Search

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]

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]

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]

Radar data can be presented in various forms, unlike visible data. In the field of radar target recognition, most current work involves point cloud data due to computing limitations, but this form of data lacks useful information. This paper proposes a semantic segmentation network to process high-dimensional data and enable automatic radar target recognition. Rather than relying on point cloud data, which is common in current radar automatic target recognition algorithms, the paper suggests using a radar heat map of high-dimensional data to increase the efficiency of radar data use. The radar heat map provides more complete information than point cloud data, leading to more accurate classification results. Additionally, this paper proposes a dimension collapse module based on a vision transformer for feature extraction between two modules with dimension differences during dimension changes in high-dimensional data. This module is easily extendable to other networks with high-dimensional data collapse requirements. The network's performance is verified using a real radar dataset, showing that the radar semantic segmentation network based on a vision transformer has better performance and fewer parameters compared to segmentation networks that use other dimensional collapse methods. [ABSTRACT FROM AUTHOR]

The efficiency and accuracy of target recognition in synthetic aperture radar (SAR) imagery have seen significant progress lately, stemming from the encouraging advancements of automatic target recognition (ATR) technology based on deep learning. However, the development of a deep learning-based SAR ATR algorithm still faces two critical challenges: the difficulty of feature extraction caused by the unique nature of SAR imagery and the scarcity of datasets caused by the high acquisition cost. Due to its desirable image nature and extremely low acquisition cost, the simulated optical target imagery obtained through computer simulation is considered a valuable complement to SAR imagery. In this study, a CycleGAN-based SAR and simulated optical image fusion network (SOIF-CycleGAN) is designed and demonstrated to mitigate the adverse effects of both challenges simultaneously through SAR-optical image bidirectional translation. SAR-to-optical (S2O) image translation produces artificial optical images that are high-quality and rich in details, which are used as supplementary information for SAR images to assist ATR. Conversely, optical-to-SAR (O2S) image translation generates pattern-rich artificial SAR images and provides additional training data for SAR ATR algorithms. Meanwhile, a new dataset of SAR-optical image pairs containing eight different types of aircraft has been created for training and testing SOIF-CycleGAN. By combining image-quality assessment (IQA) methods and human vision, the evaluation verified that the proposed network possesses exceptional bidirectional translation capability. Finally, the results of the S2O and O2S image translations are simultaneously integrated into a SAR ATR network, resulting in an overall accuracy improvement of 6.33%. This demonstrates the effectiveness of SAR-optical image fusion in enhancing the performance of SAR ATR. [ABSTRACT FROM AUTHOR]

Auto-driving detection usually acquires low-light infrared images, which pose a great challenge to the autopilot function at night due to their low contrast and unclear texture details. As a precursor algorithm in the field of automatic driving, the infrared image contrast enhancement method is of great significance in accelerating the operation speed of automatic driving target recognition algorithms and improving the accuracy of object localization. In this study, a convolutional neural network model including feature extraction and image enhancement modules is proposed to enhance infrared images. Specifically, the feature extraction module consists of three branches, a concatenation layer, and a fusion layer that connect in parallel to extract the feature images. The image enhancement module contains eight convolutional layers, one connectivity layer, and one difference layer for enhancing contrast in infrared images. In order to overcome the problem of the lack of a large amount of training data and to improve the accuracy of the model, the brightness and sharpness of the infrared images are randomly transformed to expand the number of pictures in the training set and form more sample pairs. Unlike traditional enhancement methods, the proposed model directly learns the end-to-end mapping between low- and high-contrast images. Extensive experiments from qualitative and quantitative perspectives demonstrate that our method can achieve better clarity in a shorter time. [ABSTRACT FROM AUTHOR]

Radar high-resolution range profile (HRRP) provides geometric and structural information of target, which is important for radar automatic target recognition (RATR). However, due to the limited information dimension of HRRP, achieving accurate target recognition is challenging in applications. In recent years, with the rapid development of radar components and signal processing technology, the acquisition and use of target multi-frequency and polarization scattering information has become a significant way to improve target recognition performance. Meanwhile, deep learning inspired by the human brain has shown great promise in pattern recognition applications. In this paper, a Multi-channel Fusion Feature Extraction Network (MFFE-Net) inspired by the human brain is proposed for dual-band polarimetric HRRP, aiming at addressing the challenges faced in HRRP target recognition. In the proposed network, inspired by the human brain's multi-dimensional information interaction, the similarity and difference features of dual-frequency HRRP are first extracted to realize the interactive fusion of frequency features. Then, inspired by the human brain's selective attention mechanism, the interactive weights are obtained for multi- polarization features and multi-scale representation, enabling feature aggregation and multi-scale fusion. Finally, inspired by the human brain's hierarchical learning mechanism, the layer-by-layer feature extraction and fusion with residual connections are designed to enhance the separability of features. Experiments on simulated and measured datasets verify the accurate recognition capability of MFFE-Net, and ablative studies are conducted to confirm the effectiveness of components of network for recognition. [ABSTRACT FROM AUTHOR]

In recent times, the realm of remote sensing has witnessed a remarkable surge in the area of deep learning, specifically in the domain of target recognition within synthetic aperture radar (SAR) images. However, prevailing deep learning models have often placed undue emphasis on network depth and width while disregarding the imperative requirement for a harmonious equilibrium between accuracy and speed. To address this concern, this paper presents FCCD-SAR, a SAR target recognition algorithm based on the lightweight FasterNet network. Initially, a lightweight and SAR-specific feature extraction backbone is meticulously crafted to better align with SAR image data. Subsequently, an agile upsampling operator named CARAFE is introduced, augmenting the extraction of scattering information and fortifying target recognition precision. Moreover, the inclusion of a rapid, lightweight module, denoted as C3-Faster, serves to heighten both recognition accuracy and computational efficiency. Finally, in cognizance of the diverse scales and vast variations exhibited by SAR targets, a detection head employing DyHead's attention mechanism is implemented to adeptly capture feature information across multiple scales, elevating recognition performance on SAR targets. Exhaustive experimentation on the MSTAR dataset unequivocally demonstrates the exceptional prowess of our FCCD-SAR algorithm, boasting a mere 2.72 M parameters and 6.11 G FLOPs, culminating in an awe-inspiring 99.5% mean Average Precision (mAP) and epitomizing its unparalleled proficiency. [ABSTRACT FROM AUTHOR]

