Sparse aperture inverse synthetic aperture radar (SA-ISAR) aims to reconstruct target images by undersampled data. Traditional algorithms are limited in their application scope and exhibit weak capabilities in reconstructing target details. To address these issues, an adaptive threshold sensing (ATS) sparse reconstruction algorithm based on alternating direction method of multiplier (ADMM), named ATS-ADMM, is proposed. Within our framework, a detail-enhancing operator (DEO) is designed and combined with the$l_{1}$-norm to form a joint constrained optimization function to facilitate the recovery of weak scatterers. The matrix inversion operation within the ADMM framework is optimized to efficiently solve the multiconstrained problem. To enhance clutter suppression, an adaptive threshold network is designed based on deep convolutional networks. Inspired by deep learning, the DEO is set as a learnable operator, and the parameters are trained using an unsupervised network. Finally, the performance of ATS-ADMM is validated by comparing it with advanced algorithms using both simulated and real data. The results demonstrate that ATS-ADMM effectively focuses images, is suitable for diverse imaging scenarios, and is the fastest among ADMM-based algorithms.

Tomographic synthetic aperture radar (TomoSAR) shows great potential for high-quality 3-D mapping, especially in urban areas. As TomoSAR reconstruction methods advance into the deep learning (DL) era, current studies have demonstrated DL’s strengths in both precision and efficiency. However, for reconstructing urban areas with prominent spatial features from building structures, current studies focus on pixel-by-pixel reconstruction without leveraging the potential benefits of these features. In this context, an exploratory study to introduce spatial feature regularization in DL reconstruction is proposed for the first time, focusing on feature description, modeling, and regularization. Spatial features are analyzed and summarized by sharp edges and regular geometric shapes within the scene. To model these features, 2-D slices are used as the basic reconstruction units, and a general intraslice and interslice strategy is proposed to harness features within and between slices. Two-dimensional slices are fused into the entire 3-D scene. Two methods of fusion are designed: parallel and serial. To regularize these features, a new computational framework called light reconstruction and enhancement is designed, which includes two stages: light reconstruction with sparsity feature regularization and enhancement with spatial feature regularization. Finally, to evaluate performance, we design an extensive evaluation framework. A newly self-constructed compound urban building simulation dataset, combined with two public measured data, forms six different tests ranging from a classical close point resolution test to a diverse urban landscape challenge test. Evaluation results reveal the effectiveness of the designs and the boost provided by spatial feature regularization, resulting in higher reconstruction precision, more complete building spatial structure retrieval, and fewer outliers.

Tomographic synthetic aperture radar (tomoSAR) imaging is a powerful tool for urban 3D reconstruction. While recent deep learning methods have improved reconstruction quality, their reliance on simulated measurement-scene-image pairs for supervised training raises concerns over robustness in real-world scenarios due to the distribution shifts, such as varying observation geometry, observed scene distributions, and signal/noise levels. These concerns have received limited attention until now, motivating us to explore an alternative approach that leverages the strength of deep learning for tomoSAR reconstruction without requiring paired measurement and scene-image training data. Therefore, we propose the Unified Learning and Reconstruction (ULAR), a model-driven method for robust tomoSAR reconstruction, trained without such paired data. ULAR integrates physical-model consistency with scene feature regularization (capturing spatial structures) in a unified optimization process. Specifically, it jointly performs image reconstruction and spatial structure refinement by alternating between physics-guided updates and mainly self-supervised spatial-structure learning. The approach incorporates two complementary components for spatial-structure learning: a one-step self-supervised generative model for local spatial structures and a pretrained denoiser for nonlocal ones. And the denoiser is further enhanced with equivariance properties to improve its robustness. Experimental results on both simulated and real measured datasets demonstrate that ULAR achieves reconstruction accuracy comparable to supervised methods, and even surpasses them when distribution shifts exist, revealing strong robustness while not relying on simulated measurement-ground truth paired data. These results demonstrate the robustness of self-supervised learning for tomoSAR reconstruction, while highlighting its potential for better practicality and reliability in real-world applications.

