabilities of DL models for SAR aircraft classification. • Different geographic locations, environmental conditions, and geometric variations. • Comparison using different classes of airplanes. [ABSTRACT FROM AUTHOR]

Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems. [ABSTRACT FROM AUTHOR]

The article discusses the impact of emerging technologies on nuclear deterrence in Southern Asia, focusing on China, India, and Pakistan. It highlights the pursuit of credible minimum deterrence by these nations and the influence of strategic partnerships on their nuclear capabilities. The article explores how emerging technologies such as hypersonics, cyber weapons, and AI could disrupt deterrence stability and trigger arms races. It emphasizes the need for dialogues and collaborative efforts among Southern Asian states to address shared challenges and mitigate the risks posed by emerging technologies. [Extracted from the article]

Recently, the radar high-resolution range profiles (HRRPs) have gained significant attention in the field of radar automatic target recognition due to their advantages of being easy to acquire, having a small data footprint, and providing rich target structural information. However, existing recognition methods typically focus on single-domain features, utilizing either the raw HRRP sequence or the extracted feature sequence independently. To fully exploit the multi-domain information present in HRRP sequences, this paper proposes a novel target feature fusion recognition approach. By combining a convolutional long short-term memory (ConvLSTM) network with a cascaded gated recurrent unit (GRU) structure, the proposed method leverages multi-domain and temporal information to enhance recognition performance. Furthermore, a multi-input framework based on learnable parameters is designed to improve target representation capabilities. Experimental results of 6 ship targets demonstrate that the fusion recognition method achieves superior accuracy and faster convergence compared to methods relying on single-domain sequences. It is also found that the proposed method consistently outperforms the other previous methods. And the recognition accuracy is up to 93.32% and 82.15% for full polarization under the SNRs of 20 dB and 5 dB, respectively. Therefore, the proposed method consistently outperforms the previous methods overall. [ABSTRACT FROM AUTHOR]

High-performance neural networks for synthetic aperture radar (SAR) automatic target recognition (ATR) often encounter the challenge of data scarcity. The lack of sufficient labeled SAR image datasets leads to the consideration of using simulated data to supplement the dataset. On the one hand, electromagnetic computation simulations provide high amplitude accuracy but are inefficient for large-scale datasets due to their complex computations and physical models. On the other hand, ray tracing simulations offer high geometric accuracy and computational efficiency but struggle with low amplitude correctness, hindering accurate numerical feature extraction. Furthermore, the emergence of generative adversarial networks (GANs) provides a way to generate simulated datasets, trying to balance computational efficiency with image quality. Nevertheless, the simulated SAR images generated based on random noise lack constraints, and it is also difficult to generate images that exceed the parameter conditions of the real image's training set. Hence, it is essential to integrate physics-based simulation techniques into GANs to enhance the generalization ability of the imaging parameters. In this paper, we present the SingleScene-SAR Simulator, an efficient framework for SAR image simulation that operates under limited real SAR data. This simulator integrates rasterized shooting and bouncing rays (SBR) with cycle GAN, effectively achieving both amplitude correctness and geometric accuracy. The simulated images are appropriate for augmenting datasets in target recognition networks. Firstly, the SingleScene-SAR Simulator employs a rasterized SBR algorithm to generate radar cross section (RCS) images of target models. Secondly, a specific training pattern for cycle GAN is established to translate noisy RCS images into simulated SAR images that closely resemble real ones. Finally, these simulated images are utilized for data augmentation. Experimental results based on the constructed dataset show that with only one scene SAR image containing 30 target chips, the SingleScene-SAR Simulator can efficiently produce simulated SAR images that exhibit high similarity in both spatial and statistical distributions compared with real images. By employing simulated SAR images for data augmentation, the accuracy of target recognition networks can be consistently and significantly enhanced. [ABSTRACT FROM AUTHOR]

The growing Synthetic Aperture Radar (SAR) data can build a foundation model using self-supervised learning (SSL) methods, which can achieve various SAR automatic target recognition (ATR) tasks with pretraining in large-scale unlabeled data and fine-tuning in small-labeled samples. SSL aims to construct supervision signals directly from the data, minimizing the need for expensive expert annotation and maximizing the use of the expanding data pool for a foundational model. This study investigates an effective SSL method for SAR ATR, which can pave the way for a foundation model in SAR ATR. The primary obstacles faced in SSL for SAR ATR are small targets in remote sensing and speckle noise in SAR images, corresponding to the SSL approach and signals. To overcome these challenges, we present a novel joint-embedding predictive architecture for SAR ATR (SAR-JEPA) thatleverages local masked patches to predict the multi-scale SAR gradient representations of an unseen context. The key aspect of SAR-JEPA is integrating SAR domain features to ensure high-quality self-supervised signals as target features. In addition, we employ local masks and multi-scale features to accommodate various small targets in remote sensing. By fine-tuning and evaluating our framework on three target recognition datasets (vehicle, ship, and aircraft) with four other datasets as pretraining, we demonstrate its outperformance over other SSL methods and its effectiveness as the SAR data increases. This study demonstrates the potential of SSL for the recognition of SAR targets across diverse targets, scenes, and sensors. Our codes and weights are available in https://github.com/waterdisappear/SAR-JEPA. • A large-scale pretraining is performed for synthetic aperture radar (SAR) images. • We propose a joint-embedding predictive architecture (SAR-JEPA) for speckle noise. • SAR-JEPA performs better than recent methods in small-sample classification tasks. • SAR-JEPA shows improved performance with increasing data volume. [ABSTRACT FROM AUTHOR]