With the maturity of deep learning algorithm in synthetic aperture radar (SAR) target recognition field, convolutional neural network (CNN) has become the most effective model. However, the interpretability and the separability of feature maps extracted from convolution layers have not been specially analyzed neither qualitatively nor quantitatively, which makes the traditional model work like a “black box.” To alleviate the problem, a novel model based on separability measure (SM)-CNN is proposed in this letter, which introduces the principle of maximal coding rate reduction (MCR $^{2}$) to the backbone module. SM-CNN quantitatively analyzes the separability of the feature maps and takes the value as a vital part of the loss function to guide the training process of the model. The calculation process of the SM values can be strictly derived mathematically, so it is more interpretable, turning the black box into a “gray box.” In addition, the proposed model can achieve comparable recognition performance of the backbone networks with reduced computational complexity. Comparative experiments based on moving and stationary target acquisition and recognition (MSTAR) and OpenSARShip datasets verify the effectiveness and practicability of the method proposed in this letter. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) automatic target recognition (ATR) has been widely applied in multiple fields. However, the special imaging mechanism of SAR results in different visual features of the same target at different azimuth angles, so single-aspect SAR target recognition has the limitation of observing the target from a single perspective. Multi-aspect SAR target recognition technology can overcome this limitation by utilizing information from different azimuths and effectively improve target recognition performance. Considering the order dependency and data limitation of existing methods, this paper proposes a multi-aspect SAR recognition method based on Non-Local, which applies a self-attention calculation to feature maps to learn the correlation between multi-aspect SAR images. Meanwhile, in order to improve the generalization ability of the proposed method under limited data, a network based on contrastive learning was designed to pre-train the feature extraction part of the whole network. The experimental results using the MSTAR dataset show that the proposed method has excellent recognition accuracy and good robustness. [ABSTRACT FROM AUTHOR]

Infrared automatic target recognition (ATR) technology still is a challenging problem in military applications. In recent years, convolutional neural networks (CNNs) models have already led to breakthrough developments in object detection and target recognition. However, the complex environment and the bad weather caused the poor texture information and the weak background of infrared imaging. It's difficult to use standard CNNs to perform accurate feature extraction and target classification. To overcome these shortcomings, we propose a novel deep learning framework, composed of the multi-kernel transformation and the Alpha-Beta divergence. The multi-kernel transformation operation is designed between convolutional layers and pooling layers to increase the confidence of feature extraction. The Alpha-Beta divergence is used as a penalty term to re-encode the output neurons of improved CNNs, which can promote the recognition performance of the entire network. Furthermore, comprehensive theoretical analysis and extensive experiments are confirmed that our proposed framework outperforms ResNet, VGG-19, DenseNet, and the different combinations of models in many aspects, such as short time-consuming, high accuracy, and strong robustness. Our approach yields a maximum accuracy score of 98.43% on our dataset. Meanwhile, we use the OKTAL-SE-based synthetic database and the SENSIAC dataset to verify our models. Experimental results demonstrate the maximum average accuracy is 97.16%, it is feasible and effective for infrared target recognition. [ABSTRACT FROM AUTHOR]

Automatic target recognition and detection in synthetic aperture radar (SAR) images is playing a significant role in military and civilian fields. Traditional methods are weak in migration capabilities and cumbersome in manual design. Existing deep learning-based methods can achieve high recognition and detection accuracy, but most of them have a very large number of parameters and slow recognition and computational efficiency, which makes it difficult for them to migrate to edge computing equipments, and computational efficiency is crucial in rapid maritime rescue and emergency military deployment. Therefore, we propose a lightweight feature extraction block, lightweight split concat block (LSCB), for SAR automatic target recognition and detection. Specifically, LSCB consists of several operators, such as split, depthwise convolution (DC), multiple kernel sizes block (MKSB), and channel-shuffle (CS). MKSB is a novel channel attention mechanism designed by us, which can make feature maps have target features of different scales and adjust their receptive field sizes adaptively. In addition, to assess the performance of LSCB, we use LSCB to build LSCNet-R and LSCNet-D for SAR target recognition and detection, respectively, and conduct extensive experiments on MSTAR, SSDD, and SAR-Ship-Dataset. The experimental results show that our LSCNet-R and LSCNet-D built with LSCB achieve higher recognition and detection accuracy and computational efficiency with few parameters compared with existing excellent methods. This further illustrates that the proposed LSCB can extract fine and stable features with few parameters. [ABSTRACT FROM AUTHOR]

Active sonar target classification remains an ongoing area of research due to the unique challenges associated with the problem (unknown target parameters, dynamic oceanic environment, different scattering mechanisms, etc.). Many feature extraction and classification techniques have been proposed, but there remains a need to relate and explain the classifier results in the physical domain. This work examines convolutional neural networks trained on simulated data with a known ground truth projected onto two time-frequency representations (spectrograms and scalograms). The classifiers were trained to discriminate the target material type, geometry, and internal fluid filling, while the hyperparameters were tuned to the classification task using Bayesian optimization. The trained networks were examined using an explainable artificial intelligence technique, gradient-weighted class activation mapping, to uncover the informative features used in discrimination. This analysis resulted in visual representations that allowed the CNN choices to be related to the physical domain. It was found that the scalogram representation provided a negligible classification accuracy increase compared with the spectrograms. Networks trained to discriminate between target geometries resulted in the highest accuracy, and the networks trained to discriminate the internal fluid of the target resulted in the lowest accuracy. [ABSTRACT FROM AUTHOR]

During the last decades, Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been vastly utilized in the military services and civil studies. Because of the sensibility of the SAR images of the imaging in the azimuth dimension, using the multi-aspect SAR image sequence is more practical than the single-aspect SAR image to achieve the superior classification accuracy in an actual SAR ATR task. At present time, multi-aspect SAR ATR models mostly utilize Recurrent Neural Networks (RNN) that depend on the sequence between samples and so suffer from the lack of information. In a practical work, a huge amount of training set is needed to train a deep learning network accurately, but it is so costly work to extract multi-aspect SAR images. So, in this article, a new model of multi-aspect SAR ATR is proposed by using a self-attention model. The proposed self-attention model is utilized to calculate the internal correlation between the original SAR images. At the same time, to develop the anti-noise capability of the proposed model and decrease the dependency on a huge amount of training data, a Convolutional Auto Encoder (CAE) is designed and utilized in the feature extraction section of the proposed model. On the other hand, unlike existing traditional methods, in this work we use both amplitude and phase information of SAR images to devolve the training process of the proposed model. It should be noted that all of the parameters of the proposed network are developed to a complex domain. In addition a complex backpropagation algorithm by using the gradient based model is used for training the network. In the end, experiments is obtained by using two MSTAR data set (the MSTAR-SOC and EOC). The experimental results prove that the proposed model not only can achieve a high recognitions rate on the case of sufficient training sample but also can obtain an acceptable rate in the case of small training samples in different complex situations. In addition, the simulation results demonstrate that by using the encoder of CAE in the proposed model, the whole configuration of the proposed model achieves the anti-noise capability that is a valuable benefit of any practical SAR ATR task. [ABSTRACT FROM AUTHOR]

