Automatic Target Recognition Performance Research Articles

CycleGAN-Based SAR-Optical Image Fusion for Target Recognition

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

Azimuth-Aware Discriminative Representation Learning for Semi-Supervised Few-Shot SAR Vehicle Recognition

Among the current methods of synthetic aperture radar (SAR) automatic target recognition (ATR), unlabeled measured data and labeled simulated data are widely used to elevate the performance of SAR ATR. In view of this, the setting of semi-supervised few-shot SAR vehicle recognition is proposed to use these two forms of data to cope with the problem that few labeled measured data are available, which is a pioneering work in this field. In allusion to the sensitivity of poses of SAR vehicles, especially in the situation of only a few labeled data, we design two azimuth-aware discriminative representation (AADR) losses that suppress intra-class variations of samples with huge azimuth-angle differences, while simultaneously enlarging inter-class differences of samples with the same azimuth angle in the feature-embedding space via cosine similarity. Unlabeled measured data from the MSTAR dataset are labeled with pseudo-labels from categories among the SARSIM dataset and SAMPLE dataset, and these two forms of data are taken into consideration in the proposed loss. The few labeled samples in experimental settings are randomly selected in the training set. The phase data and amplitude data of SAR targets are all taken into consideration in this article. The proposed method achieves 71.05%, 86.09%, and 66.63% under 4-way 1-shot in EOC1 (Extended Operating Condition), EOC2/C, and EOC2/V, respectively, which overcomes other few-shot learning (FSL) and semi-supervised few-shot learning (SSFSL) methods in classification accuracy.

One-Shot HRRP Generation for Radar Target Recognition

Insufficient data of a noncooperative target seriously affect the performance of radar automatic target recognition (RATR) using the high-resolution range profile (HRRP), especially when the noncooperative target has only one sample. To this end, we propose an unsupervised data generation method to generate noncooperative HRRP signals. We utilize the pretrained generative adversarial networks (GANs) model to learn the HRRP general probability distribution. To emphasize the representative and discriminative power of generated HRRP signals, a joint optimization method is proposed to preserve category information. Moreover, a feature diversification method is proposed to make the generated samples have sufficient aspect characteristics to further fit the probability distribution of the noncooperative target. Thus, the generated HRRP signals can effectively improve the recognition performance of noncooperative target. Extensive experiments on HRRP data sets demonstrate the superior performance of our method over other state-of-the-art methods.

A Convolutional Neural Network Combined with Attributed Scattering Centers for SAR ATR

It is very common to apply convolutional neural networks (CNNs) to synthetic aperture radar (SAR) automatic target recognition (ATR). However, most of the SAR ATR methods using CNN mainly use the image features of SAR images and make little use of the unique electromagnetic scattering characteristics of SAR images. For SAR images, attributed scattering centers (ASCs) reflect the electromagnetic scattering characteristics and the local structures of the target, which are useful for SAR ATR. Therefore, we propose a network to comprehensively use the image features and the features related to ASCs for improving the performance of SAR ATR. There are two branches in the proposed network, one extracts the more discriminative image features from the input SAR image; the other extracts physically meaningful features from the ASC schematic map that reflects the local structure of the target corresponding to each ASC. Finally, the high-level features obtained by the two branches are fused to recognize the target. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset prove the capability of the SAR ATR method proposed in this letter.

Multiview Deep Feature Learning Network for SAR Automatic Target Recognition

Multiview synthetic aperture radar (SAR) images contain much richer information for automatic target recognition (ATR) than a single-view one. It is desirable to establish a reasonable multiview ATR scheme and design effective ATR algorithm to thoroughly learn and extract that classification information, so that superior SAR ATR performance can be achieved. Hence, a general processing framework applicable for a multiview SAR ATR pattern is first given in this paper, which can provide an effective approach to ATR system design. Then, a new ATR method using a multiview deep feature learning network is designed based on the proposed multiview ATR framework. The proposed neural network is with a multiple input parallel topology and some distinct deep feature learning modules, with which significant classification features, the intra-view and inter-view features existing in the input multiview SAR images, will be learned simultaneously and thoroughly. Therefore, the proposed multiview deep feature learning network can achieve an excellent SAR ATR performance. Experimental results have shown the superiorities of the proposed multiview SAR ATR method under various operating conditions.