In recent years, radar automatic target recognition (RATR) utilizing high-resolution range profiles (HRRPs) has received significant attention. Approaches based on deep learning have demonstrated remarkable efficacy in HRRP recognition tasks. However, the performance of neural networks is notably vulnerable to noise, leading to a detrimental effect on their recognition accuracy and overall robustness. To address this issue, a residual scattering attention network (RSAN) is proposed for HRRP target recognition, which comprises a residual scattering network, ResNet18, and a self-attention module. The residual scattering network is designed to suppress noise components and extract noise-robust features. It is derived from the improvement of a scattering network and does not need to learn parameters from the data. ResNet18 is employed for the purpose of extracting a deep representation of scattering features for HRRPs. Furthermore, a self-attention module is integrated into ResNet18, enabling the model to focus on target regions, thereby enhancing its feature-learning capability. The effectiveness and noise robustness of the proposed method are validated through experiments conducted on two measured datasets. [ABSTRACT FROM AUTHOR]

High Resolution Range Profiles (HRRPs) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training samples to generate good performance, which could be a severe challenge under non‐cooperative circumstances. Currently, deep learning based models treat HRRPs as sequences, which may lead to ignorance of the internal relationship of range cells. This letter proposes HRRPGraphNet, a novel graph‐theoretic approach, whose primary innovation is the use of the graph‐theory of HRRP which models the spatial relationships among range cells through a range cell amplitude‐based node vector and a range‐relative adjacency matrix, enabling efficient extraction of both local and global features in noneuclidean space. Experiments on the aircraft electromagnetic simulation dataset confirmed HRRPGraphNet's superior accuracy and robustness compared with existing methods, particularly in limited training sample condition. This underscores the potential of graph‐driven innovations in enhancing HRRP‐based RATR, offering a significant advancement over sequence‐based methods. [ABSTRACT FROM AUTHOR]

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Automatic Target Recognition (ATR) synthetic aperture radar (SAR) imagery is the primary application in detecting and recognizing military vehicles such as armored vehicles, tanks, bulldozers, cannons etc. A robust method that employs Markov Random Field (MRF) and hybrid Googlenet and VGGnet (VGG-GoogleNet) Convolutional Neural Network (CNN) has been proposed in this paper. This study proposes a hybrid deep learning-based automatic target classification system for identifying military vehicles in Synthetic Aperture Radar images. The system employs a primary CNN combined with MRF to categorize the images of military vehicles. The performance of SAR images is degraded by speckle noise, and hence, we performed SAR image despeckling to reduce speckle noise in the images using the improved Adaptive Morphological filter. After despeckling, the military vehicles or targets are detected from the despeckled images by the Markov Random Field segmentation algorithm. Finally, a hybrid Googlenet and VGGnet Convolutional Neural network with an SVM classifier is adopted for classifying and recognizing the military targets from the SAR images. The proposed Markov random field with the hybrid VGG-GoogleNet pre-trained CNN notably improves the recognition accuracy compared with the conventional deep-learning CNN-based methods. [ABSTRACT FROM AUTHOR]

The Police Robot for Inspection and Mapping of Underwater Evidence (PRIME) is an uncrewed surface vehicle (USV) currently being developed for underwater search and recovery teams to assist in crime scene investigation. The USV maps underwater scenes using sidescan sonar (SSS). Test exercises use a clothed mannequin lying on the seafloor as a target object to evaluate system performance. A robust, automated method for detecting human body-shaped objects is required to maximise operational functionality. The use of a convolutional neural network (CNN) for automatic target recognition (ATR) is proposed. SSS image data acquired from four different locations during previous missions were used to build a dataset consisting of two classes, i.e., a binary classification problem. The target object class consisted of 166 196 × 196 pixel image snippets of the underwater mannequin, whereas the non-target class consisted of 13,054 examples. Due to the large class imbalance in the dataset, CNN models were trained with six different imbalance ratios. Two different pre-trained models (ResNet-50 and Xception) were compared, and trained via transfer learning. This paper presents results from the CNNs and details the training methods used. Larger datasets are shown to improve CNN performance despite class imbalance, achieving average F1 scores of 97% in image classification. Average F1 scores for target vs background classification with unseen data are only 47% but the end result is enhanced by combining multiple weak classification results in an ensemble average. The combined output, represented as a georeferenced heatmap, accurately indicates the target object location with a high detection confidence and one false positive of low confidence. The CNN approach shows improved object detection performance when compared to the currently used ATR method. [ABSTRACT FROM AUTHOR]