Millimeter-wave (mmW) automotive radar imaging technology shows significant promise in advanced driver assistance systems (ADAS). Super-resolution imaging methods can be employed the limited aperture length of automotive radar to improve azimuth (angular) resolution. However, automotive radar images typically exhibit large dynamic range (LDR) and large scene (LS), leading to pay extensive computational complexity and storage demands when striving for higher image quality. To tackle this challenge, a fast$l_{q}$sparsity-driven imaging method with adaptive-focusing framework (FLSD-AF) for mmWave automotive radar super-resolution imaging in this article. First, in AF framework, a detect-before-imaging (DBI) is proposed to make echo data to adaptive focused on potential target area (PTR), thereby reducing the dimension of the effective data to reduce computational complexity and storage demands. Second, a subspace-phase-compensation (SPC) is proposed to reduces storage demands of the measurement matrix by addressing the imaging model mismatch in near-field under LS. Finally, a fast$l_{q}$sparsity-driven (FLSD) imaging method is proposed. It employs$l_{q}$-norm nonconvex penalty function to address the biased problem to improve imaging quality under LDR, meanwhile the computational complexity of the matrix operation is greatly reduced by utilizing joint Kailath-Variant (K-V) formula and Gohberg-Semencul (G-S) factorization. In summary, the proposed FLSD-AF not only substantially enhances the imaging performance, but also significantly diminishes the storage demands and computational complexity under LDR and LS. The results of simulations and experimental data all verify the proposed method.

The near-field array synthetic aperture radar (SAR) imaging method that’s based on deep neural networks has significantly advanced imaging accuracy and efficiency compared to traditional techniques like matched filtering and sparse reconstruction. However, it currently relies on supervised learning, which is affected by differences between simulated and real data. To address the issue, we introduces an unsupervised approach based on generative models of latent variables for near-field array SAR imaging. By focusing on generating target image distributions, this method bypasses the need for simulated training data. Instead, it leverages the concept of generative models with latent variables, using a prior auxiliary variable to construct a decoding neural network that transforms these latent variables into target images. In addition, a model-driven loss function is designed based on physical priors related to the linear correspondence between echoes and target images in the SAR measurement process.To enhance image quality further, sparse constraints (L1) loss function is integrated into the approach’s final loss function. Experimental validation using actual millimeter-wave near-field array SAR data demonstrates the effectiveness of this unsupervised imaging method. It offers advantages such as not relying on simulated data for training, suitability for diverse target types, superior imaging accuracy compared to traditional methods, and the ability to maintain high accuracy even at low sampling rates (10%).

Millimeter-wave (mmW) automotive radar is widely used in advanced driving assistance systems. Coprime array can improve the imaging resolution of the small size automotive radar with limited number antennas. However, the covariance matrix of coprime array exhibits data missing compared to uniform linear array (ULA), which leads to the serious high-sidelobes interference. To solve this problem, a covariance matrix completion imaging method is proposed. Firstly, a Toeplitz matrix is got by using the covariance matrix of missing data in the coprime array. Secondly, based on the Toeplitz matrix, a nuclear norm optimization problem is established to complete the data missing of the covariance matrix. Finally, by vectorizing the covariance matrix of data completion and directly using fast Fourier transform (FFT) to obtain low sidelobes image and the imaging resolution is improved. The simulation results show that the proposed method can effectively suppress high-sidelobes interference meanwhile improve imaging resolution.

Due to the reduction of imaging accuracy caused by the approximations of signal models, traditional synthetic aperture radar(SAR) moving target motion parameter estimation methods based on frequency domain imaging algorithms may suffer from the problem of accuracy reduction. To solve this problem, a novel moving target motion parameter estimation scheme is proposed for dual-channel SAR based on the time domain back projection(BP) algorithm. First, the BP imaging model of a moving target is constructed for the dual-channel SAR, and the focus position and the phase response of the moving target are analyzed. We show that the radial velocity of the moving target is proportional to the center frequency of the azimuth wavenumber spectrum, which can be used to estimate the radial velocity. Afterwards, the displaced phase center antenna based on BP is deduced for the clutter suppression, and the constant false alarm rate detector is used to detect moving targets. Then, the azimuth offset of the moving target between the two sub-aperture images is used to estimate the azimuth velocity, since it is proportional to the azimuth velocity. Meanwhile, a modified refocussing method is applied for a more accurate azimuth velocity estimation. Furthermore, the slant-range velocity is calculated by the geometric relationship among the radial velocity, azimuth velocity, and the slant-range velocity. The simulation and semi-physical simulation experiments verify that the proposed scheme can achieve higher accuracy in motion parameter estimation than the method based on the frequency domain imaging algorithm in both the side-looking and squint-looking dual-channel SAR.