Multi-Block Mixed Sample Semi-Supervised Learning for SAR Target Recognition

In recent years, synthetic aperture radar (SAR) automatic target recognition has played a crucial role in multiple fields and has received widespread attention. Compared with optical image recognition with massive annotation data, lacking sufficient labeled images limits the performance of the SAR automatic target recognition (ATR) method based on deep learning. It is expensive and time-consuming to annotate the targets for SAR images, while it is difficult for unsupervised SAR target recognition to meet the actual needs. In this situation, we propose a semi-supervised sample mixing method for SAR target recognition, named multi-block mixed (MBM), which can effectively utilize the unlabeled samples. During the data preprocessing stage, a multi-block mixed method is used to interpolate a small part of the training image to generate new samples. Then, the new samples are used to improve the recognition accuracy of the model. To verify the effectiveness of the proposed method, experiments are carried out on the moving and stationary target acquisition and recognition (MSTAR) data set. The experimental results fully demonstrate that the proposed MBM semi-supervised learning method can effectively address the problem of annotation insufficiency in SAR data sets and can learn valuable information from unlabeled samples, thereby improving the recognition performance.

SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

The effectiveness of using the simulated synthetic aperture radar (SAR) images of military targets in databases for automatic target recognition (ATR) is widely known. However, for simulated target images to be useful, they must be sufficiently similar to measured images; otherwise, they can degrade ATR performance. Two factors affect the quality of simulated SAR images: precision of the associated computer-aided design (CAD) model of the target and the accuracy and speed of the numerical techniques used to solve the electromagnetic problems in SAR image generation. In this study, a method for the 3D CAD modeling of the target is proposed; this method can be used when direct access to the target is not feasible and only indirect information is available. Further, a bistatic image formation concept based on the shooting-and-bouncing-ray technique is adopted; this concept helps achieve an accuracy comparable to that of the monostatic method. Moreover, it helps achieve a highly enhanced computation speed. In combination, these proposals provide an efficient and fast method to generate a database of simulated SAR images that can effectively support ATR activities. We demonstrate the effectiveness of the proposed method by comparing the simulated SAR images with the measured ones using structural similarity as a similarity measure; further, we evaluate the recognition rate obtained with the simulated images. We show that the used similarity measure bears a strong relation with the recognition rate, which is an aspect that may further contribute to considerable time savings when validating and refining simulated image databases.

Feature-Enhanced Speckle Reduction via Low-Rank and Space-Angle Continuity for Circular SAR Target Recognition

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

Infrared Image Complexity Metric for Automatic Target Recognition Based on Neural Network and Traditional Approach Fusion

Infrared image complexity metric plays an important role in automatic target recognition (ATR) performance evaluation. In particular, with the development of the infrared imaging technology, there are many excellent infrared image complexity metrics for ATR. However, in the related works, there are two aspects of imperfections: (1) only the influence of individual feature is considered, ignoring the interaction among characteristics; and (2) these metrics all do not take the degradation of thermal imaging process into account. To overcome the imperfections, a novel criterion of evaluating infrared image complexity which considers the interaction among characteristics and the degradation influence is proposed. Firstly, to achieve complementary advantages among characteristics, the feature space is introduced to establish three image complexity indicators, respectively, namely feature space degradation complexity (FSDC), feature space similarity degree of global background and feature space occultation degree of local background. Each indicator is integrated by feature space to obtain complementary advantages. Secondly, to take the degradation of thermal imaging process into account, the neural network is trained to obtain the FSDC. In addition, the feature spaces are perfected by Pearson’s correlation analysis and relevant features were removed so that each indicator is more reasonable. Finally, we connect the three image complexity indicators by using an improved analytic hierarchy process. The experimental results show that the proposed algorithm is more consistent with the actual situation than traditional statistical variance and signal-to-noise ratio.