The target recognition system based on radar sensor network (RSN) has recently been widely studied in radar automatic target recognition (RATR). The system can observe the target from multiple perspectives to achieve more robust target recognition. However, the target feature information observed by different radar sensors may be interrelated, complementary, or even contradictory. Therefore, a feature extractor is needed to capture information with discriminant consistency in RSN data. In this work, we propose a new RSN cooperative target recognition method, namely global discriminant information and local geometrical structure co-learning (GILSC). Specifically, the proposed GILSC performs feature extraction by projecting global discriminant information and local neighborhood information into the common feature space. In this feature subspace, the discriminant information carried by the high-resolution range profile (HRRP) from different radars is uniformized, and the geometrical structure of the original HRRP is maintained. The experimental results on the measured HRRP dataset and public simulation dataset obtained by the Air Force Research Laboratory (AFRL) prove the effectiveness of GILSC. Compared with other RSN cooperative target recognition methods, GILSC has the highest recognition rate under the condition of low SNR, and the recognition time is greatly shortened. Compared with a single radar, the target recognition rate can be fully improved by two or three radars' cooperative target recognition. In addition, experiments on feature subspace show that GILSC has better feature cohesion. • A new subspace method for HRRP signal feature representation. • A local geometrical structure is developed to capture feature neighborhood information. • The local structure and global information are incorporated into the framework of Rayleigh quotient. • The advantages of the proposed method are verified by the measured data. [ABSTRACT FROM AUTHOR]

In this paper, a method of Synthetic Aperture Radar (SAR) image Automatic Target Recognition (ATR) based on Convolution Auto-encode (CAE) and Support Vector Machine (SVM) is proposed. Using SVM replaces the traditional softmax as the classifier of the CAE model to classify the feature vectors extracted by the CAE model, which solves the problem that the softmax classifier is less effective in the nonlinear case. Since the SVM can only solve the binary classification problem, and in order to realize the classification of the class objectives, the SVM were designed to achieve the classification of the input samples. After unsupervised training for CAE, the coding layer is connected with SVM to form a classification network. CAE can extract the features of the data by an unsupervised method, and the nonlinear classification advantage of SVM can classify the features extracted by CAE and improve the accuracy of the object recognition. At the same time, the high-accuracy identification of key targets is required in some special cases. A new initialization method is proposed, which initializes the network parameters by pretraining the key targets and changes the weights of different targets in the loss function to obtain better feature extraction, so it can ensure good multitarget recognition ability while realizing the high recognition accuracy of the key targets. [ABSTRACT FROM AUTHOR]

Asan important means in low-altitude airspace surveillance, passive radar has been widely studied. With the increasing complexity of the low-altitude environment, the urgent need for radar's capability of automatic target recognition (ATR) emerges. In the field of ATR for passive radar, the method based on radar cross section (RCS) is an important direction for the simplicity of feature extraction. In this article, we exploit the compensated quasi-echo-power (CQEP), i.e., quasi-RCS, to realize ATR in passive radar. We propose an ATR method on the basis of the angular diversity. First, we divide the angular space, which consists of four components of the incident angle and scattering angle of electromagnetic wave, into multiple subspaces. Then, we build a subrecognizer in each angular subspace according to the CQEP distribution characteristics. Each receiving station of the multistatic passive radar recognizes targets in an angular subspace corresponding to its observation and outputs a preliminary decision. Based on the preliminary decisions of all receiving stations, a voting strategy is adopted to make the final decision on the unknown target class in the fusion center. Experimental results based on real-life target data show that the proposed method has a significant improvement on the average correct recognition rate with fusion of three receiving stations, which validates the proposed method. [ABSTRACT FROM AUTHOR]

An identification method of radar targets based on improved Dijkstra algorithm with time-frequency domain filtering is proposed to solve the problem that the accuracy of micro-Doppler feature extraction of radar targets in the middle of the trajectory is not high, resulting in low target recognition rates. The improved Dijkstra algorithm is used for extracting the instantaneous Doppler features of the strongest component in the multi-component echo signal. Then the strongest component is filtered through the time-frequency domain filter. So the instantaneous Doppler features of the multi-component signal can be extracted in proper sequence, and features are applied to identify radar targets in the middle of the trajectory. The simulation results demonstrate that this method is suitable for a variety of micro-motion forms, the micro-Doppler features of the echo signal have higher accuracy, and the average recognition rate of radar targets in the middle of the trajectory is increased effectively. [ABSTRACT FROM AUTHOR]

The traditional High-Resolution Range Profile (HRRP) target recognition method has difficulty automatically extracting target deep features, and has low recognition accuracy under low training samples. To solve these problems, a ship recognition method is proposed based on the lightweight Transformer model. The model enhances the representation of key features by embedding Recurrent Neural Networks (RNN) into Transformer's encoder. The Group Linear Transformations (GLTs) are introduced into Transformer to reduce the number of parameters in the model, and stable features are extracted through linear intergroup dimensional transformations. The adaptive gradient clipping algorithm is combined with the Stochastic Gradient Descent (SGD) optimizer to allow the gradient to change dynamically with the training process and to improve the training speed and generalization ability of the model. Experimental results on the simulated dataset show that multi-layer model stacking can effectively extract deep features of targets and raise recognition accuracy. At the same time, the lightweight Transformer model can maintain good recognition performance with low parameters and low training samples. [ABSTRACT FROM AUTHOR]

