Synthetic Aperture Radar Image Recognition Research Articles

SAR Image Target Recognition Method by Global and Local Dictionary Sparse Representation

ABSTRACT Target variant detection has been challenging for Synthetic Aperture Radar (SAR), and the performance of the target variant recognition needs to be further enhanced. SAR images are widely used in the field of target recognition and are important to support reconnaissance operations. This paper proposes a novel research approach to improve the efficiency of target recognition. First, the theory surrounding sparse representation and dictionary learning is presented. Secondly, a SAR image target recognition model is constructed according to the theory. Meanwhile, a dynamic joint sparse representation model is proposed based on multi-information and applied to SAR image target recognition when sparse representation is under consideration. Finally, experiments are set up to validate the proposed model. The results are presented as follows: 1. the recognition rate range of the sample SAR image target is 0.811–0.995 and 0.867–0.990, respectively, when the two cases, without registration processing and with registration processing, utilize the recognition method of dictionary learning and sparse representation. 2. with the increase in dictionary size, the average recognition rate of SAR images based on multi-information dynamic joint sparse representation also increases under the conditions of no logarithm transformation and median filtering and after logarithm transformation and median filtering are run. Then, the average recognition rate range is 0.63–0.9 and 0.65–0.96, respectively. Thus, the recognition rate is improved by 5%-10%. 3. the recognition approach based on the sparse representation of multi-information dynamic joint has distinct sparse degrees of SAR image recognition in the case of logarithmic transformation and median filtering when the sample image has been registered and not been registered. The relative average recognition rates were 0.950–0.970 and 0.955–0.977, respectively. The key contribution of the research is to offer a workable solution to the issues plaguing SAR target variant recognition and to improve the significant limitations in the state-of-the-art literature thoroughly.

SAR-AD-BagNet: An Interpretable Model for SAR Image Recognition Based on Adversarial Defense

Although deep neural networks (DNNs) have achieved good results on some common datasets of synthetic aperture radar (SAR) automatic target recognition (ATR), DNNs are opaque and difficult to interpret, which limits its practical application. In view of this, many interpretable models have been proposed in recent years. However, the previous interpretable models only represent transparent network structures and cannot be called real “interpretable” models. We think that the interpretability of a model contains two meanings: on the one hand, the decision process of the model is transparent, and on the other hand, the decision-making basis of the model should be reasonable and conform to human cognition. For this reason, we propose a new SAR image recognition model based on adversarial defense, namely SAR-AD-BagNet. Not only does it have a transparent decision-making process, but it also has a more reasonable basis for decision-making. In addition, the model also has high SAR image recognition accuracy and strong adversarial robustness.

Dual Consistency Alignment Based Self-Supervised Learning for SAR Target Recognition With Speckle Noise Resistance

Deep learning based on Convolutional Neural Networks (CNN) has been widely applied in Synthetic Aperture Radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called Dual Consistency Alignment based Self-Supervised Learning(DCA-SSL). Firstly, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pre-training is performed on unlabeled data. During this period, we combine instance pseudo-label consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pre-trained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on MSTAR data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition and maintains a high recognition rate even in small sample learning. Our code is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Jordan-Liao/DCA-SSL</uri> .

Synthetic Aperture Radar Target Recognition Based on Multimodule Image Enhancement Network

Synthetic aperture radar (SAR) has been widely used in recent years, and SAR automatic target recognition (ATR) has become a research hotspot. Most of the existing SAR ATR methods focus on the network structure design and increasing data volume but omit image quality and real-time processing. We design a multimodule image enhancement network (MMIE-Net) to solve these problems, which include the target extraction module, the image processing module, and convolutional neural networks (CNNs). First, we use the target extraction module and the image processing module to enhance the quality of raw SAR images. Then we design a suitable network for SAR image recognition, which is simple, lightweight, and recognizable. The experiment was mainly carried out on the MSTAR dataset, which can be divided into two categories, Standard Operating Condition (SOC) and Extended Operating Condition (EOC). The identification accuracy, the parameter storage space, and the depth of the model are considered as the criterion. The experimental results show that, compared with other methods, the proposed method not only ensures the simple structure of the network model but also has better recognition accuracy. Additionally, our method is robust and stable to large depression angle variation as well.

