Synthetic Aperture Radar Automatic Target Research Articles

Research on SAR Image Target Recognition Based on Convolutional Neural Network

A synthetic aperture radar (SAR) automatic target recognition can effectively improve the utilization efficiency of SAR image data. In order to improve the generalization and accuracy of SAR image target recognition, a convolutional neural network model is proposed to be applied to SAR image target recognition. Firstly, the network structure is designed for the characteristics of SAR image. Secondly, the introduction of dense block network structure improves the generalization performance of the model. Finally, Dropout reduced the computational complexity of the network and improved the generalization performance of the model. Experimental data were obtained from the United States Moving and Stationary Target Acquisition and recognition database. Experimental results of 10 types of target recognition showed that the overall recognition rate of the improved convolutional neural network is 99.18%. The convolutional neural network model proposed in this study improves the accuracy and generalization of the network, and is an effective method for target recognition of SAR images.

A Novel Convolutional Neural Network Architecture for SAR Target Recognition

Among many improved convolutional neural network (CNN) architectures in the optical image classification, only a few were applied in synthetic aperture radar (SAR) automatic target recognition (ATR). One main reason is that direct transfer of these advanced architectures for the optical images to the SAR images easily yields overfitting due to its limited data set and less features relative to the optical images. Thus, based on the characteristics of the SAR image, we proposed a novel deep convolutional neural network architecture named umbrella. Its framework consists of two alternate CNN-layer blocks. One block is a fusion of six 3-layer paths, which is used to extract diverse level features from different convolution layers. The other block is composed of convolution layers and pooling layers are mainly utilized to reduce dimensions and extract hierarchical feature information. The combination of the two blocks could extract rich features from different spatial scale and simultaneously alleviate overfitting. The performance of the umbrella model was validated by the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark data set. This architecture could achieve higher than 99% accuracy for the classification of 10-class targets and higher than 96% accuracy for the classification of 8 variants of the T72 tank, even in the case of diverse positions located by targets. The accuracy of our umbrella is superior to the current networks applied in the classification of MSTAR. The result shows that the umbrella architecture possesses a very robust generalization capability and will be potential for SAR-ART.

A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition

Synthetic aperture radar (SAR) automatic target recognition (ATR) technology is one of the research hotspots in the field of image cognitive learning. Inspired by the human cognitive process, experts have designed convolutional neural network (CNN)-based SAR ATR methods. However, the performance of CNN significantly deteriorates when the labeled samples are insufficient. To effectively utilize the unlabeled samples, we present a novel semi-supervised CNN method. In the training process of our method, the information contained in the unlabeled samples is integrated into the loss function of CNN. Specifically, we first utilize CNN to obtain the class probabilities of the unlabeled samples. Thresholding processing is performed to optimize the class probabilities so that the reliability of the unlabeled samples is improved. Afterward, the optimized class probabilities are used to calculate the scatter matrices of the linear discriminant analysis (LDA) method. Finally, the loss function of CNN is modified by the scatter matrices. We choose ten types of targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. The experimental results show that the recognition accuracy of our method is significantly higher than other semi-supervised methods. It has been proved that our method can effectively improve the SAR ATR accuracy when labeled samples are insufficient.

Semi-Supervised Deep Transfer Learning-Based on Adversarial Feature Learning for Label Limited SAR Target Recognition

The data-driven convolutional neural networks (CNNs) have achieved great progress in Synthetic Aperture Radar automatic target recognition (SAR-ATR) after being trained in a large scale of labeled samples. However, the insufficiency of labeled SAR data always leads to over-fitting, causing significant performance degradation. To solve the mentioned problem, a semi-supervised transfer learning method based on generative adversarial networks (GANs) is presented in the present paper. The discriminator of GAN with an encoder and a discriminative layer is redesigned to make it capable of learning the feature representation of input data with unsupervised settings. Instead of training a deep neural network with the insufficient labeled data set, we first train a GAN with varieties of unlabeled samples to learn generic features of SAR images. Subsequently, the learned parameters are readopted to initialize the target network to transfer the generic knowledge to specific SAR target recognition task. Lastly, the target network is fine-tuned using both the labeled and unlabeled training samples by a semi-supervised loss function. We evaluate the proposed method on the MSTAR and OpenSARShip data set with 80%, 60%, 40%, and 20% of the training set labeled, respectively. The results suggest that the proposed method achieves up to 23.58% accuracy enhancement over the random-initialized model.

SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning

Inspired by their tremendous success in optical image detection and classification, convolutional neural networks (CNNs) have recently been used in synthetic aperture radar automatic target recognition (SAR-ATR). Although CNN-based methods can achieve excellent recognition performance, it is difficult to collect a large number of real SAR images available for training. In this paper, we introduce simulated SAR data to alleviate the problem of insufficient training data. To address domain shift and task transfer problems caused by differences between simulated and real data, we propose a model that integrates meta-learning and adversarial domain adaptation. We use sufficient simulated data and a few real data to pre-train the model. After fine-tuning, the pre-trained model can quickly adapt to new tasks in real data. Extensive experimental results obtained in the real SAR dataset demonstrate that our model effectively solves the cross-domain and cross-task transfer problem. Compared with conventional SAR-ATR methods, the proposed model can achieve better recognition performance with a small amount of training data.

Target Recognition of Synthetic Aperture Radar Images Based on Matching and Similarity Evaluation Between Binary Regions

This work uses the binary target region for synthetic aperture radar (SAR) automatic target recognition (ATR). Due to the differences of physical sizes and target shapes, the region residuals among the same classes and those between different targets are distributed in different manners. The Euclidean distance transform is then performed on the region residuals to further enhance such differences, which is beneficial for correctly discriminating different targets. Based on the results, a similarity measure is formed according to the distribution characteristics of the region residuals. In addition, the designed similarity measure considers the possible variations of the target region caused by the nuisance conditions like noise corruption, partial occlusion, etc. Owing to its robustness and comprehensiveness, the similarity measure is applied to target recognition by comparing the test sample with different kinds of template classes. Experiments are undertaken on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under standard operating condition (SOC) and some representative extended operating conditions (EOCs), i.e., configuration variants, depression angle variation, noise corruption, resolution variation and partial occlusion. Moreover, the proposed method is examined under reduced training size and possible azimuth estimation errors for a comprehensive evaluation. The experimental results demonstrate the superiority of the proposed method in comparison with several baseline algorithms in SAR ATR.

SAR ATR of Ground Vehicles Based on LM-BN-CNN

In recent studies, synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms based on convolutional neural network (CNN) have achieved high recognition rates in the moving and stationary target acquisition and recognition (MSTAR) data set. However, the correlation between clutter in the training and test data sets is ignored in these algorithms, although most of them used only the center part of the images by removing a lot of the clutter but not everything, which may result in better performance than what would be achieved in the operational scenarios. To tackle this problem, we propose a target segmentation method based on morphological operations to generate data sets without clutter. Then, we design the large-margin softmax (LM-softmax) batch-normalization CNN (LM-BN-CNN) structure, which utilizes the LM-softmax classifier in the last layer to increase the separability of samples after clutter removal. In addition, this structure performs BN with constant mean and variance to increase the convergence speed and reduce overfitting. Experiments on the MSTAR data set have shown that LM-BN-CNN obtains better performance than the available CNNs designed for SAR ATR of ground vehicles, and it has robustness to large depression angle variation, configuration variants, and version variants.

Multiview Synthetic Aperture Radar Automatic Target Recognition Optimization: Modeling and Implementation

Multiview synthetic aperture radar (SAR) images could provide much richer information for automatic target recognition (ATR) than from a single-view image. It is desirable to find optimal SAR platform flight paths and acquire a sequence of SAR images from appropriate views, so that multiview SAR ATR can be carried out accurately and efficiently. In this paper, a novel optimization framework for multiview SAR ATR is proposed and implemented. The geometry of the multiview SAR ATR is modeled according to the recognition mission and flight environment. Then, the multiview SAR ATR is abstracted and transformed into a constrained multiobjective optimization problem with objective functions considering the tradeoffs between recognition performance and efficiency and security. A specific approach based on convolutional neural network ensemble and constrained nondominated sorting genetic algorithm II is employed to solve the multiobjective optimization, and optimal flight paths and corresponding imaging viewpoints are obtained. The SAR sensor can thus choose an applicable flight path to acquire the multiview SAR images from different tradeoff solutions according to application requirements. Finally, accurate recognition results can be obtained based on those multiview SAR images. Extensive experiments have shown the validity and superiority of the proposed optimization framework of multiview SAR ATR.