In recent years, synthetic aperture radar (SAR) automatic target recognition (ATR) has been widely used in both military and civilian fields. Due to the sensitivity of SAR images to the observation azimuth, the multi-aspect SAR image sequence contains more information for recognition than a single-aspect one. Nowadays, multi-aspect SAR target recognition methods mainly use recurrent neural networks (RNN), which rely on the order between images and thus suffer from information loss. At the same time, the training of the deep learning model also requires a lot of training data, but multi-aspect SAR images are expensive to obtain. Therefore, this paper proposes a multi-aspect SAR recognition method based on self-attention, which is used to find the correlation between the semantic information of images. Simultaneously, in order to improve the anti-noise ability of the proposed method and reduce the dependence on a large amount of data, the convolutional autoencoder (CAE) used to pretrain the feature extraction part of the method is designed. The experimental results using the MSTAR dataset show that the proposed multi-aspect SAR target recognition method is superior in various working conditions, performs well with few samples and also has a strong ability of anti-noise. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image recognition plays a significant role in civil and military target perception, and deep learning methods are commonly used for SAR image recognition. However, for small-sample SAR datasets, deep learning methods suffer from problems such as overfitting and gradient explosion during the training process. In this study, first, we pre-train the deep neural network on the unlabeled SAR image dataset with self-supervised contrastive learning, so as to obtain a deep feature extraction network with better representation ability. Then, we transfer the pre-trained weights to the small-sample SAR image data for fine-tuning and linear evaluation, which in turn can improve the overfitting problem of small-sample SAR image recognition. This research can give scientific and objective small-sample target recognition laws, which will promote the long development of the scientific field of deep representation learning research and can generate great economic benefits in the field of SAR image target recognition. [ABSTRACT FROM AUTHOR]

In synthetic aperture radar automatic target recognition (SAR-ATR), target information is usually propagated and reserved in complex-valued form, namely, magnitude information and phase information. However, most of the existing SAR target recognition methods only focus on real-valued (magnitude information) calculations and ignore the phase information of targets, yielding poor recognition performance. To overcome this limitation, this article proposes a multi-stream (MS) feature fusion SAR target recognition method based on complex-valued operations, called MS complex-valued networks (MS-CVNets), to utilize the phase information of the target effectively. First of all, a series of complex-valued operation blocks are constructed to satisfy the network training in the complex field, such as complex convolution, complex batch normalization, complex activation, complex pooling, and complex full connection. Besides, an MS structure is employed by applying different convolution kernels to extract multiscale information of targets, further enhancing the representation ability of the model. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) dataset illustrate that compared with the current state-of-the-art real-valued based models, MS-CVNets can achieve better recognition results under both standard operating conditions (SOCs) and extended operating conditions (EOCs), validating the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

In the past few decades, the demand for reliable and robust systems capable of monitoring unmanned aerial vehicles (UAVs) increased significantly due to the security threats from its wide applications. During UAVs surveillance, birds are a typical confuser target. Therefore, discriminating UAVs from birds is critical for successful non-cooperative UAVs surveillance. Micro-Doppler signature (m-DS) reflects the scattering characteristics of micro-motion targets and has been utilized for many radar automatic target recognition (RATR) tasks. In this paper, the authors deploy local mean decomposition (LMD) to separate the m-DS of the micro-motion parts from the body returns of the UAVs and birds. After the separation, rotating parts will be obtained without the interference of the body components, and the m-DS features can also be revealed more clearly, which is conducive to feature extraction. What is more, there are some problems in using m-DS only for target classification. Firstly, extracting only m-DS features makes incomplete use of information in the spectrogram. Secondly, m-DS can be observed only for metal rotor UAVs, or large UAVs when they are closer to the radar. Lastly, m-DS cannot be observed when the size of the birds is small, or when it is gliding. The authors thus propose an algorithm for RATR of UAVs and interfering targets under a new system of L band staring radar. In this algorithm, to make full use of the information in the spectrogram and supplement the information in exceptional situations, m-DS, movement, and energy aggregation features of the target are extracted from the spectrogram. On the benchmark dataset, the proposed algorithm demonstrates a better performance than the state-of-the-art algorithms. More specifically, the equal error rate (EER) proposed is 2.56% lower than the existing methods, which demonstrates the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In synthetic aperture radar (SAR) automatic target recognition (ATR), there are mainly two types of methods: the physics-driven model and the data-driven network. The physics-driven model can exploit electromagnetic theory to obtain physical properties, while the data-driven network will extract deep discriminant features of targets. These two types of features represent the target characteristics in the scattering domain and the image domain, respectively. However, the representation discrepancy caused by the different modalities between them hinders the further comprehensive utilization and fusion of both features. In order to take full advantage of physical knowledge and deep discriminant feature for SAR ATR, we propose a new feature fusion learning framework SDF-Net to combine scattering and deep image features. In this work, we treat the attributed scattering centers (ASC) as set-data instead of multiple individual points, which can well mine the topological interaction among scatterers. Then, multiregion multiscale subsets are constructed at both component and target levels. To be specific, the most significant scattering intensity and overall representation in these subsets are exploited successively to learn permutation-invariant scattering features according to a set-oriented deep network. The scattering representations can provide mid-level semantic and structural features that are subsequently fused with the complementary deep image features to yield an end-to-end high-level feature learning framework, which helps enhance the generalization ability of networks especially under complex observation conditions. Extensive experiments on the Moving and Stationary Target Acquisition and Recognition database verify the effectiveness and robustness of the SDF-Net compared against both typical SAR ATR networks and ASC-based models. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks (CNNs) have drawn considerable attention for the analysis of synthetic aperture radar (SAR) data. In this study, major subareas of SAR data analysis that have been tackled by CNNs are systematically reviewed, such as automatic target recognition, land use and land cover classification, segmentation, change detection, object detection, and image denoising. Special emphasis has been given to practical techniques such as data augmentation and transfer learning. Complex-valued CNNs, which have been introduced to exploit phase information embedded in SAR complex images, have also been extensively reviewed. To conclude this review paper, open challenges and future research directions are highlighted. [ABSTRACT FROM AUTHOR]