A Few-Shot Learning Method for SAR Images Based on Weighted Distance and Feature Fusion

Convolutional Neural Network (CNN) has been widely applied in the field of synthetic aperture radar (SAR) image recognition. Nevertheless, CNN-based recognition methods usually encounter the problem of poor feature representation ability due to insufficient labeled SAR images. In addition, the large inner-class variety and high cross-class similarity of SAR images pose a challenge for classification. To alleviate the problems mentioned above, we propose a novel few-shot learning (FSL) method for SAR image recognition, which is composed of the multi-feature fusion network (MFFN) and the weighted distance classifier (WDC). The MFFN is utilized to extract input images’ features, and the WDC outputs the classification results based on these features. The MFFN is constructed by adding a multi-scale feature fusion module (MsFFM) and a hand-crafted feature insertion module (HcFIM) to a standard CNN. The feature extraction and representation capability can be enhanced by inserting the traditional hand-crafted features as auxiliary features. With the aid of information from different scales of features, targets of the same class can be more easily aggregated. The weight generation module in WDC is designed to generate category-specific weights for query images. The WDC distributes these weights along the corresponding Euclidean distance to tackle the high cross-class similarity problem. In addition, weight generation loss is proposed to improve recognition performance by guiding the weight generation module. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset and the Vehicle and Aircraft (VA) dataset demonstrate that our proposed method surpasses several typical FSL methods.

Explorations of Contrastive Learning in the Field of Small Sample SAR ATR

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.

Land-Sea Target Detection and Recognition in SAR Image Based on Non-Local Channel Attention Network

Synthetic aperture radar (SAR) target recognition is essential for SAR image interpretation. It has been widely used in national defense and national economy. At present, the SAR image detection and recognition methods based on convolutional neural network (CNN) have problems such as insufficient extraction of the feature information of SAR image targets, false targets caused by the interference of complex backgrounds, and low detection performance. The main reason is that the feature extraction of CNN is a local operation in space and time, which ignores the correlation between pixels and regions and the dependencies between channels in SAR images. In this paper, a non-local channel attention network (NLCANet) SAR image target recognition method is proposed based on the GoogLeNet structure combined with asymmetric pyramid non-local block (APNB) and squeeze-and-excitation block (SEB). APNB is added to the GoogLeNet framework to capture more context information and enhance the correlation between pixels and regions. SEB is added to the Inception structure to become Inception-SEB (ISEB), through which channel dependencies based on the fusion of different scale features can be obtained. The experimental results based on the moving and stationary target acquisition and recognition (MSTAR) dataset and the SAR ship detection dataset (SSDD) show that the proposed method improves the detection ability of targets in complex backgrounds and achieves better land-sea target recognition performance.

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.

A novel few-shot learning method for synthetic aperture radar image recognition

Synthetic aperture radar (SAR) image recognition is an important stage of SAR image interpretation. The standard convolutional neural network (CNN) has been successfully applied in the SAR image recognition due to its powerful feature extraction capability. Nevertheless, the CNN requires numerous labeled samples for satisfactory recognition performance, while the performance of the CNN decreases greatly with insufficient labeled samples. Aiming at improving the SAR image recognition accuracy with a small number of labeled samples, a new few-shot learning method is proposed in this paper. We first utilize the attention prototypical network (APN) to calculate the average features of the support images from each category, which are adopted as the prototypes. Afterwards, the feature extraction is performed on the query images using the attention convolutional neural network (ACNN). Finally, the feature matching classifier (FMC) is adopted for calculating the similarity scores between the feature maps and the prototypes. We embed the attention model SENet to the APN, ACNN, and FMC, which effectively enhances the expression of the prototypes and the feature maps. Besides, the loss function of our method consists of cross-entropy and prototype-separability losses. In the training process, this loss function increases the separability of different prototypes, which contributes to higher recognition accuracy. We perform experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) and the Vehicle and Aircraft (VA) datasets. It has been proved that our method is superior to the related state-of-the-art few-shot image recognition methods.

WITHDRAWN: Sar Image Target Recognition Method Based On Sparse Representation Of Local Dictionary

Abstract Target segments of the Synthetic Aperture Radar (SAR) images are often of SAR images used as one of the challenge the procedure of SAR target recognition interpretation. Segmentation of the object, and then be separated from the target in order to eliminate the background noise or background clutter. However, segmentation may be discarded, and the shadow of the object where the target characteristic further comprises a portion of the difference between object recognition information. Thus, the proposed automatic detection and identification of target SAR image-based approach Sparse Representation Local Dictionary. (SRLD) Using the Model to target detection and recognition experiments to get moving and stationary targets, and identify baseline data set, verify the SAR image recognition field goal deep neural networks' effectiveness.

