Synthetic Aperture Radar Target Classification Research Articles

Unsupervised domain adaptation for SAR target classification based on domain- and class-level alignment: From simulated to real data

Synthetic Aperture Radar (SAR) target classification methods based on convolutional neural networks have attracted wide attention recently. Typically, these methods necessitate a substantial quantity of labeled data to train the deep model, which is an obstacle for SAR target classification since annotating SAR images is costly and time-consuming. Generating large-scale labeled data in simulation to train the deep model is a feasible alternative. However, cross-domain recognition is challenging due to significant differences in distribution between simulated and real domains. In this paper, we propose an unsupervised domain adaptation method for SAR target classification by aligning the distribution between the simulated and unlabeled real domains. Specifically, we encode the dependencies across different granularity perspectives including domain-, and class-levels simultaneously to align two domains finely. On the one hand, a gradient-weighted adversarial alignment method is proposed to align the global distributions at the domain-level. On the other hand, a novel class-level alignment method based on the prototypical network is proposed to align the finer class structure. Technically, we respectively model the cross-domain prototype-prototype relations and cross-domain prototype-instance relations with contrastive learning to achieve intra-class prototype compact as well as inter-class prototype separation among cross-domain categories, where the prototypes of the real domain are learned with pseudo labels. To improve the quality of pseudo-labels, a pseudo-label filtering strategy combined with the attribute scattering center is further designed. The experiments on two simulation-to-reality datasets indicate that the proposed method outperforms state-of-the-art unsupervised domain adaptive methods, such as pixelfeat (+4.45% and +7.6% in accuracy on SAMPLE and S2M datasets respectively). Code and data will be available in https://github.com/YuShi1213/Sim2Real-Unsupervised-SAR-Target-Classification.

Contrastive Domain Adaptation-Based Sparse SAR Target Classification under Few-Shot Cases

Due to the imaging mechanism of synthetic aperture radar (SAR), it is difficult and costly to acquire abundant labeled SAR images. Moreover, a typical matched filtering (MF) based image faces the problems of serious noise, sidelobes, and clutters, which will bring down the accuracy of SAR target classification. Different from the MF-based result, a sparse image shows better quality with less noise and higher image signal-to-noise ratio (SNR). Therefore, theoretically using it for target classification will achieve better performance. In this paper, a novel contrastive domain adaptation (CDA) based sparse SAR target classification method is proposed to solve the problem of insufficient samples. In the proposed method, we firstly construct a sparse SAR image dataset by using the complex image based iterative soft thresholding (BiIST) algorithm. Then, the simulated and real SAR datasets are simultaneously sent into an unsupervised domain adaptation framework to reduce the distribution difference and obtain the reconstructed simulated SAR images for subsequent target classification. Finally, the reconstructed simulated images are manually labeled and fed into a shallow convolutional neural network (CNN) for target classification along with a small number of real sparse SAR images. Since the current definition of the number of small samples is still vague and inconsistent, this paper defines few-shot as less than 20 per class. Experimental results based on MSTAR under standard operating conditions (SOC) and extended operating conditions (EOC) show that the reconstructed simulated SAR dataset makes up for the insufficient information from limited real data. Compared with other typical deep learning methods based on limited samples, our method is able to achieve higher accuracy especially under the conditions of few shots.

HENC: Hierarchical Embedding Network With Center Calibration for Few-Shot Fine-Grained SAR Target Classification

Restricted by observation conditions, some scarce targets in the synthetic aperture radar (SAR) image only have a few samples, making effective classification a challenging task. Although few-shot SAR target classification methods originated from meta-learning have made great breakthroughs recently, they only focus on object-level (global) feature extraction while ignoring part-level (local) features, resulting in degraded performance in fine-grained classification. To tackle this issue, a novel few-shot fine-grained classification framework, dubbed as HENC, is proposed in this article. In HENC, the hierarchical embedding network (HEN) is designed for the extraction of multi-scale features from both object-level and part-level. In addition, scale-channels are constructed to realize joint inference of multi-scale features. Moreover, it is observed that the existing meta-learning-based method only implicitly utilize the information of multiple base categories to construct the feature space of novel categories, resulting in scattered feature distribution and large deviation during novel center estimation. In view of this, the center calibration algorithm is proposed to explore the center information of base categories and explicitly calibrate the novel centers by dragging them closer to the real ones. Experimental results on two open benchmark datasets demonstrate that the HENC significantly improves the classification accuracy for SAR targets.