With the prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning-based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning-based methods can achieve outstanding recognition performance on the condition that an abundance of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Therefore, SAR target recognition in the situation of few-shot, where only a scarce few labeled samples are available, is a fundamental problem that needs to be solved. In this paper, a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) is put forward to specially tackle the few-shot SAR ATR tasks. To be specific, a feature-extraction network based on a customized and region-aware convolution is first developed. This network can adaptively adjust convolutional kernels and their receptive fields according to each SAR image's own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, an enhanced prototypical network is proposed. This network can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset, the OpenSARShip dataset, and the SAMPLE+ dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) plays a pivotal role in civilian and military applications. However, the limited labeled samples present a significant challenge in deep learning-based SAR ATR. Few-shot learning (FSL) offers a potential solution, but models trained with limited samples may produce a high probability of incorrect results that can mislead decision-makers. To address this, we introduce uncertainty estimation into SAR ATR and propose Prior knowledge-guided Evidential Deep Learning (Prior-EDL) to ensure reliable recognition in FSL. Inspired by Bayesian principles, Prior-EDL leverages prior knowledge for improved predictions and uncertainty estimation. We use a deep learning model pre-trained on simulated SAR data to discover category correlations and represent them as label distributions. This knowledge is then embedded into the target model via a Prior-EDL loss function, which selectively uses the prior knowledge of samples due to the distribution shift between simulated data and real data. To unify the discovery and embedding of prior knowledge, we propose a framework based on the teacher-student network. Our approach enhances the model's evidence assignment, improving its uncertainty estimation performance and target recognition accuracy. Extensive experiments on the MSTAR dataset demonstrate the effectiveness of Prior-EDL, achieving recognition accuracies of 70.19% and 92.97% in 4-way 1-shot and 4-way 20-shot scenarios, respectively. For Out-Of-Distribution data, Prior-EDL outperforms other uncertainty estimation methods. The code is available at https://github.com/Xiaoyan-Zhou/Prior-EDL/. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNNs) are susceptible to adversarial attacks. In this study, we proposed an SAR black-box local adversarial attack algorithm named attention heat mapbased black-box local adversarial attack (AH-BLAA). First, we designed an attention heat map extraction module combined with the layer-wise relevance propagation (LRP) algorithm to obtain the high concerning areas of the SAR-ATR models. Then, to generate SAR adversarial attack examples, we designed a perturbation generator module, introducing the structural dissimilarity (DSSIM) metric in the loss function to limit image distortion and the differential evolution (DE) algorithm to search for optimal perturbations. Experimental results on the MSTAR and FUSAR-Ship datasets showed that compared with existing adversarial attack algorithms, the attack success rate of the AH-BLAA algorithm increased by 0.63% to 33.59% and 1.05% to 17.65%, respectively. Moreover, the lowest perturbation ratios reached 0.23% and 0.13%, respectively. [ABSTRACT FROM AUTHOR]

Sonar automatic target recognition (ATR) systems suffer from complex acoustic scattering, background clutter, and waveguide effects that are ever-present in the ocean. Traditional signal processing techniques often struggle to distinguish targets when noise and complicated target geometries are introduced. Recent advancements in machine learning and wavelet theory offer promising directions for extracting informative features from sonar return data. This work introduces a feature extraction and dimensionality reduction technique using the invariant scattering transform and Sparse Multi-view Discriminant Analysis for identifying highly informative features in the PONDEX09/PONDEX10 datasets. The extracted features are used to train a support vector machine classifier that achieves an average classification accuracy of 97.3% using six unique targets. [ABSTRACT FROM AUTHOR]

Deep learning network has the advantages of strong learning ability, strong adaptability, and good portability. Therefore, synthetic aperture radar (SAR) automatic target recognition (ATR) based on deep network is widely used in both military and civilian fields. However, due to the imaging conditions, radar angle, imaging distance, and other reasons, it is difficult to obtain efficient and usable SAR image datasets. SAR images’ recognition under small sample conditions is still a challenging problem. In this paper, a SAR target recognition method based on multi-view differential feature fusion network is proposed to address this problem. Considering the correspondence between RCS and target features, the network extracts dissimilarities between features from SAR images of different angles of the same target and fuses them with the original features of one angle to form new features, which enriches the available training data. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) public dataset show that the proposed method has a higher target recognition rate than other deep network methods, as well as single angle input recognition methods. [ABSTRACT FROM AUTHOR]

With the rapid development of the modern world, it is imperative to achieve effective and efficient monitoring for territories of interest, especially for the broad ocean area. For surveillance of ship targets at sea, a common and powerful approach is to take advantage of satellite synthetic aperture radar (SAR) systems. Currently, using satellite SAR images for ship classification is a challenging issue due to complex sea situations and the imaging variances of ships. Fortunately, the emergence of advanced satellite SAR sensors has shed much light on the SAR ship automatic target recognition (ATR) task, e.g., utilizing dual-polarization (dual-pol) information to boost the performance of SAR ship classification. Therefore, in this paper we have developed a novel cross-polarimetric interaction network (CPINet) to explore the abundant polarization information of dual-pol SAR images with the help of deep learning strategies, leading to an effective solution for high-performance ship classification. First, we establish a novel multiscale deep feature extraction framework to fully mine the characteristics of dual-pol SAR images in a coarse-to-fine manner. Second, to further leverage the complementary information of dual-pol SAR images, we propose a mixed-order squeeze–excitation (MO-SE) attention mechanism, in which the first- and second-order statistics of the deep features from one single-polarized SAR image are extracted to guide the learning of another polarized one. Then, the intermediate multiscale fused and MO-SE augmented dual-polarized deep feature maps are respectively aggregated by the factorized bilinear coding (FBC) pooling method. Meanwhile, the last multiscale fused deep feature maps for each single-polarized SAR image are also individually aggregated by the FBC. Finally, four kinds of highly discriminative deep representations are obtained for loss computation and category prediction. For better network training, the gradient normalization (GradNorm) method for multitask networks is extended to adaptively balance the contribution of each loss component. Extensive experiments on the three- and five-category dual-pol SAR ship classification dataset collected from the open and free OpenSARShip database demonstrate the superiority and robustness of CPINet compared with state-of-the-art methods for the dual-polarized SAR ship classification task. [ABSTRACT FROM AUTHOR]