Millimeter-wave (mmW) automotive synthetic aperture radar (Auto-SAR) technology holds significant promise for advanced driver assistance systems (ADASs). Sparse imaging methods can improve the quality of Auto-SAR images, such as suppressing sidelobes and noise. However, the$l_{1}$convex regularization-based sparse imaging methods suffer from the bias estimation, which reduces the target amplitude and ignores the association between scatterers, weakening the target structure. To address these issues, we proposed joint generalized$l_{q}$and convolutional (Glq-Con) regularization to enhance mmW Auto-SAR sparse imaging in this article. First, to improve the target amplitude, we propose utilizing the nonconvexity of Glq to reduce the bias effect; meanwhile, the global convergence of Glq ensures the imaging accuracy. Then, considering the continuity of the imaging target in driving scenes, we propose to utilize convolution regularization to modify the previously reconstructed amplitude of Glq to improve the target structure. Besides, to reduce computational complexity, we establish an efficient sparse imaging model. In this model, the fast Fourier transform (FFT) operator is employed to approximate complex matrix operation in the iterative process. We also use an efficient optimizer to solve the imaging model. Finally, both simulations and measured typical driving scenario experiments demonstrate that the proposed method significantly enhanced the Auto-SAR image, especially for the targets of weak scatterers.

In this study, we address the challenges associated with Video Synthetic Aperture Radar (Video SAR) shadow tracking, a technique used for continuous monitoring of ground moving targets. Due to challenges such as changes in shadow appearance, low contrast between shadow and background, and scene occlusion in Video SAR, existing methods often encounter extensive matching errors in the data association process, resulting in unsatisfactory tracking performance. To overcome these issues, we propose a novel method, GNN-JFL, which is based on joint motion-appearance feature extraction and graph neural data association. This method uses the detector as a flexible plugin and introduces two key improvements in the tracker section to enhance tracking accuracy. Firstly, we introduce joint feature learning to extract the complementary appearance and motion features from shadow shapes and positions, obtaining more robust feature representations to improve tracking performance under intricate challenges. Secondly, by organically integrating Multi-object Tracking (MOT) problems and Graph Neural Networks (GNN), we propose a novel GNN-based shadow tracking architecture, which utilizes graph relationships to learn the associations between shadows for more accurate tracking predictions. Our method is validated using two measured datasets and demonstrate superior performance in terms of multi-object tracking accuracy (MOTA). It outperforms the suboptimal method by 4.2% and 3.6% in the two datasets, respectively. This research contributes to the advancement of continuous monitoring techniques employing Video SAR shadow tracking.

regularization model is hindered by their hypothesis of inherent sparsity, causing unreal estimations of surface-like targets. Inspired by the edge-preserving property of total variation (TV), we propose a new complex-valued TV (CTV)-driven interpretable neural network with nested topology, i.e., CTV-Net, for 3-D SAR imaging. In our scheme, based on the 2-D holography imaging operator, the CTV-driven optimization model is constructed to pursue precise estimations in weakly sparse scenarios. Subsequently, a nested algorithmic framework, i.e., complex-valued TV-driven fast iterative shrinkage thresholding (CTV-FIST), is derived from the theory of proximal gradient descent (PGD) and FIST algorithm, theoretically supporting the design of CTV-Net. In CTV-Net, the trainable weights are layer-varied and functionally relevant to the hyperparameters of CTV-FIST, which aims to constrain the algorithmic parameters to update in a well-conditioned tendency. All weights are learned by end-to-end training based on a two-term cost function, which bounds the measurement fidelity and TV norm simultaneously. Under the guidance of the SAR signal model, a reasonably sized training set is generated, by randomly selecting reference images from the MNIST set and consequently synthesizing complex-valued label signals. Finally, the methodology is validated, numerically and visually, by extensive SAR simulations and real-measured experiments, and the results demonstrate the viability and efficiency of the proposed CTV-Net in the cases of recovering 3-D SAR images from incomplete echoes.

The detection of obscured vehicle targets and non-line-of-sight imaging by vehicle-mounted radar systems have broad application prospects in the field of urban traffic and autonomous driving. In this paper, a non-line-of-sight (NLOS) model and synthetic aperture radar (SAR) imaging method are proposed to perform millimeter wave imaging of obscured vehicle targets using electromagnetic wave reflection echoes from the road surface. Then, the NLOS echoes are imaged in two dimensions with high accuracy by compressed sensing algorithm (CSA). Finally, an experimental system for NLOS vehicle targets was developed using TI millimeter-wave radar. The feasibility of millimeter-wave NLOS radar imaging and the effectiveness of the proposed algorithm are experimentally verified, and high-precision 2D imaging results of obscured vehicle targets are obtained.

Point cloud upsampling and surface reconstruction work has important implications in model generation and target recognition, indoor navigation and autonomous driving. In this paper, an auto-encoder(AE) network based on octree convolution network are proposed for target surface reconstruction with millimeter-wave (MMW) radar and LIDAR. In the scheme, we learn to generate point cloud data by a two-stage method. The input point cloud data is constructed as an octree, and the structure of the octree is estimated by the network. Then we construct the surface of the object by using the signed distance method by implicit function and learn the fine position information of the point cloud in the octree by the network, which realizes the upsampling of point clouds as well. Finally, we use the generated point cloud to achieve surface reconstruction.