Selecting pseudo supervision for unsupervised domain adaptive SAR target classification

In recent years, deep learning has brought significant progress for the problem of synthetic aperture radar (SAR) target classification. However, SAR image characteristics are highly sensitive to the change of imaging conditions. The inconsistency of imaging parameters (especially the depression angle) leads to the distribution shift between the training and test data and severely deteriorates the classification performance. To address this problem, in this paper we propose an unsupervised domain adaptation method based on selective pseudo-labelling for SAR target classification. Our method directly trains a deep model using the data from the target domain by generating pseudo-labels in the target domain. The key idea is to iteratively select valuable samples from the target domain and optimize the classifier. In each iteration, the breaking ties (BT) criterion is adopted to select the best samples with the highest scores of relative confidence. Besides, to avoid error accumulation in the iterative process, class confusion regularization is used to improve the accuracy of pseudo-labelling. Our method is compared with state-of-the-art methods, including supervised classification and unsupervised domain adaptation methods, over the moving and stationary target acquisition and recognition (MSTAR) dataset. The experimental results demonstrate that the proposed method can achieve better classification performance, especially when the difference of depression angles of the source and target domain images is large. Besides, our method also shows its superiority under limited-sample conditions.

Complex-Valued Sparse SAR-Image-Based Target Detection and Classification

It is known that synthetic aperture radar (SAR) images obtained by typical matched filtering (MF)-based algorithms always suffer from serious noise, sidelobes and clutter. However, the improvement in image quality means that the complexity of SAR systems will increase, which affects the applications of SAR images. The introduction of sparse signal processing technologies into SAR imaging proposes a new way to solve this problem. Sparse SAR images obtained by sparse recovery algorithms show better image performance than typical complex SAR images with lower sidelobes and higher signal-to-noise ratios (SNR). As the most widely applied fields of SAR images, target detection and target classification rely on SAR images with high quality. Therefore, in this paper, a target detection framework based on sparse images recovered by complex approximate message passing (CAMP) algorithm and a novel classification network via sparse images reconstructed by the new iterative soft thresholding (BiIST) algorithm are proposed. Experimental results show that sparse SAR images have better performance whether for target classification or for target detection than the images recovered by MF-based algorithms, which validates the huge application potentials of sparse images.

Multi-Class Dual- Stream Convolutional Neural Network for Synthetic Aperture Radar Automatic Target Recognition of Ground Military Vehicle

Synthetic Aperture Radar (SAR) target classification is one of the largest branches of SAR image analysis. Despite the remarkable achievements of deep learning-based SAR target prediction algorithms, current object recognition algorithms are limited in terms of military applications. Acquisition and labeling of SAR target images are time-consuming and cumbersome. Obtaining adequate training data is also challenging in many cases. Deep learning-based models are always susceptible to overfitting because of insufficient training data. This limitation prevents them from being widely used to classify SAR targets. To overcome the problem of insufficient sampling and to learn more accurate representations for SAR image recognition, we propose a two way input of SAR images into a dual stream of DCNN. Concatenating two input SAR images representations was done using the restricted raw SAR data in order to extract the integral features from the 2 input SAR images representations for classification. The proposed methodology addressed the problem of insufficient sample in SAR target classification and improved classification accuracy without overfitting. Experimental results confirmed that the proposed method is effective in addressing the problem of insufficient sample in SAR target classification. This technique can be integrated into any SAR classification model based on convolutional neural networks (CNNs). The model MCDS-CNN results in a 99.1% recognition accuracy. Despite the limited availability of SAR image data from MSTAR, this approach provides good recognition results.

