Synthetic Aperture Radar Target Classification Research Articles

SAR target classification using multi-aspect multi-feature collaborative representation

ABSTRACT In this paper, a novel approach is proposed for Synthetic Aperture Radar (SAR) target classification based on multi-aspect multi-feature collaborative representation. Firstly, principal component analysis (PCA), wavelet and 2-dimensional slice Zernike moments (2DSZM) features are extracted from SAR images. Next, based on the strong correlation among the adjacent aspect SAR target images, we extend the basic collaborative representation classification (CRC) model to a neighbourhood multi-aspect CRC model. For each feature of the current test sample, neighbourhood multi-aspect test samples are regarded as the input to the model, then the temporary label is obtained for the current test sample under this feature. Finally, the temporary label is fused using the voting method to get the final classification result. The novelty of the proposed method is to improve the performance of target classification by integrating representation learning ability of different features and exploiting neighbourhood multi-aspect correlation. Experiments are investigated on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. The results show that the proposed algorithm can achieve a 98.52% overall accuracy and is superior to state-of-the-art methods for SAR target classification.

Representation of BVMD features via multitask compressive sensing for SAR target classification

ABSTRACT This letter develops a synthetic aperture radar (SAR) target classification method based on bidimensional variational mode decomposition (BVMD) and multitask compressive sensing (MTCS). BVMD is employed to decompose SAR images to exploit the time-frequency properties of the described targets. The MTCS is used to jointly classify the original SAR image and its BVMD components. So, the merits of BVMD and MTCS can be combined in the proposed method. Finally, based on the reconstruction errors, the target label can be decided. The Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset is used to set up experimental conditions to test the proposed method. By comparison with several reference methods from published works, the effectiveness and robustness of the proposed method can be confirmed.

Spatial–Temporal Ensemble Convolution for Sequence SAR Target Classification

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.

SAR Target Classification Based on Deep Forest Model

Synthetic aperture radar (SAR) has become one of the most important means of information acquisition in today’s society and shows great potential in many fields. Target identification and classification of SAR images are also the focus of research. With the vigorous development of deep learning, many researchers apply this method to SAR target classification to obtain a more automatic process and more accurate results. In this paper, a novel deep forest model constructed by multi-grained cascade forest (gcForest), which is different from the traditional neural network (NN) model, is employed to classify ten types of SAR targets in the moving and stationary target acquisition and recognition (MSTAR) dataset. Considering that the targets of input images may be off-center and of different sizes in practical applications, two improved models based on varying weights by image features have been put forward, and both obtain better results. A series of experiments have been conducted to optimize model parameters, and final results with the MSTAR dataset illustrate that the two improved models are both superior to the original gcForest model. This is the first attempt to classify SAR targets using the non-NN model.

Multiview Low-Rank Hybrid Dilated Network for SAR Target Recognition Using Limited Training Samples

Deep learning (DL) have been intensively exploited for synthetic aperture radar (SAR) target classification, and we have witnessed exciting performances provided by previous studies. Multiview-based DL methods exhibited huge potentials for SAR target classification since they can generate adequate sample images from few raw images. In order to further improve the generalization performance of the multiview-based framework with limited training samples, we propose a novel multiview low-rank hybrid dilated network (MLHDN) for SAR target recognition. Firstly, we design a parameter-sharing hybrid dilated convolution (HDC) to learn multiview features. Secondly, a composite low-rank bilinear pooling (CLRBP) is proposed to fuse multiview features and to reduce their dimensions, yielding class-oriented and compacted feature vectors which are distinctive and representative for classification. Finally, a Softmax layer is used as a classifier. Accordingly, MLHDN encompasses fewer parameters compared to existing multiview-based DL methods. Experimental results demonstrate that MLHDN can achieve state-of-the-art performances on the moving and stationary target acquisition and recognition (MSTAR) datasets for SAR target classification, yielding an accuracy of 96.13% with only 10 training samples per class.