TomoSAR imaging is a classical inverse problem. Learning to optimize is a newly emerging technique for solving such problems in a deep-learning way. This technique may facilitate the efficiency and accuracy of the inverse process. In this research, we apply this framework to TomoSAR imaging and aim to enhance spatial structures within the framework. We establish a two-part imaging optimization model. One part is a regularization term for the forward observation process, and the other part is for constraining the sparsity of structures in the gradient domain. Using the methodology of learning to optimize, we design basic neural network modules and stack them in a cascaded manner to solve the model. We validate the proposed network using a public TomoSAR dataset. The results show that the proposed method obtains buildings with much more complete overall surfaces and more apparent edges.

The Synthetic Aperture Radar (SAR) system has undergone significant advancements, transitioning into a multi-functional platform with various modes. This study introduces a novel imaging mode that enables the simultaneous acquisition of height and intensity features, addressing the diverse requirements of different regions. Referred to as non-common band imaging, this mode optimizes bandwidth allocation within the limited illumination time, enhancing efficiency and flexibility. However, the interferometric phase retrieval problem arises in this mode. To address this challenge, we establish a forward model for the master-slave images and propose an optimization-solving model that incorporates wavelet sparsity regularization to mitigate noise interference. Furthermore, we introduce a physics-aware spectrum fusion network, combining proximal gradient descent methodology with the innovative deep unfolding technique, to restore the interferometric phase. Extensive experiments conducted on simulated and real measured data validate the effectiveness of the proposed network in terms of efficiency, accuracy, and noise reduction capabilities.

Spaceborne Synthetic Aperture Radar(SAR) can be mounted on space vehicles to collect information on the entire planet with all-day and all-weather imaging capacity. However, the spaceborne SAR sensor may suffer from severe interferences resulting in image degradation, which puts forward an urgent need for interference identification and mitigation. This paper proposes a high-precision interference identification method for spaceborne SAR images, named HPII-NET. The network is trained with simulation and real measurement data, and the effectiveness of the proposed method is verified by both simulation and the Setinel-1 satellite SAR images. Compared with the traditional identification networks, experimental results show that the HPII-NET can achieve more than 97% interference identification accuracy and thus improve the interference identification performance.

The tomographic Synthetic Aperture Radar (SAR) reconstruction based on deep learning (DL) can achieve high precision and efficiency, making it a promising method for various applications. However, current deep learning-based methods perform reconstruction by separately processing each range-azimuth resolution unit, which limits the utilization of features between resolution units and ignores the three-dimensional characteristics of the target. To address this limitation, we propose an iterative multidimensional feature reconstruction network that improves the accuracy of reconstruction by introducing correlation constraints between resolution units. Specifically, the proposed method slices the pulse-compressed data along the azimuth direction and treats each range-elevation slice as a calculation unit for reconstruction processing. And a multidimensional feature regularization module is designed to iteratively process two-dimensional features within the slice, taking into account the correlation between resolution units. Real-data experiments demonstrate that our proposed method outperforms existing network that utilize L1-norm sparse regularization in terms of achieving higher completeness.

Tomographic SAR (TomoSAR) can achieve 3-D imaging for observation targets through tomographic synthetic aperture, and shows good characteristics in urban building information extraction and scene 3-D inversion. Though the existing CS-based imaging algorithms can achieve high-resolution imaging results, requiring multiple iterations and manual adjustment of hyper-parameters. Currently, deep learning techniques in TomoSAR show great advantages in improving the imaging accuracy and efficiency. Inspired by deep unfolding, we unfolded the CS-based ADMM algorithm and mapped it into deep unfolded ADMM-net (DUADMM-net), so as to achieve high-resolution TomoSAR imaging. DUADMM-net consists of reconstructed signal estimation module, nonlinear fitting module and multiplier update module. The introduction of convolutional layers enhances the learning ability and nonlinear fitting ability. Compared to the conventional sparse imaging algorithms, the experimental imaging results and quantitative indicators demonstrate the effectiveness and efficiency of DUADMM-net.

The near-field array three-dimensional SAR can obtain the three-dimensional electromagnetic scattering characteristics of targets and present the imaging results in the form of point cloud. In recent years, it has been gradually used in the field of target RCS measurement. However, there are some problems in near-field array three-dimensional SAR images, such as interference, sidelobe and missing of target shape. Lidar has the characteristics of high positioning accuracy and strong target shape description. The fusion of Lidar with the near-field array three-dimensional SAR can effectively assist the scattering characteristic diagnosis of SAR images, in which the calibration plays an important role. This paper presents a calibration method for Lidar and near-field array three-dimensional SAR. The method is divided into three steps of calibration target design, extraction and alignment. By designing a special calibration target, correcting the imaging position deviation of Lidar, and converting the problem of calibration corresponding point selection into a problem of matching target set, the coordinate system of Lidar and SAR can be aligned. The effectiveness of the proposed method is verified by the experimental results of measured data.