SAR Target Classification Using the Multikernel-Size Feature Fusion-Based Convolutional Neural Network

It is well-known that the convolutional neural network (CNN) is an effective method for synthetic aperture radar (SAR) target classification. In the convolutional layer of CNN, convolutional kernels of different sizes can extract different feature information of the target. The small-size kernel can extract the local texture feature information, and the large-size kernel can extract the global contour feature information. Traditional CNN methods usually use fixed-size kernels for convolution, and they generally lose part of the target’s feature information, resulting in the inaccurate classification of the SAR targets. This article proposes a novel CNN model based on multikernel-size feature fusion (MKSFF-CNN) for SAR target classification. MKSFF-CNN designs a convolutional methodology with a multichannel parallel topology, it uses convolutional kernels of different sizes to extract the multikernel-size deep features of the SAR target, and then, these features are fused in an optimal way to acquire the lowest loss. Moreover, MKSFF-CNN concatenates the fused features extracted by the convolutional layers of different dimensions to achieve the finest classification. MKSFF-CNN greatly elevates the feature representation completeness of the SAR targets so that more useful feature information can be exploited for SAR target classification. Undoubtedly, MKSFF-CNN can achieve a better classification performance compared with traditional CNN models with a fixed kernel size. The superiority of MKSFF-CNN is validated on the moving and stationary target acquisition and recognition (MSTAR) dataset with the detailed objective and subjective evaluation.

Mixed Loss Graph Attention Network for Few-Shot SAR Target Classification

Restricted by the observation condition, synthetic aperture radar (SAR) automatic target classification based on deep learning usually suffers from insufficient training samples. To tackle this problem, a novel few-shot learning (FSL) framework for SAR target classification, i.e., the mixed loss graph attention network (MGA-Net), is proposed. The classification procedure of the MGA-Net consists of three main stages. In the first stage, the task set is expanded by the data augmentation module to increase diversity. In the second stage, the embedding network is designed to map samples to the embedding space with strong intra-class similarity and inter-class divergence. In the third stage, the multilayer graph attention network (GAT) is constructed and updated according to a novel mixed loss to obtain the classification result. In particular, the data augmentation module alleviates the desire of training samples under large model capacity and enhances the robustness to noise and viewing angle variation; the multilayer GAT accurately captures relations between samples by the attention mechanism; and the mixed loss increases the inter-class separability and accelerates convergence. Experimental results under various few-shot observation settings of the MSTAR and the OpenSARShip benchmark datasets demonstrate that the MGA-Net obtains higher accuracy than typical FSL methods and exhibits robustness to large depression angle variation.

SAR Target Classification Based on Multiscale Attention Super-Class Network

The convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features. On the other hand, conventional CNN approaches only assign fine-class labels to SAR targets, ignoring the high-level semantics information of similar categories, which reduces the feature differences between categories and the generalization ability of the model. Therefore, this paper proposes a multi-scale attention super-class CNN (MSA-SCNN) for SAR target classification. Firstly, MSA-SCNN combines multi-scale feature fusion with the attention module to improve the integrity of SAR target feature representation. The attention module includes channel and spatial attention modules, which realize the weighted enhancement of different scale features. Additionally, MSA-SCNN introduces super-class labels to increase the feature difference between categories. The classification stage consists of a fine-class branch and a super-class branch, and the features trained on the super-class branch are fused to the fine-class branch to improve the network's fine classification ability. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the FUSAR-Ship dataset show that the proposed MSA-SCNN outperforms many current existing state-of-the-art methods.