Aircraft detection in synthetic aperture radar (SAR) imagery is a challenging task in SAR automatic target recognition (SAR ATR) areas due to aircraft’s extremely discrete appearance, obvious intraclass variation, small size, and serious background’s interference. In this article, a single shot detector (SSD), namely, attentional feature refinement and alignment network (AFRAN), is proposed for detecting aircraft in SAR images with competitive accuracy and speed. Specifically, three significant components, including attention feature fusion module (AFFM), deformable lateral connection module (DLCM), and anchor-guided detection module (ADM), are carefully designed in our method for refining and aligning informative characteristics of aircraft. To represent the characteristics of aircraft with less interference, low-level textural and high-level semantic features of aircraft are fused and refined in AFFM thoroughly. The alignment between aircraft’s discrete backscatting points and convolutional sampling spots is promoted in DLCM. Eventually, the locations of aircraft are predicted precisely in ADM based on aligned features revised by refined anchors. To evaluate the performance of our method, a self-built SAR aircraft sliced dataset and a large scene SAR image are collected. Extensive quantitative and qualitative experiments with detailed analysis illustrate the effectiveness of the three proposed components. Furthermore, the topmost detection accuracy and competitive speed are achieved by our method compared with other domain-specific methods, e.g., dense attention pyramid network (DAPN) and pyramid attention dilated network (PADN), and general convolutional neural network (CNN)-based methods, e.g., Feature Pyramid Network (FPN), Cascade R-CNN, SSD, RefineDet, and RepPoints Detector (RPDet). [ABSTRACT FROM AUTHOR]

In this article, a new microwave-radar-based technique for short-range detection and classification of multiple human and vehicle targets crossing a monitored area is proposed. This approach, which can find applications in both security and infrastructure surveillance, relies upon the processing of the scattered-field data acquired by low-cost off-the-shelf components, i.e., a 24 GHz frequency-modulated continuous wave (FMCW) radar module and a Raspberry Pi mini-PC. The developed method is based on an ad hoc processing chain to accomplish the automatic target recognition (ATR) task, which consists of blocks performing clutter and leakage removal with an infinite impulse response (IIR) filter, clustering with a density-based spatial clustering of applications with noise (DBSCAN) approach, tracking using a Benedict-Bordner $\alpha $ - $\beta $ filter, features extraction, and finally classification of targets by means of a $k$ -nearest neighbor ($k$ -NN) algorithm. The approach is validated in real experimental scenarios, showing its capabilities in correctly detecting multiple targets belonging to different classes (i.e., pedestrians, cars, motorcycles, and trucks). [ABSTRACT FROM AUTHOR]

Recent deep learning (DL) detectors adopted by radar or sonar (RS) are normally trained with transfer learning, where the typical workflow is to pretrain a convolutional neural network (CNN) on external large-scale classification datasets (e.g., ImageNet) as the backbone and then finetune the entire detector on detection datasets. Though transfer learning could effectively avoid overfitting, transferred models are usually redundant and might not generalize well on RS datasets. To achieve high generalization and to eliminate the dependence on transfer learning, a self-trained target detection method is established by including Automatic Deep Learning (AutoDL) to design optimal detectors. This self-trained target detection consists of three stages. First, a derived classification dataset (DCD) consisting of image blocks of targets and backgrounds is derived from detection datasets. Then, a memory-efficient Differentiable Architecture Search algorithm with flexible search space and large inputs (FL-DARTS), which is characterized by its predefined multistride convolutions, poolings, and unique super-structure, is proposed to automatically design and self-train optimal CNNs on DCDs. Finally, self-trained AutoDL detectors are implemented with the automatic backbone designed by FL-DARTS. We evaluated three self-trained AutoDL detectors on the public SAR ship detection dataset (SSDD) and the self-made sonar common target detection dataset (SCTD). The experiments show that while the number of parameters of automatic backbones designed for SSDD and SCTD are only 11.8% and 15.2% of that of ResNet50, self-trained AutoDL detectors implemented with automatic backbones significantly outperform their transfer learning detectors and achieve state-of-the-art detection precisions and high detection speeds. Data, codes are publicly available. [ABSTRACT FROM AUTHOR]

With the maturity of synthetic aperture radar (SAR) technology, the problem of imbalanced data has gradually emerged. This problem makes it difficult for the automatic target recognition (ATR) model to properly learn the classification boundaries of majority and minority category target samples. In this article, we propose an ATR model with new architecture, called the cost-sensitive awareness-based automatic target recognition (CA-ATR) model, which provides an effective way of solving the problem of imbalanced data. Aimed at the two issues caused by imbalanced data on ATR models, the proposed method solves the problems from both the data and algorithm levels. At the data level, CA-ATR avoids adverse correlations among the target samples through different oversampling methods. By making the ATR model cost-sensitive, the proposed method also avoids the empirical risk preference of the ATR model for majority category target samples at the algorithm-level. At the same time, CA-ATR can autonomously learn different cost-sensitive awareness from different imbalanced data sets. The awareness enables the ATR model to more accurately learn the classification boundaries between target samples that belong in different categories. Several experimental results show the superiority of the proposed approach based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set. Compared with other imbalanced learning methods, the proposed method is able to solve different types of imbalanced data problems. [ABSTRACT FROM AUTHOR]

Deep learning has been gradually used to solve SAR image classification problems for its desired performance on various recognition problems. A deep variational autoencoding model (DVAEM), that constructs a multi-stochastic-layer generative network (decoder) and variational inference network (encoder), can be employed to build a flexible and interpretable model for the SAR image target recognition task. It is scalable in the training phase and fast in the testing stage, and can extract the hierarchical structured and interpretable features from SAR images. However, the current DVAEM extracts the features of SAR images unsupervisedly, without incorporating the label information, and may fail to extract discriminative representations for the recognition task. In this article, to jointly model SAR images and their corresponding labels, we further propose supervised DVAEM with Euclidean distance restriction (rs-DVAEM), which enhances the discriminative power of latent representations of SAR images. Notably, our proposed rs-DVAEM combines the flexibility of DVAEM in describing the SAR images and the discriminative power of supervised models. Experimental results on the moving and stationary target acquisition and recognition public dataset demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Aiming at the problem of feature extraction and recognition in high resolution range profile (IIRRP) target recognition, a recognition method based on one-dimensional stacked pooling fusion convolutional autoencoder (ID SPF-CAE) is proposed in this paper. Firstly, a one-dimensional pooling fusion convolutional autoencoder (ID PF-CAE) is constructed. In the encoding stage, the maximum pooling and average pooling are used to extract different encoding features and fuse them to extract the structural features of IIRRP. Then, multiple ID PF-CAEs are stacked to form ID SPF-CAE. Finally, the network is fine-tuned using label data to realize IIRRP target recognition. And the AdaBound algorithm is used to optimize network training for improving the recognition performance. The experimental results based on the simulated data of the target in the middle part of the trajectory show that the method has strong feature extraction capability, and has high accuracy and robustness for IIRRP target recognition. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) automatic target recognition (ATR) plays an important role in SAR image interpretation. However, at least hundreds of training samples are usually required for each target type in the existing SAR ATR algorithms. In this article, a novel few-shot learning framework named hybrid inference network (HIN) is proposed to tackle the problem of SAR target recognition with only a few training samples. The recognition procedure of HIN consists of two main stages. In the first stage, an embedding network is utilized to map the SAR images into an embedding space. In the second stage, a hybrid inference strategy that combines the inductive inference and the transductive inference is adopted to classify the samples in the embedding space. In the inductive inference section, each sample is recognized independently according to a metric based on Euclidean distance. In the transductive inference section, all samples are recognized as a whole according to their manifold structures by label propagation. Finally, in the hybrid inference section, the classification result is obtained by combining the above two inference methods. To train the framework more effectively, a novel loss function named enhanced hybrid loss is proposed to constrain samples to gain better interclass separability in the embedding space. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set illustrate that HIN performs well in few-shot SAR image classification. [ABSTRACT FROM AUTHOR]