Non-line-of-sight (NLOS) imaging of moving targets is of tremendous interest in the fields of urban sensing and autonomous driving. In this paper, a novel NLOS inverse synthetic aperture radar (ISAR) imaging method is proposed for moving targets by automotive millimeter-wave (MMW). In this scheme, an imaging model of the moving target in urban scenes is developed and analyzed. A low-frequency filtering method is employed to remove stationary interfering signals, a typical threshold method is applied to extract the triple-reflected echo of a hidden moving target, and the range migration algorithm (RMA) is utilized to achieve envelope alignment. Then, the well-focused image of the moving target is achieved by the polar format algorithm (PFA) with Prominent Point Processing (PPP) autofocus algorithm. Finally, an outfield experimental system for the obscured moving targets is built by TI MMW sensors. The results demonstrate our method can provide a high-resolution image of the moving target.

Inverse Synthetic Aperture Radar (ISAR) target recognition is an important branch of ISAR image research. The traditional ISAR recognition mission is done based on monostatic radar. However, the monostatic ISAR can only generate a single view image of the target. In this paper, to improve the recognition accuracy, a method of joint target recognition for Multi-station ISAR (MS-ISAR) via Multi-station ISAR Image Recognition (MIIR) network is proposed. In this scheme, the spatial matching algorithm and SURF algorithm are exploited to achieve multi-view fusion. The MIIR is present to achieve high accuracy recognition. To validate the proposed method, we use electromagnetic simulation software to obtain multi-view echo data of six types of aircraft targets. Then the proposed method and the traditional method are used for recognition respectively. Finally, we acquire the real experiment data of a model aircraft to validate the effectiveness of the proposed method. The results demonstrate our method provides a higher recognition accuracy rate.

Millimeter-wave (mmW) automotive radar imaging technology has great potential in advanced driver assistance systems (ADAS). Existing super-resolution imaging methods can improve angular (azimuth) resolution for automotive radar with limited aperture. However, these super-resolution methods have high computational complexity meanwhile have poor imaging performance in single-snapshot. In this paper, combined with CS based on ℓ1-norm regularization, we proposed a fast super-resolution imaging method via subspace detection and near-field phase compensation. Frist, the range-pulse-compression (RPC) data in the near and far field is formed by using range FFT. Then, the subspace detection is presented to reduce the size of the measurement matrix by using angle FFT to obtain the potential angle subspace of the target with all RPC data. After, the near-field phase compensation is utilized to make the measurement matrix applicable to all RPC data. Finally, the iterative shrinkage-thresholding algorithm (ISTA) algorithm is utilized to form the super-resolution images based on the measurement matrices and all RPC data. The simulation results show the proposed method can significantly improve imaging resolution with lower computational complexity than other imaging methods.

Near-field three-dimensional synthetic aperture radar (Near-field 3D-SAR) is a powerful imaging technique with diverse applications in scattering diagnosis, person/parcel imaging, building monitoring, forest monitoring, and more. This paper provides an overview of the imaging methods employed in Near-field 3D-SAR, focusing on the underlying methodologies, imaging models, and solving flowcharts. By analyzing and summa-rizing these methodologies and flowcharts, valuable insights are uncovered. Additionally, potential research directions are identified for further exploration.

The wide application of automotive radar greatly increases the risk of mutual interference between vehicles. To address this problem, this paper proposes an efficient interference suppression framework based on frequency domain sparsity. Firstly, The linear time-domain signal model is transformed into an optimal solution to the problem of extracting targets. Moreover, we utilize the orthogonal property of the Fourier matrix to avoid complex inverse matrix calculations and greatly reduce the computational memory while maintaining interference suppression performance. Both simulation and measured data validate the effectiveness of our approach, showing that our method not only suppresses mutual interference between automotive radars but also extracts range information from multiple targets.

This work focuses on 3D Radar imaging inverse problems. Current methods obtain undifferentiated results that suffer task-depended information retrieval loss and thus don’t meet the task’s specific demands well. For example, biased scattering energy may be acceptable for screen imaging but not for scattering diagnosis. To address this issue, we propose a new task-oriented imaging framework. The imaging principle is task-oriented through an analysis phase to obtain task's demands. The imaging model is multi-cognition regularized to embed and fulfill demands. The imaging method is designed to be generalized, where couplings between cognitions are decoupled and solved individually with approximation and variable-splitting techniques. Tasks include scattering diagnosis, person screen imaging, and parcel screening imaging are given as examples. Experiments on data from two systems indicate that the proposed framework outperforms the current ones in task-depended information retrieval.