SCAN: Scattering Characteristics Analysis Network for Few-Shot Aircraft Classification in High-Resolution SAR Images

Recently, deep learning in synthetic aperture radar (SAR) automatic target recognition (ATR) has made significant progress, but the sample limitation problem in the SAR field is still obvious. Compared with the optical remote sensing images, the SAR images are insufficient, especially those containing the geospatial targets with certain target attitude angles (TAAs). To solve these problems, a novel few-shot learning framework named scattering characteristics analysis network (SCAN) is proposed in this article. First, a scattering extraction module (SEM) is designed to combine the target imaging mechanism with the network, which learns the number and distribution of the scattering points for each target type via explicit supervision. Besides, considering the imaging variability of SAR targets, a TAA-guided metalearning network consisting of an angle self-adaption classifier (ASC) and a frequency embedded module (FEM) is designed. ASC guides the network to focus on the positive sample pairs with different TAAs. FEM combines pulse cosine transform (PCT) with the network training process effectively to enrich frequency-domain information. In addition, a new dataset named SAR aircraft category dataset is constructed for the experiments. Compared with other few-shot SAR target classification approaches, our model efficiently integrates the scattering characteristics with the learning process, and the test accuracy for 5-way 1-shot has been improved by 4.74%. Finally, the experimental results are provided to demonstrate the validity of the proposed method.

Amplitude-Phase CNN-Based SAR Target Classification via Complex-Valued Sparse Image

It is known that a synthetic aperture radar (SAR) image obtained by matched filtering (MF)-based algorithms always suffers from serious noise, sidelobes, and clutters. However, the improvement of the image quality means the complexity of the SAR system will increase, which affects the application of the SAR image. The introduction of the sparse signal processing technique into SAR imaging proposes a new way to solve this problem. Sparse SAR image obtained by sparse recovery algorithms shows a better image performance than the typical complex SAR image with lower sidelobes and higher signal-to-noise ratio. As the most widely applied field of the SAR image, target classification relies on the SAR image with high quality. Therefore, a novel target classification model based on the amplitude and phase information of the sparse SAR image is introduced in this article. First, complex sparse image dataset is constructed by a novel iterative soft thresholding (BiIST) algorithm. Compared with typical regularization-based sparse recovery algorithms, BiIST not only can improve the quality of recovered image, but also can obtain a nonsparse solution with retaining phase information and background statistical distribution of the SAR image. Then, targets are classified by the proposed amplitude-phase convolutional neural network (AP-CNN). Typical SAR target classification networks imitate those on optical image, just using amplitude data. However, considering the particularity of the SAR image, the AP-CNN uses both amplitude and phase for training, which theoretically improves the classification accuracy. Experimental results show that the AP-CNN outperforms the typical amplitude-based CNN in target classification, both under standard operating conditions (SOCs) and extended operating conditions (EOCs). Results under SOC demonstrate that the AP-CNN improves the classification accuracy by 11.46% with only 1000 training samples. Even under EOC, the accuracy gap between the AP-CNN and CNN can reach 6.6% in the case of 800 training samples. This means that even if the number of samples is limited, the AP-CNN can obtain optimal classification result.

Few-Shot SAR Target Classification via Metalearning

The state-of-the-art deep neural networks have made a great breakthrough in remote sensing image classification. However, the heavy dependence on large-scale data sets limits the application of the deep learning to synthetic aperture radar (SAR) automatic target recognition (ATR) field where the target sample set is generally small. In this work, a metalearning framework named MSAR, consisting of a metalearner and a base-learner, is proposed to solve the sample restriction problem, which can learn a good initialization as well as a proper update strategy. After training, MSAR can implement fast adaptation with a few training images on new tasks. To the best of our knowledge, this is the first study to solve a few-shot SAR target classification via metalearning. In particular, the few-task problem is defined by analyzing the effect of available training classes on the performance of metalearning models. In order to reduce the metalearning difficulties caused by the few-task problem, three transfer-learning methods are employed, which can leverage the prior knowledge from the pretraining phase. Besides, we design a hard task mining method for effective metalearning. Based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, a specialized data set named NIST-SAR is devised to train and evaluate the proposed method. The experiments on NIST-SAR have shown that the proposed method yields better performances with the largest absolute improvements of 1.7% and 2.3% for 1-shot and 5-shot, respectively, over the next best, which indicates that the proposed method is promising and metalearning is a feasible solution for few-shot SAR ATR.