Complexity Estimation of Infrared Image Sequence for Automatic Target Track

Infrared image complexity metrics are an important task of automatic target recognition and track performance assessment. Traditional metrics, such as statistical variance and signal-to-noise ratio, targeted to single frame infrared image. However, there are some studies on the complexity of infrared image sequences. For this problem, a method to measure the complexity of infrared image sequence for automatic target recognition and track is proposed. Firstly, based on the analysis of the factors affecting the target recognition and track, the specific reasons which background influences target recognition and track are clarified, and the method introduces the feature space into confusion degree of target and occultation degree of target respectively. Secondly, the feature selection is carried out by using the grey relational method, and the feature space is optimized, so that confusion degree of target and occultation degree of target are more reasonable, and statistical formula F1-Score is used to establish the relationship between the complexity of single-frame image and the two indexes. Finally, the complexity of image sequence is not a linear sum of the single-frame image complexity. Target recognition errors often occur in high-complexity images and the target of low-complexity images can be correctly recognized. So the neural network Sigmoid function is used to intensify the high-complexity weights and weaken the low-complexity weights for constructing the complexity of image sequence. The experimental results show that the present metric is more valid than the other, such as sequence correlation and inter-frame change degree, has a strong correlation with the automatic target track algorithm, and which is an effective complexity evaluation metric for image sequence.

Fusing Deep Learning and Sparse Coding for SAR ATR

We propose a multimodal and multidiscipline data fusion strategy appropriate for automatic target recognition (ATR) on synthetic aperture radar imagery. Our architecture fuses a proposed clustered version of the AlexNet convolutional neural network with sparse coding theory that is extended to facilitate an adaptive elastic net optimization concept. Evaluation on the MSTAR dataset yields the highest ATR performance reported yet, which is 99.33% and 99.86% for the three- and ten-class problems, respectively.

Target recognition for synthetic aperture radar imagery based on convolutional neural network feature fusion (Erratum)

Driven by the great success of deep convolutional neural networks (CNNs) that are currently used by quite a few computer vision applications, we extend the usability of visual-based CNNs into the synthetic aperture radar (SAR) data domain without employing transfer learning. Our SAR automatic target recognition (ATR) architecture efficiently extends the pretrained Visual Geometry Group CNN from the visual domain into the X-band SAR data domain by clustering its neuron layers, bridging the visual—SAR modality gap by fusing the features extracted from the hidden layers, and by employing a local feature matching scheme. Trials on the moving and stationary target acquisition dataset under various setups and nuisances demonstrate a highly appealing ATR performance gaining 100% and 99.79% in the 3-class and 10-class ATR problem, respectively. We also confirm the validity, robustness, and conceptual coherence of the proposed method by extending it to several state-of-the-art CNNs and commonly used local feature similarity/match metrics.

Target recognition for synthetic aperture radar imagery based on convolutional neural network feature fusion

Driven by the great success of deep convolutional neural networks (CNNs) that are currently used by quite a few computer vision applications, we extend the usability of visual-based CNNs into the synthetic aperture radar (SAR) data domain without employing transfer learning. Our SAR automatic target recognition (ATR) architecture efficiently extends the pretrained Visual Geometry Group CNN from the visual domain into the X-band SAR data domain by clustering its neuron layers, bridging the visual—SAR modality gap by fusing the features extracted from the hidden layers, and by employing a local feature matching scheme. Trials on the moving and stationary target acquisition dataset under various setups and nuisances demonstrate a highly appealing ATR performance gaining 100% and 99.79% in the 3-class and 10-class ATR problem, respectively. We also confirm the validity, robustness, and conceptual coherence of the proposed method by extending it to several state-of-the-art CNNs and commonly used local feature similarity/match metrics.

Seafloor Description in Sonar Images Using the Monogenic Signal and the Intrinsic Dimensionality

In a mine warfare context, the performance of automatic target recognition (ATR) algorithms depends on the environment. Globally, minelike textures and regions with high clutter density increase the false alarm rate. Thus, the environment must be considered as information that can be used to define robust ATR or at least to give a level of confidence in the results according to the seafloor environment. Previous works dealing with this objective have led to the description of the seafloor in terms of anisotropy and complexity. Following these approaches, in this paper, we propose a new definition of these features for describing the seafloor in sonar images. It is based on the monogenic representation of the images and the continuous intrinsic dimensionality (ciD). The monogenic signal, which is the multidimensional extension of the analytic signal, provides an orthogonal separation between energetic, geometric, and structural information of the image in a multiscale framework. The ciD provides information on 2-D geometric structures in the image. The resulting method leads to continuous values giving a confidence degree in relation to three features: the homogeneity, the anisotropy, and the complexity. Several data sets from different sonar systems are used to show the potential of our approach. They also show the ability of the method to deal with different image sources without changing or recalibrating the number of parameters.