Joint classification of complementary features based on multitask compressive sensing with application to synthetic aperture radar automatic target recognition

Joint classification of complementary features based on multitask compressive sensing with application to synthetic aperture radar automatic target recognition

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

In this paper, a robust synthetic aperture radar (SAR) automatic target recognition (ATR) method is proposed by combining the global and local filters, especially aiming to improve the recognition performance under various extended operating conditions (EOCs). Due to the cleanness of the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, which is the prevalent benchmark for SAR ATR, extremely high performance has been reported in many literatures. However, in the real-world scenarios, there exist many types of EOCs such as noise corruption, partial occlusion, sensor variation, etc. Therefore, this study focuses on the SAR ATR problem under several typical EOCs. The intensities of the test image to be classified is taken as the global filter. The spatial correlation between the test image and its corresponding template is calculated as the global response, which describes the global consistency. To depict the local properties of the target, the attributed scattering centers (ASCs) are employed as local filters. Each ASC of the test image is matched with its counterpart from the template ASC set. Then, the local response is evaluated based on the attributes’ differences. The global response and local responses are linearly combined using a random weight matrix. Afterwards, a judgment variable is designed as the measure for target recognition. Experiments are conducted on the MSTAR dataset under the standard operating condition (SOC) and various EOCs including configuration variance, depression angle variance, noise corruption, resolution variance, and partial occlusion. Compared with several state-of-the-art SAR ATR methods, the validity and robustness of the proposed method is fully demonstrated.

SAR-Oriented Visual Saliency Model and Directed Acyclic Graph Support Vector Metric Based Target Classification

The performance of a synthetic aperture radar automatic (SAR) target recognition system mainly depends on feature extraction and classification. It is crucial to select discriminative features to train a classifier to achieve desired performance. In this paper, we propose an efficient feature extraction and classification algorithm based on a visual saliency model. First, an SAR-oriented graph-based visual saliency model is introduced. Second, relying on the ability of our saliency model in highlighting the most significant regions, Gabor and histogram of oriented gradients features are extracted from the processed SAR images. Third, in order to have more discriminative features, the discrimination correlation analysis algorithm is used for feature fusion and combination. Finally, a two-level directed acyclic graph (DAG) support vector metric learning is developed that seamlessly takes advantage of a two-level DAG by eliminating weak classifiers and the Mahalanobis distance-based radial basis function kernel which emphasizes relevant features and reduces the influence of noninformative features. Experiments on real SAR data from the MSTAR database are conducted and the experimental results demonstrate that the proposed method outperforms the state-of-the-art methods.

Target recognition of SAR images by partially matching of target outlines

A synthetic aperture radar (SAR) automatic target recognition method is proposed based on the matching of the target outlines. The target outline describes the physical sizes and shape of the target thus discriminative for SAR target recognition. The original target outline is segmented into several independent parts. The distance between each part and its counterpart in the corresponding template is measured by the least-trimmed square Hausdorff distance. Afterwards, the results of individual parts are combined to form a similarity measure, which comprehensively considers the possible deformations of the target outline. Based on the similarity measure, the target type is determined to be the class sharing the maximum similarity with the test sample. To evaluate the performance of the proposed method, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition dataset under both the standard operating condition and several typical extended operating conditions.