Extensible Embedded Processor for Convolutional Neural Networks

Convolutional neural networks (CNNs) require significant computing power during inference. Smart phones, for example, may not run a facial recognition system or search algorithm smoothly due to the lack of resources and supporting hardware. Methods for reducing memory size and increasing execution speed have been explored, but choosing effective techniques for an application requires extensive knowledge of the network architecture. This paper proposes a general approach to preparing a compressed deep neural network processor for inference with minimal additions to existing microprocessor hardware. To show the benefits to the proposed approach, an example CNN for synthetic aperture radar target classification is modified and complimentary custom processor instructions are designed. The modified CNN is examined to show the effects of the modifications and the custom processor instructions are profiled to illustrate the potential performance increase from the new extended instructions.

Attribute-Guided Multi-Scale Prototypical Network for Few-Shot SAR Target Classification

Few-shot synthetic aperture radar (SAR) target classification has received more and more attention in recent years, where most of the existing methods have applied existing networks designed for natural images to SAR images, ignoring the special characteristics of SAR data. Therefore, in this paper, we propose an attribute guided multi-scale prototypical network (AG-MsPN) combined with subband decomposition for few-shot SAR target classification, aiming to learn more discriminative features from a few labeled data. Since the SAR images are essentially complex-valued images containing both amplitude and phase information, we employ the subband decomposition on complex-valued SAR images to explore the backscattering behavior variation of targets to get more complete descriptions of targets. Then, considering the complementary information extracted by different convolutional layers, based on prototypical network, a multi-scale prototypical network is proposed to aggregate the features of different layers to enhance the discrimination of feature representations, thus relieving the problem of intraclass diversity and inter-class similarity. Besides, we devise the prior binary attributes of SAR targets and present the attribute classification module to further strengthen the performance of multi-scale prototypical network under the joint supervision of the label and prior attribute information. We demonstrate the effectiveness of our proposed AG-MsPN on the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark dataset and our method surpasses many other existing methods in the few-shot cases.

CNN-Based Target Detection and Classification When Sparse SAR Image Dataset is Available

Synthetic aperture radar (SAR) is an earth observation technology that can obtain high-resolution image in all-weather and all-time conditions, and hence, has been widely used in civil and military applications. SAR target detection and classification are the key processes for the detailed feature information extraction of the interested target. Compared with traditional matched filtering (MF) recovered result, sparse SAR image has lower sidelobes, noise, and clutter. Thus, it will theoretically has better performance in target detection and classification. In this article, we propose a novel sparse SAR image based target detection and classification framework. This novel framework first obtains the sparse SAR image dataset by complex approximate message passing (CAMP), which is an <inline-formula><tex-math notation="LaTeX">$L_1$</tex-math></inline-formula>-norm regularization sparse imaging method. Different from other regularization recovery algorithms, CAMP can output not only a sparse solution, but also a nonsparse estimation of considered scene that well preserves the statistical characteristic of the image when protruding the target. Then, we detect and classify the targets by using the convolutional neural network based technologies from the sparse SAR image datasets constructed by the sparse and nonsparse solutions of CAMP, respectively. For clarify, these two kinds of sparse SAR image datasets are named as <inline-formula><tex-math notation="LaTeX">$\mathcal {D}_{\rm Sp}$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\mathcal {D}_{\rm Nsp}$</tex-math></inline-formula>. Experimental results show that under standard operating conditions, the proposed framework can obtain 92.60&#x0025; and 99.29&#x0025; mAP on Faster RCNN and YOLOv3 by using the <inline-formula><tex-math notation="LaTeX">$\mathcal {D}_{\rm Nsp}$</tex-math></inline-formula> sparse SAR image dataset. Under extended operating conditions, the mAP value of Faster RCNN and YOLOv3 are 95.69&#x0025; and 89.91&#x0025; mAP, respectively. These values based on the <inline-formula><tex-math notation="LaTeX">$\mathcal {D}_{\rm Nsp}$</tex-math></inline-formula> dataset are much higher than the classified result based on the corresponding MF dataset.