The near-field SAR technology has shown great application value in many fields, such as security inspection, and radar cross section (RCS) measurement. However, due to side-lobe crosstalk and near-field spherical wave effect, the near-field SAR image has high clutter and side-lobe, which leads to serious image degradation. Complex image degradation results in the loss of target structure and contour, which limits the further application of near-field SAR technology. Due to the complex degradation, current restoration methods are not effective enough in terms of weak scattering center and target shape (geometry and structure) restoration. In this article, we first analyze near-field SAR image degradation. Then, utilizing the recent promising deep learning, we propose a novel near-field SAR image restoration framework. In this framework, we construct model-driven 2D CNN for 2D image restoration and 3D CNN for 3D image restoration, respectively. To validate the proposed framework, we construct experiments on simulated 2D and 3D test set, respectively. The experimental results prove the effectiveness of the proposed framework for both 2D and 3D situations.

Video synthetic aperture radar (Video SAR) has drawn much attention because it can continuously observe and track the moving target. Rather than tracking the target directly, it is better to track its shadow because the shadow has no location shift, and the back-scattering characteristic is stable. However, most current shadow tracking methods not only suffer from false alarms because their discrimination capacities are not good enough but also suffer from missed detection because the feature extraction capacities are limited under complicated environment. Therefore, we propose a shadow-enhanced self-attention and anchor-adaptive network (SE-SA-AAN) to achieve accurate moving target tracking for Video SAR. Firstly, the pre-processing technique sparse low-rank noise decomposition (SLRND) is proposed for enhancing shadows’ salience to facilitate subsequent feature extraction. Secondly, the transformer self-attention mechanism (TSAM) is embedded in the parameters-shared backbone in the feature extraction network to concentrate on regions of interests for suppressing clutter interference. Then, the representative features are input to the detector and tracker. The detector adds the semantic guided anchor-adaptive mechanism (SGAAM) to obtain optimized anchors that match the shadows’ location and shape in each frame. Meanwhile, the tracker applies a Siamese network to achieve trajectory tracking for each shadow. Based on the detection and tracking results, a data association is applied to achieve moving targets tracking. Finally, experiments on Sandia National Laboratories (SNL) data demonstrate that SE-SA-AAN outperforms the state-of-the-art methods FairMOT, TransTrack and Centertrack by 6.4%, 7.8% and 8.3% multiple object tracking accuracy (MOTA) separately.

Mathematically, 3-D synthetic aperture radar (SAR) imaging is a typical inverse problem, which, by nature, can be solved by applying the theory of sparse signal recovery. However, many reconstruction algorithms are constructed by exploring the inherent sparsity of imaging space, which may cause unsatisfactory estimations in weakly sparse cases. To address this issue, we propose a new perceptual learning framework, dubbed as PeFIST-Net, for 3-D SAR imaging, by unfolding the fast iterative shrinkage-thresholding algorithm (FISTA) and exploring the sparse prior offered by the convolutional neural network (CNN). We first introduce a pair of approximated sensing operators in lieu of the conventional sensing matrices, by which the computational efficiency is highly improved. Then, to improve the reconstruction accuracy in inherently nonsparse cases, a mirror-symmetric CNN structure is designed to explore an optimal sparse representation of roughly estimated SAR images. The network weights control the hyperparameters of FISTA by elaborated regularization functions, ensuring a well-behaved updating tendency. Unlike directly using pixelwise loss function in existing unfolded networks, we introduce the perceptual loss by defining loss term based on high-level features extracted from the pretrained VGG-16 model, which brings higher reconstruction quality in terms of visual perception. Finally, the methodology is validated on simulations and measured SAR experiments. The experimental results indicate that the proposed method can obtain well-focused SAR images from highly incomplete echoes while maintaining fast computational speed.

Millimeter-wave (mmW) automotive radar imaging technology has shown significant potential in autopilot assistance systems. The automotive radar with limited aperture can achieve high-resolution image by synthetic aperture technology. However, conventional imaging methods result in strong background clutter and high sidelobe interferences. To solve these problems, we propose a target-oriented Bayesian compressive sensing imaging method with region-adaptive extractor (TO-BCS-RAE) for mmW automotive radar imaging. (1) First, to extract the potential-target-regions (PTR) as well as subtracting the background clutters outside the PTR in a high-resolution initial image (by synthetic aperture), a region-adaptive extractor (RAE) is developed with utilizing 2D CFAR, isolated-point removing, and imaging clustering. Meanwhile, a more accurate prior distribution of target scattering points can be obtained in the PTR. (2) Then, to suppress the background clutters while enhancing the smooth structure of targets in the PTR, a target-oriented Bayesian compressive sensing (TO-BCS) imaging method is proposed by combining the prior probability distributions and inherent continuity of the target scattering points. It can also effectively reduce the high sidelobes. (3) Finally, to verify the effectiveness of TO-BCS-RAE, we conduct experiments on real data collected from an automotive radar with a vehicle platform in three typical driving scenarios. Both simulated and experimental results show the imaging quality of the proposed imaging method over conventional BP, OMP and ISTA methods.