In military contexts, synthetic aperture radar (SAR) automatic target recognition (ATR) models frequently encounter the challenge of imbalanced data, resulting in a noticeable degradation in the recognition performance. Therefore, the authors propose a cost‐sensitive awareness generative adversarial network (CAGAN) model, aiming to improve the robustness of ATR models under imbalanced data. Firstly, the authors introduce a convolutional neural network (DCNN) to extract features. Then, the synthetic minority over‐sampling technique (SMOTE) is applied to achieve feature‐level balancing for the minority category. Finally, a CAGAN model is designed to perform the final classification task. In this process, the GAN‐based adversarial training mechanism enriches the diversity of training samples, making the ATR model more comprehensive in understanding different categories. In addition, the cost matrix increases the penalty for misclassification results and further improves the classification accuracy. Simultaneously, the cost‐sensitive awareness can accurately adjust the cost matrix through training data, thus reducing dependence on expert knowledge and improving the generalisation performance of the ATR model. This model is an end‐to‐end ATR scheme, which has been experimentally validated on the MSTAR and OpenSARship datasets. Compared to other methods, the proposed method exhibits strong robustness in dealing with various imbalanced scenarios and significant generalisation capability across different datasets. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) enables the acquisition of high-resolution imagery even under severe meteorological and illumination conditions. Its utility is evident across a spectrum of applications, particularly in automatic target recognition (ATR). Since SAR samples are often scarce in practical ATR applications, there is an urgent need to develop sample-efficient augmentation techniques to augment the SAR images. However, most of the existing generative approaches require an excessive amount of training samples for effective modeling of the SAR imaging characteristics. Additionally, they show limitations in augmenting the interesting target samples while maintaining image recognizability. In this study, we introduce an innovative single-sample image generation approach tailored to SAR data augmentation. To closely approximate the target distribution across both the spatial layout and local texture, a multi-level Generative Adversarial Network (GAN) architecture is constructed. It comprises three distinct GANs that independently model the structural, semantic, and texture patterns. Furthermore, we introduce multiple constraints including prior-regularized noise sampling and perceptual loss optimization to enhance the fidelity and stability of the generation process. Comparative evaluations against the state-of-the-art generative methods demonstrate the superior performance of the proposed method in terms of generation diversity, recognizability, and stability. In particular, its advantages over the baseline method are up to 0.2 and 0.22 in the SIFID and SSIM, respectively. It also exhibits stronger robustness in the generation of images across varying spatial sizes. [ABSTRACT FROM AUTHOR]

Current synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms primarily operate under the closed-set assumption, implying that all target classes have been previously learned during the training phase. However, in open scenarios, they may encounter target classes absent from the training set, thereby necessitating an open set recognition (OSR) challenge for SAR-ATR. The crux of OSR lies in establishing distinct decision boundaries between known and unknown classes to mitigate confusion among different classes. To address this issue, we introduce a novel framework termed reinforced class separability for SAR target open set recognition (RCS-OSR), which focuses on optimizing prototype distribution and enhancing the discriminability of features. First, to capture discriminative features, a cross-modal causal features enhancement module (CMCFE) is proposed to strengthen the expression of causal regions. Subsequently, regularized intra-class compactness loss (RIC-Loss) and intra-class relationship aware consistency loss (IRC-Loss) are devised to optimize the embedding space. In conjunction with joint supervised training using cross-entropy loss, RCS-OSR can effectively reduce empirical classification risk and open space risk simultaneously. Moreover, a class-aware OSR classifier with adaptive thresholding is designed to leverage the differences between different classes. Consequently, our method can construct distinct decision boundaries between known and unknown classes to simultaneously classify known classes and identify unknown classes in open scenarios. Extensive experiments conducted on the MSTAR dataset demonstrate the effectiveness and superiority of our method in various OSR tasks. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) automatic target recognition (ATR) technology has seen significant advancements. Despite these advancements, the majority of research still operates under the closed-set assumption, wherein all test samples belong to classes seen during the training phase. In real-world applications, however, it is common to encounter targets not previously seen during training, posing a significant challenge to the existing methods. Ideally, an ATR system should not only accurately identify known target classes but also effectively reject those belonging to unknown classes, giving rise to the concept of open set recognition (OSR). To address this challenge, we propose a novel approach that leverages the unique capabilities of the Capsule Network and the Kullback-Leibler divergence (KLD) to distinguish unknown classes. This method begins by deeply mining the features of SAR targets using the Capsule Network and enhancing the separability between different features through a specially designed loss function. Subsequently, the KLD of features between a testing sample and the center of each known class is calculated. If the testing sample exhibits a significantly larger KLD compared to all known classes, it is classified as an unknown target. The experimental results of the SAR-ACD dataset demonstrate that our method can maintain a correct identification rate of over 95% for known classes while effectively recognizing unknown classes. Compared to existing techniques, our method exhibits significant improvements. [ABSTRACT FROM AUTHOR]

Polarimetric high-resolution range profile (HRRP), with its rich polarimetric and spatial information, has become increasingly important in radar automatic target recognition (RATR). This study proposes an interpretable target-aware vision Transformer (ITAViT) for polarimetric HRRP target recognition with a novel attention loss. In ITAViT, we initially fuse the polarimetric features and the amplitude of polarimetric HRRP with a polarimetric preprocessing layer (PPL) to obtain the feature map as the input of the subsequent network. The vision Transformer (ViT) is then used as the backbone to automatically extract both local and global features. Most importantly, we introduce a novel attention loss to optimize the alignment between the attention map and the HRRP span. Thus, it can improve the difference between the target and the background, and enable the model to more effectively focus on real target areas. Experiments on a simulated X-band dataset demonstrate that our proposed ITAViT outperforms comparative models under various experimental conditions. Ablation studies highlight the effectiveness of polarimetric preprocessing and attention loss. Furthermore, the visualization of the self-attention mechanism suggests that attention loss enhances the interpretability of the network. [ABSTRACT FROM AUTHOR]

Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations. This paper studies the synthetic-to-measured (S2M) transfer setting, where an attacker generates adversarial perturbation based solely on synthetic data and transfers it against victim models trained with measured data. Compared with the current measured-to-measured (M2M) transfer setting, our approach does not need direct access to the victim model or the measured SAR data. We also propose the transferability estimation attack (TEA) to uncover the adversarial risks in this more challenging and practical scenario. The TEA makes full use of the limited similarity between the synthetic and measured data pairs for blind estimation and optimization of S2M transferability, leading to feasible surrogate model enhancement without mastering the victim model and data. Comprehensive evaluations based on the publicly available synthetic and measured paired labeled experiment (SAMPLE) dataset demonstrate that the TEA outperforms state-of-the-art methods and can significantly enhance various attack algorithms in computer vision and remote sensing applications. Codes and data are available at https://github.com/scenarri/S2M-TEA. [ABSTRACT FROM AUTHOR]

Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems.

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers. [ABSTRACT FROM AUTHOR]

Recent research has revealed that the deep neural network (DNN)-based synthetic-aperture radar (SAR) automatic target recognition (ATR) techniques are vulnerable to adversarial examples, which poses significant security risks for their deployment in real-world systems. At the same time, the adversarial examples often exhibit transferability across DNN models, whereby when they are generated on the surrogate model they can also attack other target models. As the significant property in black-box scenarios, transferability has been enhanced by various methods, among which input transformations have demonstrated excellent effectiveness. However, we find that existing transformations suffer from limited enhancement of transferability due to the unique imaging mechanism and scattering characteristics of SAR images. To overcome this issue, we propose a novel method called intra-class transformations and inter-class nonlinear fusion attack (ITINFA). It enhances transferability from two perspectives: intra-class single image transformations and inter-class multiple images fusion. The intra-class transformations module utilizes a series of diverse transformations that align with the intrinsic characteristics of SAR images to obtain a more stable gradient update direction and prevent the adversarial examples from overfitting the surrogate model. The inter-class fusion strategy incorporates the information from other categories in a nonlinear manner, effectively enhances the feature fusion effect, and guides the misclassification of adversarial examples. Extensive experiments on the MSTAR dataset and SEN1-2 dataset demonstrate that ITINFA exhibits significantly better transferability than the existing transfer-based methods, with the average transfer attack success rate increases exceeding 8% for single models and over 4% for ensemble models. [ABSTRACT FROM AUTHOR]

The presence of side-lobe noise degrades the image quality and adversely affects the performance of inverse synthetic aperture radar (ISAR) image understanding applications, such as automatic target recognition (ATR), target detection, etc. However, methods reliant on data processing, such as windowing, inevitably encounter resolution reduction, and current deep learning approaches under-appreciate the sparsity inherent in ISAR images. Taking the above analysis into consideration, a convolutional neural network-based process for ISAR side-lobe noise training is proposed in this paper. The proposed processing, based on the ISAR images sparsity characteristic analysis, undergoes enhancements in three core ideas, dataset construction, prior network design, and loss function improvements. In the realm of dataset construction, we introduce a bin-by-bin fast clean algorithm and accelerate the processing speed significantly on the basis of image complete information. Subsequently, a spatial attention layer is incorporated into the prior network designed to augment the network's focus on the crucial regions of ISAR images. In addition, a loss function featuring a weighting factor is devised to ensure the precise recovery of the strong scattering point. Simulation experiments demonstrate that the proposed process achieves significant improvements in both quantitative and qualitative results over the classical denoise methods. [ABSTRACT FROM AUTHOR]

Context. Target recognition is a priority in military affairs. This task is complicated by the fact that it is necessary to recognize moving objects, different terrain and landscape create obstacles for recognition. Combat actions can take place at different times of the day, accordingly, it is necessary to take into account the perspective of lighting and general lighting. It is necessary to detect the object in the video by segmenting the video frames, recognize and classify. Objective of the study is to develop a technology for the analysis of the development of a technology for recognizing targets in real time as a component of the fire control system, due to the use of artificial intelligence, YOLO and machine learning. Method. The article develops a video stream analysis technology for automatic target recognition of the fire control system based on machine learning. The paper proposes the development of a target recognition module as a component of the fire control system within the framework of the proposed information technology using artificial intelligence. The YOLOv8 pattern recognition model family was used to develop the target recognition module. The methods used during the study of the formed dataset. – Bounding Box: Noise – Up to 15% of pixels (limiting frame: adding salt and pepper noise to the image – up to 15% of pixels). – Bounding Box: Blur – Up to 2.5px (bounding box: adding Gaussian blur to the image – up to 2.5 pixels). – Cutout – 3 boxes with 10% size each (cut out a part of the image – 3 boxes of 10% size each). – Brightness Between –25% and +25% (changing the brightness of the image to increase the resistance of the model to changes in lighting and camera settings – from –25% to +25%). – Rotation – Between –15° and +15° (rotation of the image object – clockwise or counterclockwise by degrees from –15° to +15°). – Flip – Horizontal (flip the image object horizontally). Results. The data is collected from open sources, in particular, from videos posted in open sources on the YouTube platform. The main task of data preprocessing is the classification of three classes of objects on video or in real time – APC, BMP and TANK. The dataset is formed using the Roboflow platform based on the labeling tools and subsequently the augmentation tools. The dataset consists of 1193 unique images – approximately equally for each class. The training was conducted using Google Colab resources. It took 100 epochs to train the model. Conclusions. Analysis is performed according to mAP50 (average precision as 0.85), mAP50-95 (0.6), precision (0.89) and recall (0.75). Big losses are due to the fact that the background was not taken into account during the research – training the module on the basis of confirmed data (images) of the background without technology. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN) can generate diverse and high-resolution images for data augmentation. However, when GAN is applied to the synthetic aperture radar (SAR) dataset, the generated categories are not of the same quality. The unrealistic category will affect the performance of the subsequent automatic target recognition (ATR). To overcome the problem, we propose a reinforced constraint filtering with compensation afterwards GAN (RCFCA-GAN) algorithm to generate SAR images. The proposed algorithm includes two stages. We focus on improving the quality of easily generated categories in Stage 1. Then, we record the categories that are hard to generate and compensate by using traditional augmentation methods in Stage 2. Thus, the overall quality of the generated images is improved. We conduct experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset. Recognition accuracy and Fréchet inception distance (FID) acquired by the proposed algorithm indicate its effectiveness. [ABSTRACT FROM AUTHOR]