A SAR Target Recognition Based on Guided Reconstruction and Weighted Norm-Constrained Deep Belief Network

The deep learning has some new vitality to the synthetic aperture radar (SAR) automatic target recognition (ATR). By introducing different constraints, deep belief network (DBN) has become apply to SAR target recognition recent years, but the existing DBN algorithms have some questions including the high training epochs, low recognition rate and complex structure. Therefore, an algorithm based on guided reconstruction and weighted norm-constrained DBN is proposed. Firstly, in order to reduce the dimension of the image output feature, increase the speed of preprocessing, generate a one-dimensional image vector and normalized, a SAR target classification algorithm with two-scale fusion character based on guided filter reconstruction algorithm is introduced. Then, the sparse feature extraction of SAR image is carried out by weighted norm-constrained DBN. By the regularization constraint of the probability distribution, the algorithm can minimize the joint probability distribution of visual layer and hidden layer by samples. The low-dimensional feature is further improved based on the generalized optimization of norm-constrained RBM. Finally, by a regularized Softmax which can classify the targets and obtain output results. The experimental results show that the SAR target recognition algorithm based on the guided reconstruction and weighted constrained deep confidence network not only improves the target recognition performance and generalization ability, but also reduces the output feature dimension and network training times, and the recognition performance of the algorithm is further improved.

Complex-Valued Full Convolutional Neural Network for SAR Target Classification

Complex-valued convolutional neural network (CV-CNN) has been presented in recent years. In this letter, CV full convolutional neural network (CV-FCNN) is proposed for synthetic aperture radar (SAR) target classification, which contains only convolution layers in the hidden layer. The purpose of replacing both the pooling and fully connected layers in CV-CNN with the convolution layers is to avoid complex pooling operation and prevent overfitting, respectively. Considering the label of target is always real-valued, the magnitude of the complex vector obtained from the last convolution layer is calculated before softmax classification in the output layer. Moreover, the back-propagation formula for each layer of CV-FCNN is presented in detail. Furthermore, the complex <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> convolution layer is added into CV-FCNN to learn the cross-channel information of feature maps. The experimental results show that the average accuracy can be improved using CV-FCNN, and it is further improved using CV-FCNN with the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> convolution layer.

Sequence SAR Image Classification Based on Bidirectional Convolution-Recurrent Network

Although the deep convolutional neural network (DCNN) has been successfully applied to target classification of military vehicles based on synthetic aperture radar (SAR), most of the available methods do not fully exploit the characteristics of continuous SAR imaging and only utilize single image for recognition. To extract significant identification features contained in the image sequence, this paper proposes a sequence of SAR target classification method based on bidirectional convolution-recurrent network. In this network, we extract spatial features of each image through DCNNs without the fully connected layer, and then learn sequence features by bidirectional long short-term memory networks. Finally, we design the average softmax classifier to obtain the classification results. Compared with the available methods, the proposed network takes advantage of the significant information in the image sequence and achieves higher classification accuracy in the moving and stationary target acquisition and recognition data set. In addition, it has shown robustness to large depression angle variants, configuration variants, and version variants.

Efficient deep convolutional neural networks using CReLU for ATR with limited SAR images

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.

Synthetic aperture radar target classification via joint sparse representation of multi-level dominant scattering images

As one of the key steps in synthetic aperture radar (SAR) target classification, feature extraction plays an important role. In this study, the multi-level dominant scattering images (DSIs) are generated based on the original images, which can better convey the discrimination capability. DSI is generated by selecting a certain number of dominant scattering points in the original image, which describes the relative positions and amplitudes of the dominant scattering centers. In addition, the background noises, which are usually with low intensities, can be effectively eliminated with high efficiency. For a test sample, each of multi-level DSIs is classified by sparse representation classification (SRC) at first and a reliability level is calculated based on the reconstruction errors, which reflects its contribution to the correct recognition of the present sample. A prescreening of the multi-level DSIs is performed based on their reliability levels. Only those DSIs with higher reliability levels than a predefined threshold is used for target recognition. Afterwards, the selected multi-level DSIs are jointly classified by joint sparse representation (JSR). JSR is actually a multi-task learning algorithm, which comprehensively considers the individual tasks as well as their inner correlations. Therefore, it can better make use of the multi-level to improve the target classification performance. The moving and stationary target acquisition and recognition (MSTAR) dataset is used for experimental evaluation. The results illustrate that the proposed method could achieve notably high recognition accuracy over 97.5% under the standard operating condition (SOC). Moreover, the robustness of the proposed method to various extended operating conditions (EOCs), e.g., configuration variants, large depression variation, noise corruption and partial occlusion, is also superior over some state-of-the-art SAR target classification methods by comparison.