High-Resolution Range Profile (HRRP) is effective in various Radar Automatic Target Recognition problems. Multi-scale techniques have been verified in aircraft target HRRP feature enrichment to achieve aircraft recognition performance optimization. The involvement of multiple training-classification procedures in existing multi-scale methods results in tremendous resource consumption which challenges their real-time classification performance and application significance. This paper introduces a novel method that enables multi-scale HRRP features to be manipulated under a single scale for efficiency enhancement. Numerical analysis indicates that multi-scale intensity variations for particular HRRP scatterers could be modeled as Gaussian noises. Linear Discriminant Analysis and Singular Value Decomposition techniques are applied on reconstructed feature vectors for better separability and noise tolerance capability. Experimental results from dynamic aircraft recognition experiments verify the expected efficiency enhancement of the proposed method while maintaining comparable classification accuracy and better noise tolerance performance. [ABSTRACT FROM AUTHOR]

The scattering signatures of a synthetic aperture radar (SAR) target image will be highly sensitive to different azimuth angles/poses, which aggravates the demand for training samples in learning-based SAR image automatic target recognition (ATR) algorithms, and makes SAR ATR a more challenging task. This paper develops a novel rotation awareness-based learning framework termed RotANet for SAR ATR under the condition of limited training samples. First, we propose an encoding scheme to characterize the rotational pattern of pose variations among intra-class targets. These targets will constitute several ordered sequences with different rotational patterns via permutations. By further exploiting the intrinsic relation constraints among these sequences as the supervision, we develop a novel self-supervised task which makes RotANet learn to predict the rotational pattern of a baseline sequence and then autonomously generalize this ability to the others without external supervision. Therefore, this task essentially contains a learning and self-validation process to achieve human-like rotation awareness, and it serves as a task-induced prior to regularize the learned feature domain of RotANet in conjunction with an individual target recognition task to improve the generalization ability of the features. Extensive experiments on moving and stationary target acquisition and recognition benchmark database demonstrate the effectiveness of our proposed framework. Compared with other state-of-the-art SAR ATR algorithms, RotANet will remarkably improve the recognition accuracy especially in the case of very limited training samples without performing any other data augmentation strategy. [ABSTRACT FROM AUTHOR]

In this paper, an object recognition approach for synthetic aperture radar (SAR) images is addressed, which is based on the enhanced kernel sparse representation of monogenic signal. It consists of two main modules. In the first module, to capture the spatial and spectral properties of a target at the same time, a multi-scale monogenic feature extraction scheme is proposed. In the second module, an enhanced kernel sparse representation-based classifier (KSRC) is designed. Different from the traditional KSRC, in the enhanced KSRC, we first integrate the kernel principal component analysis (KPCA) as well as the kernel fisher discriminant analysis (KFDA) to generate an augmented pseudo-transformation matrix. Then, a new discriminative feature mapping approach is presented by exploiting the augmented pseudo-transformation matrix so that the dimensionality of the kernel feature space can be effectively reduced. At last, the ℓ1 -norm minimization is utilized to calculate the sparse coefficients for a test sample, and thus the inference can be reached in terms of the total reconstruction error. Experimental results on the public moving and stationary target acquisition and recognition dataset (MSTAR) demonstrate that the proposed method achieves high recognition accuracy for SAR automatic target recognition. [ABSTRACT FROM AUTHOR]

Understanding the decision-making process of deep learning networks is a key challenge that has rarely been investigated for synthetic aperture radar (SAR) images. In this article, a set of new analytical tools is proposed and applied to a convolutional neural network (CNN) handling automatic target recognition on two SAR datasets containing military targets. First, an analysis of the respective influence of target, shadow, and background areas on classification performance is carried out. The shadow appears to be the least used portion of the image affecting the decision process, compared to the target and clutter, respectively. Second, the location of the most influential features is determined with classification maps obtained by systematically hiding specific target parts and registering the associated classification rate relative to the images to be classified. The location of the image areas without which classification fails is target type and orientation specific. Nonetheless, a strong contribution of specific parts of the target, such as the target top and the areas facing the radar, is noticed. Finally, results show that features are increasingly activated along the CNN depth according to the target type and its orientation, even though target orientation is absent from the loss function. [ABSTRACT FROM AUTHOR]

Although numerous methods based on sequence image classification have improved the accuracy of synthetic-aperture radar (SAR) automatic target recognition, most of them only concentrate on the fusion of spatial features of multiple images and fail to fully utilize the temporal-varying features. In order to exploit the spatial and temporal features contained in the SAR image sequence simultaneously, this article proposes a sequence SAR target classification method based on the spatial–temporal ensemble convolutional network (STEC-Net). In the STEC-Net, the dilated 3-D convolution is first applied to extract the spatial–temporal features. Then, the features are gradually integrated hierarchically from local to global and represented as the united tensors. Finally, a compact connection is applied to obtain a lightweight classification network. Compared with the available methods, the STEC-Net achieves a higher accuracy (99.93%) in the moving and stationary target acquisition and recognition (MSTAR) data set and exhibits robustness to depression angle, configuration, and version variants. [ABSTRACT FROM AUTHOR]