Micro‐Doppler effect is a vital feature of a target that reflects its oscillatory motions apart from bulk motion and provides an important evidence for target recognition with radars. However, establishing the micro‐Doppler database poses a great challenge, since plenty of experiments are required to get the micro‐Doppler signatures of different targets for the purpose of analyses and interpretations with radars, which are dramatically limited by high cost and time‐consuming. Aiming to overcome these limits, a low‐cost and powerful simulation platform of the micro‐Doppler effects is proposed based on time‐domain digital coding metasurface (TDCM). Owing to the outstanding capabilities of TDCM in generating and manipulating nonlinear harmonics during wave‐matter interactions, it enables to supply rich and high‐precision electromagnetic signals with multiple micro‐Doppler frequencies to describe the micro‐motions of different objects, which are especially favored for the training of artificial intelligence algorithms in automatic target recognition and benefit a host of applications like imaging and biosensing. [ABSTRACT FROM AUTHOR]

The utilization of deep learning in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) has witnessed a recent surge owing to its remarkable feature extraction capabilities. Nonetheless, deep learning methodologies are often encumbered by inadequacies in labeled data and the protracted nature of training processes. To address these challenges and offer an alternative avenue for accurately extracting image features, this paper puts forth a novel and distinctive network dubbed the Capsule Broad Learning System Network for robust SAR ATR (CBLS-SARNET). This novel strategy is specifically tailored to cater to small-sample SAR ATR scenarios. On the one hand, we introduce a United Division Co-training (UDC) Framework as a feature filter, adeptly amalgamating CapsNet and the Broad Learning System (BLS) to enhance network efficiency and efficacy. On the other hand, we devise a Parameters Sharing (PS) network to facilitate secondary learning by sharing the weight and bias of BLS node layers, thereby augmenting the recognition capability of CBLS-SARNET. Experimental results unequivocally demonstrate that our proposed CBLS-SARNET outperforms other deep learning methods in terms of recognition accuracy and training time. Furthermore, experiments validate the generalization and robustness of our novel method under various conditions, including the addition of blur, Gaussian noise, noisy labels, and different depression angles. These findings underscore the superior generalization capabilities of CBLS-SARNET across diverse SAR ATR scenarios. [ABSTRACT FROM AUTHOR]

Learning visual models of object classes conventionally require hundreds or a large number of training samples. Conventional gradient-based approaches for target recognition require lot of data to be trained on and require exhaustive training with high computational expense. Hence, when a new condition or untrained data is encountered, such systems inadequately misconfigure newly learned feature sets in the trained model. This misconfigures the structure of re-learned features and is then carried out in subsequent recognition stages. Thus, a development in this scenario with low training time will allow us to fend of this disadvantage. This study presents a new automatic target recognition framework that gives the enhanced performance of target-recognition system when several imaging sensors are connected with one another. This is in contrast with traditional automatic target recognition frameworks, which utilizes one-on-one computational model over synthetic-aperture radar image-processing systems. The work comprises of a learning-based classifications strategy when dealing with sharing of learned parameters over the network to discern critical changes in target-recognition performance by utilizing a novel one-shot learning-based reconfigurable learning network for image processing platform. This upgrades the networked connected CCTV and multiview synthetic-aperture radar image object identification and recognition process. [ABSTRACT FROM AUTHOR]

In modern surveillance, automatic target recognition (ATR) is a critical challenge, necessitating rapid and precise object identification, especially in military and disaster response scenarios. This research presents a comprehensive framework for ground target classification, focusing on Synthetic Aperture Radar (SAR) imagery. Harnessing the Moving and Stationary Target Acquisition and Recognition (MSTAR) Mixed Targets dataset, this study integrates Convolutional Neural Networks (CNNs) into SAR image analysis. Transfer learning emerges as a key strategy, adapting insights from pre-trained CNNs to the intricacies of target recognition in SAR imagery. This approach outperforms traditional methods, enhancing efficiency amid dataset annotation challenges. Noteworthy CNN architectures including DarkNet-19, DenseNet-121, InceptionV4, ResNet-152, and VGG19 are explored. The ResNet-152 model demonstrates exceptional performance, emerging as a leading contender with a remarkable testing accuracy of 98.56% when trained from scratch. Furthermore, by employing transfer learning, the model's accuracy may be further enhanced to reach 98.81% on the testing dataset. This research signifies a transformative SAR imagery path guided by pre-trained CNNs and transfer learning. It reshapes ATR's accuracy and efficiency, pointing to a future where innovation surmounts challenges previously deemed insurmountable. [ABSTRACT FROM AUTHOR]