Tomographic Synthetic aperture radar (TomoSAR) imaging algorithms for urban areas based on Compressed Sensing (CS) often have high time complexity due to many times iterations. Moreover, the phase error (PE) that exists will defocus TomoSAR imaging results. To reduce PE in the TomoSAR process, researchers use methods such as PS-InSAR, phase gradient autofocusing (PGA), etc. However, these methods are computationally expensive, which hinders the application of fast high-resolution TomoSAR imaging. In this paper, we merge the PE compensation into FISTA framework and proposed a novel deep learning approach for TomoSAR imaging. The network is based on Ada-LFISTA architecture, dubbed as AdaTomo-Net. Experiment results show that AdaTomo-Net has higher imaging accuracy and considerable computational efficiency compared with typical CS algorithms and learning-based algorithms such as LISTA in the presence of PE.

With the booming of Convolutional Neural Networks (CNNs), CNNs such as VGG-16 and ResNet-50 widely serve as backbone in SAR ship detection. However, CNN based backbone is hard to model long-range dependencies, and causes the lack of enough high-quality semantic infor-mation in feature maps of shallow layers, which leads to poor detection performance in complicated background and small-sized ships cases. To address these problems, we pro-pose a SAR ship detection method based on Swin Trans-former and Feature Enhancement Feature Pyramid Network (FEFPN). Swin Transformer serves as backbone to model long-range dependencies and generates hierarchical features maps. FEFPN is proposed to further improve the quality of feature maps by gradually enhencing the semantic infor-mation of feature maps at all levels, especially feature maps in shallow layers. Experiments conducted on SAR ship de-tection dataset (SSDD) reveal the advantage of our pro-posed methods.

Image resolution is the key point for the 3-D synthetic aperture radar (SAR) application, especially in small-scale scene observation. The traditional filter-based image enhancement algorithms used for 3-D SAR may suffer from quality degeneration in case of parameter mismatch. This paper proposes a robust and efficient convolutional neural network (CNN) based U-net framework for 3-D SAR image enhancement. The U-net extracts image features in down sampling and up sampling, which is realized by max pooling and deconvolution layers. We use the mean square error(MSE) as the loss function to estimate the difference between the predicted images and the label, while Adam optimizer updates parameters to achieve the global minimum MSE. Both simulation and measured data verify the effectiveness of the network. The results demonstrate that the U-net outperform some traditional filter-based algorithms.

Phase filtering is a key step in the interferometric synthetic aperture radar (InSAR). Compared with the traditional method, the deep learning-based phase filtering method is superior in both accuracy and speed. However, traditional deep learning overly relies on huge data volume and is not interpretable and unstable for the purely data-driven and black-box properties. Therefore, a sparse model-based network for interferometric phase denoising (PD-SMNet) is proposed in this paper which joins conventional ISTA algorithm with the theory basis into a network structure. In contrast with the conventional network, the PD-SMNet is interpretable and more stable, and has good performance on small training samples. The experimental results on simulated and measured data show the proposed method significantly outperforms the previous three widely-used methods in both precision and speed. In addition, the proposed method has higher accuracy on small training sets than conventional deep learning.

Compressed sensing (CS) is a promising method for high-resolution InSAR imaging if the underlying scene is sparsity. However, the conventional CS-based direct reconstruction will lead to interferometric phase loss due to the non-sparsity of most InSAR complex-valued image. In this paper, a high-resolution InSAR imaging algorithm via CS-based amplitude-phase separation (CS-APS) is proposed. In this scheme, we firstly recover the amplitude of SAR images by a CS-based iterative weighted regularization method. Then we estimate the phase of InSAR images by the least square algorithm. Finally, the high-resolution imaging results of InSAR are obtained with stepwise amplitude-phase iterative estimation. Compared with the conventional direct sparse reconstruction (DSR) algorithm, the proposed method not only enhances the accuracy of the interferogram but also reduces the computational burden for the imaging orocess.