With the development of synthetic aperture radar (SAR) system, automatic target recognition (ATR) has attracted wide attention in many decision-making tasks, in which an enhanced feature of SAR image is a powerful tool to improve the recognition accuracy. However, the presence of speckle noise and natural clutter inevitably contaminates SAR images and, thus, degrades image features. In this article, we explicitly address the speckle reduction problem for the circular SAR system, in which the motion of aircraft platform causes continuous angular variations so that different SAR images can be captured with the high interrelationship. By exploiting the underlying low-rank and continuous properties among different SAR images, a method called the $\ell _{p}$ -regularized low-rank and space-angle continuity extraction ($\ell _{p}$ -LSCE) is proposed to suppress the noise and enhance the target feature. Taking into account the interrelationship between SAR images, we arrange the images in a 3-D tensor to investigate the space-angle continuity of the targets. Furthermore, we develop a robust $\ell _{p}$ -regularized scheme to incorporate the low-rank property of targets. Then, the joint optimization problem is solved via the framework of augmented Lagrange multiplier (ALM) with efficient computation of each ALM subproblem. The experimental results of circular SAR data sets of the moving and stationary target acquisition and recognition (MSTAR) and the VideoSAR demonstrate that the proposed method can efficiently despeckle SAR images with well-preserved target features, which is conducive to the improvement of ATR performance. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) automatic target recognition (ATR) based on convolutional neural network (CNN) is a research hotspot in recent years. However, CNN is data-driven, and severe overfitting occurs when training data is scarce. To solve this problem, we first introduce a non-greedy CNN network. But when a CNN structure with a non-greedy classifier is used to handle the SAR ATR in the case of scarce training data, the feature extraction capability of the network degrades. To balance the feature extraction and anti-overfitting capabilities of the network, a semi-greedy network called transfer learning with convolutional auto-encoders (CAE) and hinge loss CNN (HL-CNN), namely CAE-HL-CNN, is proposed in this paper. First, the CAE-HL-CNN introduces a non-greedy network which uses a hinge loss classifier in the CNN structure to enhance the network's generalization performance. It retains the hierarchical feature extraction structure of CNN and has the same anti-overfitting capability as support vector machine. Then, by combining CAE with the HL-CNN through transfer learning, the CAE-HL-CNN extracts a complete feature representation to compensate for the degradation in feature extraction capability in a greedy way. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that in the case of scarce training data, the proposed network can improve the recognition performance of CNN, which achieves higher classification accuracy and performs more equably on each category, and it extracts sparser feature maps than the compared methods. [ABSTRACT FROM AUTHOR]

The low resolution of infrared (IR) images makes feature extraction for classification of a challenging work. Learning-based methods, therefore, are preferred to be used on such raw imagery. In this article, in order to avoid difficulties in feature extraction, a novel multitask extension of the widely used sparse-representation-classification (SRC) method is proposed in both single and multiview set-ups. That is, the test sample could be a single IR image or images from different views. In both single-view and multiview scenarios, we try to employ collaborative spike and slab priors. This is because the traditional sparsity-inducing measures such as the $l_{0}$ -row pseudonorm makes it hard to capture the sparse structure of the coefficient matrix when expanded in terms of a training dictionary, and the priors are proved to be able to capture fairly general sparse structures. Furthermore, a joint prior and sparse coefficient estimation method (JPCEM) is proposed for the first time in this article in order to alleviate the need to handpick prior parameters required before classification. Multiple experiments are conducted on a synthetic Comanche Forward Looking IR (FLIR) Automatic Target Recognition (ATR) database collected by Army Research Lab and a challenging mid-wave IR (MWIR) image ATR database made available by the U.S. Army Night Vision and Electronic Sensors Directorate. The final results substantiate the merits of the proposed JPCEM through comparisons with other state-of-the-art methods, including both the ones based on SRC and the ones constructed using deep learning frameworks. [ABSTRACT FROM AUTHOR]

In this article, a supervised nonlinear dictionary learning (DL) method, called multiscale supervised kernel DL (MSK-DL), is proposed for target recognition in synthetic aperture radar (SAR) images. We use Frost filters with different parameters to extract an SAR image’s multiscale features for data augmentation and noise suppression. In order to reduce the computation cost, the dimension of each scale feature is reduced by principal component analysis (PCA). Instead of the widely used linear DL, we learn multiple nonlinear dictionaries to capture the nonlinear structure of data by introducing the dimension-reduced features into the nonlinear reconstruction error terms. A classification model, which is defined as a discriminative classification error term, is learned simultaneously. Hence, the objective function contains the nonlinear reconstruction error terms and a classification error term. Two optimization algorithms, called multiscale supervised kernel K-singular value decomposition (MSK-KSVD) and multiscale supervised incremental kernel DL (MSIK-DL), are proposed to compute the multidictionary and the classifier. Experiments on the moving and stationary target automatic recognition (MSTAR) data set are performed to evaluate the effectiveness of the two proposed algorithms. And the experimental results demonstrate that the proposed scheme outperforms some representative common machine learning strategies, state-of-the-art convolutional neural network (CNN) models and some representative DL methods, especially in terms of its robustness against training set size and noise. [ABSTRACT FROM AUTHOR]

Aiming at the key problem of effective representation and extraction of features in radar high resolution range profile (HRRP) target recognition, a recognition method based on bispectrum-spectrogram feature and deep convolution neural network (DCNN) is proposed. Firstly, this method extracts the bispectrum-spectrogram feature representation of HRRP as the input of the CNN. Then, the deep and essential features are extracted by the network training and the radar targets can be recognized. Finally, the recognition results of different feature representations are compared. The experimental results of the satellite target measured data show that the method can recognize radar target effectively and accurately, and the bispectrum-spectrogram feature has better recognition accuracy and noise robustness than other commonly used HRRP feature representations. [ABSTRACT FROM AUTHOR]