A novel group squeeze excitation sparsely connected convolutional networks for SAR target classification

ABSTRACTAutomatic Target Recognition (ATR) based on Synthetic Aperture Radar (SAR) images plays a key role in military applications. However, there are difficulties with this traditional recognition method. Principally, it is a challenge to design robust features and classifiers for different SAR images. Although Convolutional Neural Networks (CNNs) are very successful in many image classification tasks, building a deep network with limited labeled data remains a problem. The topologies of CNNs like the fully connected structure will lead to redundant parameters and the negligence of channel-wise information flow. A novel CNNs approach, called Group Squeeze Excitation Sparsely Connected Convolutional Networks (GSESCNNs), is therefore proposed as a solution. The group squeeze excitation performs dynamic channel-wise feature recalibration with less parameters than squeeze excitation. Sparsely connected convolutional networks are a more efficient way to operate the concatenation of feature maps from different layers. Experimental results on Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR images, demonstrate that this approach achieves, at 99.79%, the best prediction accuracy, outperforming the most common skip connection models, such as Residual Networks and Densely Connected Convolutional Networks, as well as other methods reported in the MSTAR dataset.

Synthetic Aperture Radar Target Recognition Using Weighted Multi-Task Kernel Sparse Representation

As an extension of traditional sparse representation (SR), kernel SR has received great interest recently in the areas of computer vision and pattern recognition. It shows a considerable capacity to map linearly inseparable data into high-dimensional feature space via nonlinear mapping technique, and has been widely used in target recognition problems. In this paper, we propose a new weighted multi-task kernel sparse representation method to solve the synthetic aperture radar (SAR) target recognition problem. To capture the spatial and spectral information of a SAR target simultaneously, the proposed method explores the monogenic signal transformation to generate multi-scale monogenic features at first. Then, the proposed method provides a unified framework, named multi-task kernel sparse representation, for SAR target classification. The framework implicitly maps monogenic features into a high-dimensional kernel feature space by using the nonlinear mapping associated with a kernel function. In the kernelized subspace, SAR target recognition is formulated as a joint covariate selection problem across a group of related tasks. Furthermore, a multi-task weight optimization scheme is developed to compensate for the heterogeneity of the multi-scale features and enhance the recognition performance. Extensive experimental results tested on the public moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate that our proposed method achieves better recognition performance than other existing competitive algorithms.

Ground Target Classification in Noisy SAR Images Using Convolutional Neural Networks

Speckle noise is an inherent but annoying property in the synthetic aperture radar (SAR) imaging. In this paper we investigate the influence of speckle on the classical convolutional neural network (CNN) for SAR target classification. Then a dual stage coupled CNN architecture, named despeckling and classification coupled CNNs (DCC-CNNs), is proposed to distinguish multiple categories of ground targets in SAR images with strong and varying speckle. It first applies the despeckling sub-network for noise reduction. After that, residual speckle features as well as target information would be learned by the classification sub-network in order to solve the noise robustness problem of CNN. Besides, a new quantitative measure is developed for the quality assessment of SAR target images. It takes into account structural properties of the speckled SAR image of the target of interest and consistency with visual perception. Finally, a series of comparative experiments and discussions are carried out to validate the proposed assessment criterion and DCC-CNNs. Using synthetic SAR images based on the public MSTAR datasets, results show that the overall classification accuracy for ten ground target classes could be higher than 82% at a variety of speckle noise levels.