Adversarial Examples for CNN-Based SAR Image Classification: An Experience Study

Synthetic aperture radar (SAR) has all-day and all-weather characteristics and plays an extremely important role in the military field. The breakthroughs in deep learning methods represented by convolutional neural network (CNN) models have greatly improved the SAR image recognition accuracy. Classification models based on CNNs can perform high-precision classification, but there are security problems against adversarial examples (AEs). However, the research on AEs is mostly limited to natural images, and remote sensing images (SAR, multispectral, etc.) have not been extensively studied. To explore the basic characteristics of AEs of SAR images (ASIs), we use two classic white-box attack methods to generate ASIs from two SAR image classification datasets and then evaluate the vulnerability of six commonly used CNNs. The results show that ASIs are quite effective in fooling CNNs trained on SAR images, as indicated by the obtained high attack success rate. Due to the structural differences among CNNs, different CNNs present different vulnerabilities in the face of ASIs. We found that ASIs generated by nontarget attack algorithms feature attack selectivity, which is related to the feature space distribution of the original SAR images and the decision boundary of the classification model. We propose the sample-boundary-based AE selectivity distance to successfully explain the attack selectivity of ASIs. We also analyze the effects of image parameters, such as image size and number of channels, on the attack success rate of ASIs through parameter sensitivity. The experimental results of this study provide data support and an effective reference for attacks on and the defense capabilities of various CNNs with regard to AEs in SAR image classification models.

A Method Combining CNN and ELM for Feature Extraction and Classification of SAR Image

Due to the large number of Sigmoid activation function derivation in the traditional convolution neural network (CNN), it is difficult to solve the question of the low efficiency of extracting the feature of Synthetic Aperture Radar (SAR) images. The Sigmoid activation function in the CNN is improved to be a rectified linear unit (ReLU) activation function, and the classifier is modified by the Extreme Learning Machine (ELM). Finally, in this CNN model, the improved CNN works as the feature extractor and ELM performs as a recognizer. A SAR image recognition algorithm based on the CNN-ELM algorithm is proposed by combining the CNN and the ELM algorithm. The experiment is conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database which contains 10 kinds of target images. The experiment result shows that the algorithm can realize the sparsity of the network, alleviate the overfitting problem, and speed up the convergence speed of the network. It is worth mentioning that the running time of this experiment is very short. Compared with other experiment on the same database, it indicates that this experiment has generated a higher recognition rate. The accuracy of the SAR image recognition is 100%.

Adaptive convolutional network for SAR image classification

Convolutional neural network (CNN) has an outstanding performance in image classification via extracting highly effective features automatically. However, when CNN is applied to target recognition of synthetic aperture radar (SAR) images, overfitting problem exists since the lack of sufficient labelled SAR images. Hence, based on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset, the authors proposed the Adaptive-Convnet, it has a strong generalisation ability and has a good performance in different testing conditions. Besides, they also studied the transfer learning method to transfer knowledge learned from simulated SAR data to real SAR image recognition, to achieve the purpose of expanding the data set at low cost. When they substitute a part of real T72 images from MSTAR with more simulated T72 SAR images and reduce the dataset bias and enhance transferability in the last three convolution layers, the classification accuracy improved.

The super‐resolution reconstruction of SAR image based on the improved FSRCNN

Synthetic aperture radar (SAR) images have become an important way to obtain information in the military and civilian fields, because of its unique advantages. With the development of technology and the need of application, people subjectively put forward a higher demand for image quality. Image resolution is a key factor for evaluating digital image quality and is the basis for subsequent image processing. However, the image quality of SAR images is far worse than that of optical images because of the imaging mechanism and so on. Therefore, it is more difficult to realise super-resolution reconstruction on SAR images. In the image super-resolution reconstruction method, a reconstruction-based method is generally used, but the effect is poor. A method based on deep learning is used to realise the reconstruction of SAR images based on floating-point data by obtaining the mapping relationship between low-resolution images and high-resolution images. At the same time, the SSIM index is introduced into the loss function, so that the reconstructed SAR image is improved both in subjective visual and in objective evaluation indicators. It lays the foundation for subsequent SAR image recognition and other work.