SAR Target Classification Based on Integration of ASC Parts Model and Deep Learning Algorithm

Automatic target recognition of synthetic aperture radar (SAR) images has been a vital issue in recent studies. The recognition methods can be divided into two main types: traditional machine learning methods and deep-learning-based methods. For most traditional machine learning methods, target features are extracted based on electromagnetic scattering characteristics which are interpretable and stable. However, the extraction process of effective recognition features is often complex and the computational efficiency is low. Compared with the traditional methods, the deep learning methods can directly learn the high-dimensional features of the target to obtain higher target recognition accuracy. However, these algorithms have poor generalization performance and are difficult to explain. In order to comprehensively consider the advantages of the two kinds of methods, this article proposes a novel method for SAR target classification based on integration parts model and deep learning algorithm. First, part convolution and modified bidirectional convolutional-recurrent network are used to extract local feature of target through parts model which is calculated based on attribute scattering centers. Then, modified all-convolutional networks are used to extract the global feature of the target. The final classification result is achieved through decision fusion of local and global features. Experimental results on the moving and stationary target acquisition and recognition show the superiority of the proposed method, especially under complex conditions. Besides, a brief analysis of target key parts with part occlusion method is given, which is helpful to the interpretability of the deep learning network.

SAR Target Classification Based on Sample Spectral Regularization

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

Target classification of SAR images using nonlinear correlation information entropy

A synthetic aperture radar (SAR) target classification method is proposed by selecting deep features learned by convolutional neural network (CNN) using the nonlinear correlation information entropy (NCIE). The deep feature maps are learned from original SAR images by CNN. Considering the possible indiscrimination and redundancy, all the deep feature maps from different layers are analyzed by NCIE to select out those discriminative ones. The selected feature maps share high inner correlations, which are jointly classified based on joint sparse representation (JSR). Finally, the target label is determined based on the reconstruction errors from JSR. The famous moving and stationary target acquisition and recognition dataset are employed to setup the standard operating condition and several extended operating conditions, including configuration variants, depression angle differences, noise corruption, and partial occlusion, to comprehensively evaluate the performance of the proposed method. The results confirm the superior effectiveness and robustness of the proposed method in comparison with some state-of-the-art SAR target classification methods.

Two-stage sparse representation of NSCT features with application to SAR target classification

To improve synthetic aperture radar (SAR) target classification performance, both the feature extraction and classification algorithms are considered. The nonsubsampled contourlet transform (NSCT) is employed to decompose SAR images to generate multi-layer components, which provide more discriminative descriptions for the targets. During the classification, the two-stage sparse representations are developed. Each NSCT component is classified using the sparse representation-based classification (SRC). Afterwards, the joint sparse representation (JSR) is adopted to represent the selected NSCT components from the first stage, which are assumed to be highly discriminative. Based on the two decisions, the target label of the test sample is determined. In the experiment, the moving and stationary target acquisition and recognition (MSTAR) dataset is used to set up scenarios for performance evaluation including the standard operating condition (SOC) and several extended operating conditions (EOCs). The results show the superior performance of the proposed methodover some current methods.

Shadow Compensation for Synthetic Aperture Radar Target Classification by Dual Parallel Generative Adversarial Network

Due to the incident angle of synthetic aperture radar electromagnetic wave, the ground target is usually captured with some parts missing in the raw SAR image instead of an area of shadow. In recent years, most of the deep learning methods on SAR target classification problems are only applied to the raw SAR images, which require a large number of images to train the neural network for a good result. Aiming at this problem, we propose a novel method for reconstructing the complete target profile to study the SAR target classification problem, which merges two raw SAR images with the opposite azimuth together to one new image. Then, a dual parallel generative adversarial network is proposed to extend the fused SAR image dataset. Finally, we construct a convolutional neural network to train the extended fused image dataset, which outputs the label for each ground target. The experimental result shows that the whole network framework conducted on the MSTAR dataset achieves the average classification accuracy of 99.93% with far fewer data than the state-of-the-art methods, which is a breakthrough in the research process for the SAR target classification with limited labeled data.