With the wide application of high-resolution radar, the application of Radar Automatic Target Recognition (RATR) is increasingly focused on how to quickly and accurately distinguish high-resolution radar targets. Therefore, Synthetic Aperture Radar (SAR) image recognition technology has become one of the research hotspots in this field. Based on the characteristics of SAR images, a Sparse Data Feature Extraction module (SDFE) has been designed, and a new convolutional neural network SSF-Net has been further proposed based on the SDFE module. Meanwhile, in order to improve processing efficiency, the network adopts three methods to classify targets: three Fully Connected (FC) layers, one Fully Connected (FC) layer, and Global Average Pooling (GAP). Among them, the latter two methods have less parameters and computational cost, and they have better real-time performance. The methods were tested on public datasets SAR-SOC and SAR-EOC-1. The experimental results show that the SSF-Net has relatively better robustness and achieves the highest recognition accuracy of 99.55% and 99.50% on SAR-SOC and SAR-EOC-1, respectively, which is 1% higher than the comparison methods on SAR-EOC-1. [ABSTRACT FROM AUTHOR]

Automatic target recognition (ATR) is an important part for many computer vision applications. Despite the extensive research which has been carried out in this area for many years, there is no ATR system which performs well on all applications. Recently, different object recognition frameworks have been proposed which yield a high performance in baseline databases. However, our experiments showed that they can fail in real-world scenarios, when dealing with a limited number of data samples. In this paper, we propose a new ATR system, based on deep convolutional neural network (DCNN), to detect the targets in forward looking infrared (FLIR) scenes and recognize their classes. In our proposed ATR framework, a fully convolutional network is trained to map the input FLIR imagery data to a fixed stride correspondingly-sized target score map. The potential targets are identified by applying a threshold on the target score map. Finally, the corresponding regions centered at these target points are fed to a DCNN to classify them into different target types while at the same time rejecting the false alarms. The proposed architecture achieves a significantly better performance in comparison with that of the state-of-the-art methods on two large FLIR image databases. [ABSTRACT FROM AUTHOR]

This paper proposes a fast target indexing method based on target geometric models and further conceives a forward method based coarse-to-fine hierarchical synthetic aperture radar (SAR) automatic target recognition (ATR) system. The proposed fast SAR target indexing method is employed for coarse classification before the implementation of fine classification and recognition, resulting in significant acceleration of target recognition. Furthermore, the fast SAR target indexing method is purely based on target geometric models without resorting to any time-consuming electromagnetic (EM) computation, which enables the online and real-time classification. The binary target region and shadow region are selected as the indexing features, and a forward feature prediction method based on optical visibility is developed to predict the features from the target geometric model in real time. Then, the features extracted from the testing SAR image are aligned with the predicted features to establish correlation ship and a fused similarity based on four types of complementary similarity criteria is designed to further implement target indexing. The effectiveness of the proposed fast SAR target indexing method is demonstrated by using the MSTAR dataset. [ABSTRACT FROM AUTHOR]

Although the deep convolutional neural network (DCNN) has been successfully applied to automatic target recognition (ATR) of ground vehicles based on synthetic aperture radar (SAR), most of the available techniques are not suitable for inverse synthetic aperture radar (ISAR) because they cannot tackle the inherent unknown deformation (e.g., translation, scaling, and rotation) among the training and test samples. To achieve robust polarimetric-ISAR (Pol-ISAR) ATR, this paper proposes the spatial transformer-multi-channel-deep convolutional neural network, i.e., ST-MC-DCNN. In this structure, we adopt the double-layer spatial transformer network (STN) module to adjust the image deformation of each polarimetric channel and then perform a robust hierarchical feature extraction by MC-DCNN. Finally, we carry out feature fusion in the concatenation layer and output the recognition result by the softmax classifier. The proposed network is end-to-end trainable and could learn the optimal deformation parameters automatically from training samples. For the fully Pol-ISAR image database generated from electromagnetic (EM) echoes of four satellites, the proposed structure achieves higher recognition accuracy than traditional DCNN and MC-DCNN. Additionally, it has shown robustness to image scaling, rotation, and combined deformation. [ABSTRACT FROM AUTHOR]

The computational cost of many deep convolutional neural networks (CNNs) for the automatic target recognition proposed in the area of synthetic aperture radar (SAR) imagery recently is huge, and the limited SAR images are always insufficient for training the deep CNNs. To improve the computational efficiency, a new light but very efficient convolutional network architecture is designed using some novel techniques to get the better results. The authors apply the batch normalisation before each convolutional layer in order to reduce 'internal covariate shift' and use the drop-out strategy in the fully layer to avoid over-fitting. Additionally, concatenated ReLU is used as activation scheme specially instead of ReLU for preserving the negative phase information to get the double feature maps of the previous layer rather than to increase the depth of the filters that can lessen the parameters of the networks. The results of the experimental demonstrate that the authors' CNNs can both achieve a state-of-the-art classification accuracy of 99.53% of the SAR target classification in the Moving and Stationary Target Acquisition and Recognition ten classes public dataset and perform well even when the training data is sparse. [ABSTRACT FROM AUTHOR]

Utilising neural networks to learn and extract valuable features has achieved satisfactory performance for synthetic aperture radar automatic target recognition (SAR ATR). However, such target recognition capability could be seriously limited by severe image rotation. To greatly improve the performance of convolutional neural networks-based SAR ATR, a data augmentation method combining region of interest (ROI) extraction and full-angle rotation method is firstly proposed in this study. Then, an inception-SAR NET is presented to polymerise multi-branch feature maps. The superior performance of inception-SAR NET structures is obtained by comprehensive experiments. Finally, the results based on MSTAR dataset demonstrate that authors' methods could achieve the most advanced performance. [ABSTRACT FROM AUTHOR]

Template-matching-based approaches have been developed for many years in the field of synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of template-matching-based approaches is strongly affected by two factors: background clutter and noise and the size of the data set. To solve the problems mentioned above, a multilevel reconstruction-based multitask joint sparse representation method is proposed in this paper. According to the theory of the attributed scattering center (ASC) model, a SAR image exhibits strong point-scatter-like behavior, which can be modeled by scattering centers on the target. As a result, the ASCs can be extracted from SAR images based on the ASC model. Then, ASCs extracted from SAR images are used to reconstruct the SAR target at multilevels based on energy ratio (ER). The multilevel reconstruction is a process of data augmentation, which can not only restrain the background clutter and noise but also augment the data set. Several subdictionaries are designed after multilevel reconstruction according to the label of training samples. Meanwhile, a test image chip is reconstructed into multiple test images. The random projection coefficients associated with multiple reconstructed test images are fed into a multitask joint sparse representation classification framework. The final decision is made in terms of accumulated reconstruction error. Experiments on moving and stationary target acquisition and recognition (MSTAR) data set proved the effectiveness of our method. [ABSTRACT FROM AUTHOR]