Discriminative Feature Learning for Real-Time SAR Automatic Target Recognition With the Nonlinear Analysis Cosparse Model

This letter presents an efficient application of the nonlinear analysis cosparse model (NACM) to the task of real-time synthetic aperture radar automatic target recognition (ATR). In contrast to the conventional synthesis sparse representation model, NACM enables efficient sparse feature extraction and selection using a feed-forward mechanism. Furthermore, NACM does not require a sparsity-inducing regularizer. This model uses a task-driven learning framework, in which a naive Bayes or a discriminative classifier is adaptively learned along with the regularized features. Experimental results with the moving and stationary target acquisition and recognition benchmark demonstrate the effectiveness and efficiency of our proposed approach. Compared with traditional classification algorithms using sparse representation, our approach not only achieves higher or comparable recognition accuracy but also dramatically reduces the execution time for real-time ATR.

Target Reconstruction Based on 3-D Scattering Center Model for Robust SAR ATR

This paper proposes a robust synthetic aperture radar (SAR) automatic target recognition method based on the 3-D scattering center model. The 3-D scattering center model is established offline from the CAD model of the target using a forward method, which can efficiently predict the 2-D scattering centers as well as the scattering filed of the target at arbitrary poses. For the SAR images to be classified, the 2-D scattering centers are extracted based on the attributed scattering center model and matched with the predicted scattering center set using a neighbor matching algorithm. The selected model scattering centers are used to reconstruct an SAR image based on the 3-D scattering center model, which is compared with the test image to reach a robust similarity. The designed similarity measure comprehensively considers the image correlation between the test image and the model reconstructed image and the model redundancy as for describing the test image. As for target recognition, the model with the highest similarity is determined to the target type of the test SAR image when it is denied to be an outlier. Experiments are conducted on both the data simulated by an electromagnetic code and the data measured in the moving and stationary target acquisition recognition program under standard operating condition and various extended operating conditions to validate the effectiveness and robustness of the proposed method.

Fast ISAR Image Formations Over Multiaspect Angles Using the Shooting and Bouncing Rays

Synthetic aperture radar automatic target recognition (SAR ATR) is a powerful tool for recognizing targets. The SAR ATR needs a massive database of inverse synthetic aperture radar (ISAR) images from computer-aided design (CAD) models for multiple aspect angles. To rapidly build the multiview database, we present a fast method to simulate the ISAR images over multiple aspect angles using the shooting and bouncing ray technique. Compared to the previous fast method where a ray-tracing process must be performed at each aspect angle of the ISAR images, the proposed method generates the ISAR images over multiple aspect angles through only a one-time ray-tracing process at an arbitrary angle. Therefore, the computation time is decreased as much as the number of ray-tracing processes is decreased. Similar to the previous fast method, the proposed method should be used under small angle conditions for perfect electric conductor (PEC) CAD models with a sufficiently smooth surface. The ISAR images of a tank CAD model are simulated over multiple aspect angles to verify the performance of the proposed method.

A Region Matching Approach Based on 3-D Scattering Center Model With Application to SAR Target Recognition

This paper proposes a region matching approach based on 3-D scattering center model with application to synthetic aperture radar (SAR) automatic target recognition (ATR). Each of the model scattering centers is represented by a binary region obtained by segmenting its predicted image using a global threshold. Afterwards, a region-to-region matching algorithm is performed to match the individual predicted regions with the extracted target region from the test image. Three scores are designed to comprehensively evaluate the matching result, which are linearly fused as an overall similarity based on their sparabilities as for discriminating different targets. In the classification stage, a coarse-to-fine region matching is performed and the test image is decided to be the class with the maximum similarity. Experiments are conducted on the simulated data by the electromagnetic code. The results demonstrate that the proposed method outperforms several template-based and model-based SAR ATR methods under the standard operating condition. The superiority of the proposed method becomes more remarkable under various extended operating conditions, including noise corruption, resolution variance, and partial occlusion.