Image feature extraction and matching constitute fundamental steps in computer vision and image analysis, enabling various applications ranging from object recognition to scene reconstruction. Object recognition is one of the major applications of artificial intelligence. Since last two decades, different techniques for object recognition were given by researchers from across the world. This paper presents a novel approach for automatic target recognition in autonomous weapons by matching connected graph of feature pixels. The Moving and Stationary Target Acquisition and Recognition (MSTAR) is taken for experimental purpose. The Proposed model has three stages for a target recognition; Image Denoising, Feature extraction & graph generation, and feature matching. Firstly, a sample image of targets taken from the MSTAR is taken as an input. Further, input sample is de-noised and features are extracted using Speeded-Up Robust Features (SURF) algorithm. Thereafter, a graph is created using feature pixels and this complete process is repeated with test image. Further, both graphs are compared using a proposed feature graph matching algorithm which results an recognition accuracy score. Proposed model is tested over the MSTAR dataset and it resulted in varying accuracy at different feature matching thresholds. [ABSTRACT FROM AUTHOR]

This article discusses the use of a deep learning neural network (DLNN) as a tool to improve maritime safety by classifying the potential threat to shipping posed by unexploded ordnance (UXO) objects. Unexploded ordnance poses a huge threat to maritime users, which is why navies and non-governmental organisations (NGOs) around the world are using dedicated advanced technologies to counter this threat. The measures taken by navies include mine countermeasure units (MCMVs) and mine-hunting technology, which relies on the use of sonar imagery to detect and classify dangerous objects. The modern mine-hunting technique is generally divided into three stages: detection and classification, identification, and neutralisation/disposal. The detection and classification stage is usually carried out using sonar mounted on the hull of a ship or on an underwater vehicle. There is now a strong trend to intensify the use of more advanced technologies, such as synthetic aperture sonar (SAS) for high-resolution data collection. Once the sonar data has been collected, military personnel examine the images of the seabed to detect targets and classify them as mine-like objects (MILCO) or non mine-like objects (NON-MILCO). Computer-aided detection (CAD), computer-aided classification (CAC) and automatic target recognition (ATR) algorithms have been introduced to reduce the burden on the technical operator and reduce post-mission analysis time. This article describes a target classification solution using a DLNN-based approach that can significantly reduce the time required for post-mission data analysis during underwater reconnaissance operations. [ABSTRACT FROM AUTHOR]

A 3-D scattering centre model-based synthetic aperture radar (SAR) automatic target recognition (ATR) method is proposed. Multi-level dominant scattering areas (DSAs) are generated from the test sample and model predicted target images, which can describe the target region and scattering centres distribution from coarse to fine. The DSA matching is conducted at each level using the morphological erosion operation and Euclidean distance transform. Finally, the energy of the region residuals is taken as the distance measure between the test sample and different target models so as to confirm the target label. The 3-D scattering centre model can provide very complete descriptions of the target. In addition, the designed distance measure comprehensively considers the possible nonlinear transformations between the model and test image using the morphological erosion operation and Euclidean distance transform. Experiments are performed on the electromagnetic (EM) simulated data of three military targets. [ABSTRACT FROM AUTHOR]

The ARGO-USV (Unmanned Surface Vehicle for ARchaeological GeO-application) is a technological project involving a marine drone aimed at devising an innovative methodology for marine geological and geomorphological investigations in shallow areas, usually considered critical areas to be investigated, with the help of traditional vessels. The methodological approach proposed in this paper has been implemented according to a multimodal mapping technique involving the simultaneous and integrated use of both optical and geoacoustic sensors. This approach has been enriched by tools based on artificial intelligence (AI), specifically intended to be installed onboard the ARGO-USV, aimed at the automatic recognition of submerged targets and the physical characterization of the seabed. This technological project is composed of a main command and control system and a series of dedicated sub-systems successfully tested in different operational scenarios. The ARGO drone is capable of acquiring and storing a considerable amount of georeferenced data during surveys lasting a few hours. The transmission of all acquired data in broadcasting allows the cooperation of a multidisciplinary team of specialists able to analyze specific datasets in real time. These features, together with the use of deep-learning-based modules and special attention to green-compliant construction phases, are the particular aspects that make ARGO-USV a modern and innovative project, aiming to improve the knowledge of wide coastal areas while minimizing the impact on these environments. As a proof-of-concept, we present the extensive mapping and characterization of the seabed from a geoarchaeological survey of the underwater Roman harbor of Puteoli in the Gulf of Naples (Italy), demonstrating that deep learning techniques can work synergistically with seabed mapping methods. [ABSTRACT FROM AUTHOR]

Radar Automatic Target Recognition (RATR) based on high-resolution range profile (HRRP) has received intensive attention in recent years. In practice, RATR usually needs not only to recognize in-library samples but also to reject out-of-library samples. However, most rejection methods lack a specific and accurate description of the underlying distribution of HRRP, which limits the effectiveness of the rejection task. Therefore, this paper proposes a novel rejection method for HRRP, named Deep Multi-modal Support Vector Data Description (DMMSVDD). On the one hand, it forms a more compact rejection boundary with the Gaussian mixture model in consideration of the high-dimensional and multi-modal structure of HRRP. On the other hand, it captures the global temporal information and channel-dependent information with a dual attention module to gain more discriminative structured features, which are optimized jointly with the rejection boundary. In addition, a semi-supervised extension is proposed to refine the boundary with available out-of-library samples. Experimental results based on measured data show that the proposed methods demonstrate significant improvement in the HRRP rejection performance. [ABSTRACT FROM AUTHOR]