Simulated target insertion for automatic target recognition performance estimation

To support automatic target recognition (ATR) algorithm development as well as predict their performance in various operational environments, there is a need for more realistic sonar data that captures environmental effects that are not only difficult to model using physical acoustical models but expensive to measure in the real world. Previous target insertion efforts have focused on high frequency imaging sonar. As such, these efforts effectively combine only the magnitudes of the real and simulated data. This effort will focus on low frequency sonar, and the goal is to retain the phase by combining the complex data where possible. Maintaining the phase allows us to take advantage of the resonant frequency information available in the lower frequency bands, which is lost when the magnitudes are summed. In this effort, several approaches to inserting simulated target data into real sonar data will be investigated. Typically, there are no shadows in the low frequency images; therefore, none of the approaches investigated here take shadows into account. For each method, an analysis will be carried out to evaluate how the simulated targets behave compared to real targets. These analyses will be performed on real and simulated image snippets, gradients of snippets, and the frequency content of the target scattering response or acoustic color plots. The analysis will include several statistical measures which will be used to compare snippets of real and simulated targets as well as backgrounds of their immediate surroundings.To support automatic target recognition (ATR) algorithm development as well as predict their performance in various operational environments, there is a need for more realistic sonar data that captures environmental effects that are not only difficult to model using physical acoustical models but expensive to measure in the real world. Previous target insertion efforts have focused on high frequency imaging sonar. As such, these efforts effectively combine only the magnitudes of the real and simulated data. This effort will focus on low frequency sonar, and the goal is to retain the phase by combining the complex data where possible. Maintaining the phase allows us to take advantage of the resonant frequency information available in the lower frequency bands, which is lost when the magnitudes are summed. In this effort, several approaches to inserting simulated target data into real sonar data will be investigated. Typically, there are no shadows in the low frequency images; therefore, none of the approac...

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).

Robust Automatic Target Recognition via HRRP Sequence Based on Scatterer Matching.

High resolution range profile (HRRP) plays an important role in wideband radar automatic target recognition (ATR). In order to alleviate the sensitivity to clutter and target aspect, employing a sequence of HRRP is a promising approach to enhance the ATR performance. In this paper, a novel HRRP sequence-matching method based on singular value decomposition (SVD) is proposed. First, the HRRP sequence is decoupled into the angle space and the range space via SVD, which correspond to the span of the left and the right singular vectors, respectively. Second, atomic norm minimization (ANM) is utilized to estimate dominant scatterers in the range space and the Hausdorff distance is employed to measure the scatter similarity between the test and training data. Next, the angle space similarity between the test and training data is evaluated based on the left singular vector correlations. Finally, the range space matching result and the angle space correlation are fused with the singular values as weights. Simulation and outfield experimental results demonstrate that the proposed matching metric is a robust similarity measure for HRRP sequence recognition.

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.

Image Matting for Automatic Target Recognition

Features used in the classification of targets are generally based on the shape or gray-level information of the preprocessed target chip. Consequently, the performance of an automatic target recognition (ATR) system critically depends on the preprocessing result. In this paper, we propose to apply recent advances in image matting to address these challenges. First, a trimap is automatically generated in an adaptive manner to assign appropriate known foreground and background constraints. Then modified geometric clustering, which estimates the target center robustly, is performed on the estimated trimap. Then propagation-based matting is used to remove nontarget regions while retaining target information. The proposed framework is evaluated using visual examination, ATR performance comparison, and constraints dependency analysis. Our method has robust capabilities and outperforms conventional schemes.

Evaluating 3D local descriptors for future LIDAR missiles with automatic target recognition capabilities

ABSTRACTFuture light detection and ranging seeker missiles incorporating 3D automatic target recognition (ATR) capabilities can improve the missile’s effectiveness in complex battlefield environments. Considering the progress of local 3D descriptors in the computer vision domain, this paper evaluates a number of these on highly credible simulated air-to-ground missile engagement scenarios. The latter take into account numerous parameters that have not been investigated yet by the literature including variable missile – target range, 6-degrees-of-freedom missile motion and atmospheric disturbances. Additionally, the evaluation process utilizes our suggested 3D ATR architecture that compared to current pipelines involves more post-processing layers aiming at further enhancing 3D ATR performance. Our trials reveal that computer vision algorithms are appealing for missile-oriented 3D ATR.