A Deep Convolutional Generative Adversarial Networks (DCGANs)-Based Semi-Supervised Method for Object Recognition in Synthetic Aperture Radar (SAR) Images

Synthetic aperture radar automatic target recognition (SAR-ATR) has made great progress in recent years. Most of the established recognition methods are supervised, which have strong dependence on image labels. However, obtaining the labels of radar images is expensive and time-consuming. In this paper, we present a semi-supervised learning method that is based on the standard deep convolutional generative adversarial networks (DCGANs). We double the discriminator that is used in DCGANs and utilize the two discriminators for joint training. In this process, we introduce a noisy data learning theory to reduce the negative impact of the incorrectly labeled samples on the performance of the networks. We replace the last layer of the classic discriminators with the standard softmax function to output a vector of class probabilities so that we can recognize multiple objects. We subsequently modify the loss function in order to adapt to the revised network structure. In our model, the two discriminators share the same generator, and we take the average value of them when computing the loss function of the generator, which can improve the training stability of DCGANs to some extent. We also utilize images of higher quality from the generated images for training in order to improve the performance of the networks. Our method has achieved state-of-the-art results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and we have proved that using the generated images to train the networks can improve the recognition accuracy with a small number of labeled samples.

Hierarchical Fusion of Convolutional Neural Networks and Attributed Scattering Centers with Application to Robust SAR ATR

This paper proposes a synthetic aperture radar (SAR) automatic target recognition (ATR) method via hierarchical fusion of two classification schemes, i.e., convolutional neural networks (CNN) and attributed scattering center (ASC) matching. CNN can work with notably high effectiveness under the standard operating condition (SOC). However, it can hardly cope with various extended operating conditions (EOCs), which are not covered by the training samples. In contrast, the ASC matching can handle many EOCs related to the local variations of the target by building a one-to-one correspondence between two ASC sets. Therefore, it is promising that both effectiveness and efficiency of the ATR method can be improved by combining the merits of the two classification schemes. The test sample is first classified by CNN. A reliability level calculated based on the outputs from CNN. Once there is a notably reliable decision, the whole recognition process terminates. Otherwise, the test sample will be further identified by ASC matching. To evaluate the performance of the proposed method, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under SOC and various EOCs. The results demonstrate the superior effectiveness and robustness of the proposed method compared with several state-of-the-art SAR ATR methods.

Target Reconstruction Based on Attributed Scattering Centers with Application to Robust SAR ATR

This paper proposes a synthetic aperture radar (SAR) automatic target recognition (ATR) method by target reconstruction based on attributed scattering centers (ASCs). The extracted ASCs can effectively describe the electromagnetic scattering characteristics of the target, while eliminating the background clutters and noises. Therefore, the ASCs are discriminative features for SAR ATR. The neighbor matching algorithm was used to build the correspondence between the test ASC set and corresponding template ASC set. Afterwards, the selected template ASCs were used to reconstruct the template image, whereas all the test ASCs were used to reconstruct the test image based on the ASC model. A similarity measure was further designed based on the reconstructed images for target recognition. Compared with traditional ASC matching methods, the complex one-to-one correspondence between two ASC sets was avoided. Moreover, all the attributes of the ASCs were utilized during the target reconstruction. Therefore, the proposed method can better exploit the discriminability of ASCs to improve the ATR performance. To evaluate the effectiveness and robustness of the proposed method, extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset were conducted under both the standard operating condition (SOC) and typical extended operating conditions (EOCs).

Convolutional neural networks based on augmented training samples for synthetic aperture radar target recognition

A synthetic aperture radar (SAR) automatic target recognition (ATR) method based on the convolutional neural networks (CNN) trained by augmented training samples is proposed. To enhance the robustness of CNN to various extended operating conditions (EOCs), the original training images are used to generate the noisy samples at different signal-to-noise ratios (SNRs), multiresolution representations, and partially occluded images. Then, the generated images together with the original ones are used to train a designed CNN for target recognition. The augmented training samples can contrapuntally improve the robustness of the trained CNN to the covered EOCs, i.e., the noise corruption, resolution variance, and partial occlusion. Moreover, the significantly larger training set effectively enhances the representation capability for other conditions, e.g., the standard operating condition (SOC), as well as the stability of the network. Therefore, better performance can be achieved by the proposed method for SAR ATR. For experimental evaluation, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition dataset under SOC and several typical EOCs.