Deep feature extraction and combination for synthetic aperture radar target classification

Feature extraction has always been a difficult problem in the classification performance of synthetic aperture radar automatic target recognition (SAR-ATR). It is very important to select discriminative features to train a classifier, which is a prerequisite. Inspired by the great success of convolutional neural network (CNN), we address the problem of SAR target classification by proposing a feature extraction method, which takes advantage of exploiting the extracted deep features from CNNs on SAR images to introduce more powerful discriminative features and robust representation ability for them. First, the pretrained VGG-S net is fine-tuned on moving and stationary target acquisition and recognition (MSTAR) public release database. Second, after a simple preprocessing is performed, the fine-tuned network is used as a fixed feature extractor to extract deep features from the processed SAR images. Third, the extracted deep features are fused by using a traditional concatenation and a discriminant correlation analysis algorithm. Finally, for target classification, K-nearest neighbors algorithm based on LogDet divergence-based metric learning triplet constraints is adopted as a baseline classifier. Experiments on MSTAR are conducted, and the classification accuracy results demonstrate that the proposed method outperforms the state-of-the-art methods.

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

Tremendous progress has been made in object recognition with deep convolutional neural networks (CNNs), thanks to the availability of large-scale annotated dataset. With the ability of learning highly hierarchical image feature extractors, deep CNNs are also expected to solve the Synthetic Aperture Radar (SAR) target classification problems. However, the limited labeled SAR target data becomes a handicap to train a deep CNN. To solve this problem, we propose a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data. We design an assembled CNN architecture consisting of a classification pathway and a reconstruction pathway, together with a feedback bypass additionally. Instead of training a deep network with limited dataset from scratch, a large number of unlabeled SAR scene images are used to train the reconstruction pathway with stacked convolutional auto-encoders (SCAE) at first. Then, these pre-trained convolutional layers are reused to transfer knowledge to SAR target classification tasks, with feedback bypass introducing the reconstruction loss simultaneously. The experimental results demonstrate that transfer learning leads to a better performance in the case of scarce labeled training data and the additional feedback bypass with reconstruction loss helps to boost the capability of classification pathway.

Deep Convolutional Highway Unit Network for SAR Target Classification With Limited Labeled Training Data

The deep convolutional neural network (CNN) has been widely used for target classification, because it can learn highly useful representations from data. However, it is difficult to apply a CNN for synthetic aperture radar (SAR) target classification directly, for it often requires a large volume of labeled training data, which is impractical for SAR applications. The highway network is a newly proposed architecture based on CNN that can be trained with smaller data sets. This letter proposes a novel architecture called the convolutional highway unit to train deeper networks with limited SAR data. The unit architecture is formed by modified convolutional highway layers, a maxpool layer, and a dropout layer. Then, the networks can be flexibly formed by stacking the unit architecture to extract deep feature representations for classification. Experimental results on the moving and stationary target acquisition and recognition data set indicate that the branched ensemble model based on the unit architecture can achieve 99% classification accuracy with all training data. When the training data are reduced to 30%, the classification accuracy of the ensemble model can still reach 94.97%.

Tensor subclass discriminant analysis for radar target classification

A novel tensor subspace learning algorithm, called tensor subclass discriminant analysis, is presented for inverse synthetic aperture radar target classification. Assuming there are multiple subclasses in each class of inverse synthetic aperture radar data, an objective function, which is based on clustering based analysis criterion and aimed at maximising the distance between subclasses of different classes, is constructed for target classification using inverse synthetic aperture radar images in the form of a tensor. Then the formula of the algorithm is deduced, and the optimal tensor projections for classification are worked out. Simulation demonstrates the effectiveness and robustness of the proposed method.

Statistical target behaviour in SAR images

The paper discusses the statistical behaviour of targets in synthetic aperture radar (SAR) images and demonstrates how this information can be exploited for automatic SAR target classification and recognition. It describes a target-smoothing algorithm for estimating the underlying radar cross-section, which can be used with an appropriate noise model to generate many target realisations for a given imaging configuration. This allows a statistical analysis of target features to be performed that can be used to enhance feature-based classification, as is demonstrated by a simple classification experiment using real targets.