Real-world deployment of Automatic Target Recognition (ATR) in Synthetic Aperture Radar (SAR) often faces challenges due to the computational demands of Convolutional Neural Networks (CNNs). This paper proposes an innovative solution, combining Iterative Transfer Learning (ITL) with a lightweight branched-CNN architecture, to address these limitations. The proposed approach cleverly decomposes the multi-class classification problem into smaller, binary subtasks. Each branch in the network, consisting of specialized Fully Connected (FC) layers, acts as an expert in identifying a specific target class. These branches are trained sequentially, focusing on one class at a time using a One-vs-All (OVA) strategy. This simplification reduces the model’s complexity, enabling efficient performance even with a smaller CNN. Furthermore, the branched architecture significantly alleviates the need for a large labeled dataset. By dividing the problem into binary tasks, the model learns effectively even with limited data, making it suitable for resource-constrained scenarios. During inference, the branch with the highest output probability determines the final target class. The model’s performance was adjusted by meticulous hyperparameter tuning of batch size, learning rate, and number of epochs, resulting in exceptional accuracy on the MSTAR dataset. Featuring a mere 0.2 million parameters and 0.2 million Multiply-Accumulate Operations (MACCs), it achieves an impressive accuracy of 98.48% under standard conditions. This model performs better than DenseNet-161, a substantially bigger model with 130 times more parameters and nearly 1000 times more MACCs. Furthermore, the model consistently achieved accuracies of 97.83%, 98.15%, and 98.53% across diverse operating conditions, solidifying its potential for SAR applications.

Synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep neural networks (DNNs) are vulnerable to attacks of adversarial examples. Universal adversarial attack algorithms can help evaluate and improve the robustness of the SAR-ATR models and have become a research hotspot. However, current universal adversarial attack algorithms have limitations. First, considering the difficulty in obtaining information on the attacking SAR-ATR models, there is an urgent need to design a universal adversarial attack algorithm under a black-box scenario. Second, given the difficulty of acquiring synthetic aperture radar images, the effectiveness of attacks under small-sample conditions requires improvement. To address these limitations, this study proposed a black-box universal adversarial attack algorithm: transferable universal adversarial network (TUAN). Based on the idea of the generative adversarial network, we implemented the game of generator and attenuator to improve the transferability of universal adversarial perturbation (UAP). We designed loss functions for the generator and the attenuator, respectively, which can effectively improve the success rate of black-box attacks and the stealthiness of attacks. In addition, U-Net was used as a network structure of the generator and the attenuator to fully learn the distribution of examples, thereby enhancing the attack success rate under small-sample conditions. The TUAN attained a higher black-box attack success rate and superior stealthiness than up-to-date UAP algorithms in non-targeted and targeted attacks.

In this article, we explore a cutting-edge concept known as class incremental learning (CIL) in novel category discovery for synthetic aperture radar (SAR) targets (CNTs). This innovative task involves the challenge of identifying categories within unlabeled datasets by utilizing a provided labeled dataset as reference. In contrast to the conventional category discover approaches, our method introduces novel categories without relying on old labeled classes and effectively mitigates the issue of catastrophic forgetting. Specifically, to reduce the bias of the established categories toward unknown ones, CNT extracts representational information via self-supervised learning, gleaned directly from the SAR data itself to facilitate generalization. To retain the model's competence in classifying previously acquired knowledge, we employ a dual strategy incorporating the rehearsal of base category feature prototypes and the application of knowledge distillation. Our methodology integrates multiview and pseudolabeling strategies. In addition, we introduce a novel approach that focuses on enhancing the discernibility of class spaces. This strategy primarily ensures distinct separation of the unlabeled classes from base class prototypes, and imposes stringent constraints on the internal relationships among individual samples and their corresponding perspectives. To the best of our knowledge, this is the first study on category discovery in the CIL scenario. The experimental results show that our method significantly improves the performance on SAR images compared to the previous optimal method, which indicates the effectiveness of our method.

ABSTRACT In various applications of radar imagery, one of the fundamental problems is mainly linked to the analysis and interpretation of the images provided, in particular the recognition of moving and/or fixed targets. This task has become more difficult due to the large volume of radar data. This led to the use of automatic processing and target recognition methods. The aim of this study is to explore data fusion in SAR (Synthetic Aperture Radar) image classifiers. To this end, we propose a new approach to combine three CNN (Convolutional Neural Networks) architectures with several fusion rules. First, we perform a training process of three deep learning architectures; namely, the basic CNN, the Xception, and the AlexNet architectures. Then, two fusion techniques are proposed. The first one deals with the majority rule and the second uses a neural networks to combine the decision outputs obtained from three elementary classifiers to achieve the final decision. To evaluate and validate the proposed approach, the MSTAR (Moving and Stationary Target Acquisition and Recognition) dataset is used. The obtained performances of the fusion techniques improve the recognition rate with a final accuracy of 99.59% for the majority rule and 99.51 for the neural network-based rule, which surpasses the accuracy of each individual CNN. [JJCIT 2023; 9(4.000): 347-359]