MF‐SarNet: Effective CNN with data augmentation for SAR automatic target recognition

An effective Max-Fire CNN model MF-SarNet for synthetic aperture radar (SAR) automatic target recognition (ATR) is presented, here. By selecting the convolution kernel of the Fire module in the network, the parameters are reduced to obtain the effective convolutional neural network of less parameter. In view of the requirement of deep learning for large-scale data, an augmentation method is proposed, which can learn the features of large database better. The results based on MSTAR database show that the model is effective and the result is encouraging. The accuracy of SAR image recognition is 98.53%.

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.

SAR Image Recognition with Monogenic Scale Selection-Based Weighted Multi-task Joint Sparse Representation

The monogenic signal, which is defined as a linear combination of a signal and its Riesz-transformed one, provides a great opportunity for synthetic aperture radar (SAR) image recognition. However, the incredibly large number of components at different scales may result in too much of a burden for onboard computation. There is great information redundancy in monogenic signals because components at some scales are less discriminative or even have negative impact on classification. In addition, the heterogeneity of the three types of components will lower the quality of decision-making. To solve the problems above, a scale selection method, based on a weighted multi-task joint sparse representation, is proposed. A scale selection model is designed and the Fisher score is presented to measure the discriminative ability of components at each scale. The components with high Fisher scores are concatenated to three component-specific features, and an overcomplete dictionary is built. Meanwhile, the scale selection model produces the weight vector. The three component-specific features are then fed into a multi-task joint sparse representation classification framework. The final decision is made in terms of accumulated weighted reconstruction error. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset have proved the effectiveness and superiority of our method.

A Novel Active Semisupervised Convolutional Neural Network Algorithm for SAR Image Recognition.

Convolutional neural network (CNN) can be applied in synthetic aperture radar (SAR) object recognition for achieving good performance. However, it requires a large number of the labelled samples in its training phase, and therefore its performance could decrease dramatically when the labelled samples are insufficient. To solve this problem, in this paper, we present a novel active semisupervised CNN algorithm. First, the active learning is used to query the most informative and reliable samples in the unlabelled samples to extend the initial training dataset. Next, a semisupervised method is developed by adding a new regularization term into the loss function of CNN. As a result, the class probability information contained in the unlabelled samples can be maximally utilized. The experimental results on the MSTAR database demonstrate the effectiveness of the proposed algorithm despite the lack of the initial labelled samples.

A Novel SAR Image Recognition Algorithm with Rejection Mode via Biomimetic Pattern Recognition

Due to increasing demand of the modern battlefield awareness and military reconnaissance, Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) has been receiving more and more attention. In this paper, a SAR ATR algorithm with rejection mode based on Local Phase Quantization (LPQ) plus Biomimetic Pattern Recognition (BPR) has been proposed. There are three main steps in the proposed algorithm: firstly, a simple preprocessing procedure based on centroid location is applied to the original SAR image to extract the target’s Region of Interest (ROI). Secondly, Short-term Fourier Transform (STFT) computed over sub-windows at every pixel of the ROI image is performed and the extracted information of the Fourier phase spectrum is quantized as features to overcome the target’s azimuth angle variations. Finally, high dimensional geometry space covering method based on BPR theory is adopted and hyper-sausage neuron is employed to construct geometry coverage for the purpose of recognizing or rejecting the incoming targets. Experiments on the public standard MSTAR database show that this proposed algorithm can achieve relatively high recognition rate while obtaining high rejection rate for unknown incoming targets.

Two-beam-coupling correlator for synthetic aperture radar image recognition with power-law scattering centers preenhancement

Synthetic radar image recognition is an area of interest for military applications including automatic target recognition, air traffic control, and remote sensing. Here a dynamic range compression two-beam-coupling joint transform correlator for detecting synthetic aperture radar targets is utilized. The joint input image consists of a prepower-law, enhanced scattering center of the input image and a linearly synthesized power-law-enhanced scattering center template. Enhancing the scattering center of both the synthetic template and the input image furnishes the conditions for achieving dynamic range compression correlation in two-beam coupling. Dynamic range compression (a) enhances the signal-to-noise ratio, (b) enhances the high frequencies relative to low frequencies, and (c) converts the noise to high frequency components. This improves the correlation-peak intensity to the mean of the surrounding noise significantly. Dynamic range compression correlation has already been demonstrated to outperform many optimal correlation filters in detecting signals in severe noise environments. The performance is evaluated via established metrics such as peak-to-correlation energy, Horner efficiency, and correlation-peak intensity. The results showed significant improvement as the power increased.