Video synthetic aperture radar (SAR) has been found to be very valuable for detecting and tracking moving targets and observing areas of interest. Shadows produced by target motion in sequential radar images can be used to detect targets themselves. Since existing deep learning shadow detection methods often require many hand-designed components, in this paper, we propose a shadow detection method for video SAR moving target based on transformer, which is named Deformable Shadow-DETR. Deformable Shadow-DETR can better extract shadow features, and use the transformer encoder-decoder network to treat shadow detection as a direct set prediction problem, eliminating the need for cumbersome hand-designed components. Experiments on the real video SAR data published by the Sandia National Laboratories show that our proposed moving target shadow detection method can achieve excellent performance.

High-resolution imaging of the corner-hidden moving target makes tremendous sense in the fields of urban sensing and autonomous driving. In this paper, a joint No-line-of-sight (NLOS) model and inverse synthetic aperture radar (ISAR) imaging method are proposed for millimeter-wave (MMW) imaging of the hidden moving target. In the scheme, a classical threshold method is used to remove the interference signals of the stationary background and extract the triple-reflected echo of the hidden moving target. Then, the image focusing on the moving target is achieved by the range migration algorithm (RMA) with the mirror projection of the wall. Finally, a near-field NLOS experiment system for the hidden rotating target was constructed by TI MMW sensors. The effectiveness of the method is verified by these experiments.

Due to the existence of system error or the difference in reference coordinates for imaging, there is a significantly spatial mismatch among video SAR frames, which will affect the performance of target localization and tracking greatly. To solve this problem, a PCE-RPM-Net that can achieve video SAR inter-frame images registration is proposed in this paper. PCE-RPM-Net is mainly composed of U-Net and RPM-Net, in which U-Net is adopted to extract features of SAR images to generate point clouds and RPM-Net is used to align the point clouds. Experimental results show that the PCE-RPM-Net has higher registration accuracy and faster speed compared with the classical traditional algorithm.

Interferometric Synthetic Aperture Radar (InSAR) Imaging methods are usually based on algorithms of match-filtering type, without considering the scene's characteristic, which causes limited imaging quality. Besides, post-processing steps are inevitable, like image registration, flat-earth phase removing and phase noise filtering. To solve these problems, we propose a new InSAR imaging method. First, to enhance the imaging quality, we propose a new imaging framework base on 2D sparse regularization, where the characteristic of scene is embedded. Second, to avoid the post processing steps, we establish a new forward observation process, where the back-projection imaging method is embedded. Third, a forward and backward iterative solution method is proposed based on proximal gradient descent algorithm. Experiments on simulated and measured data reveal the effectiveness of the proposed method. Compared with the conventional method, higher quality interferogram can be obtained directly from raw echoes without post-processing. Besides, in the under-sampling situation, it's also applicable.

Inevitable interferences exist for the SAR system, adversely affecting the imaging quality. However, current analysis and suppression methods mainly focus on the far-field situation. Due to different sources and characteristics of interferences, they are not applicable in the near field. To bridge this gap, in the first time, analysis and the suppression method of interferences in near-field SAR are presented in this work. We find that echoes from both the nadir points and the antenna coupling are the main causes, which have the constant-time-delay feature. To characterize this, we further establish an analytical model. It reveals that their patterns in 1D, 2D and 3D imaging results are all comb-like, while those of targets are point-like. Utilizing these features, a suppression method in image domain is proposed based on low-rank reconstruction. Measured data are used to validate the correctness of our analysis and the effectiveness of the suppression method.

Images of near-field SAR contains spatial-variant sidelobes and clutter, subduing the image quality. Current image restoration methods are only suitable for small observation angle, due to their assumption of 2D spatial-invariant degradation operation. This limits its potential for large-scale objects imaging, like the aircraft. To ease this restriction, in this work an image restoration method based on the 2D spatial-variant deconvolution is proposed. First, the image degradation is seen as a complex convolution process with 2D spatial-variant operations. Then, to restore the image, the process of deconvolution is performed by cyclic coordinate descent algorithm. Experiments on simulation and measured data validate the effectiveness and superiority of the proposed method. Compared with current methods, higher precision estimation of the targets' amplitude and position is obtained.

SAR is usually subject to strong electromagnetic interference (EMI) during electronic reconnaissance missions, which will seriously weaken its ability of surveying and mapping. This paper presents a novel method for SAR image interference suppression based on the encoder-decoder network (named as ISEDnet). ISEDnet mainly consists of consecutive feature extraction net (FEN), the additional encoder-decoder network, and the image supervision mechanism. FEN is used to extract the features of interfered SAR images, and the Encoder-Decoder network (EDN) is used to suppress interference of SAR images. The image supervision mechanism is proposed to recover the target features. The network trained with simulation and real measurement data, the effectiveness of ISED-net are verified by both simulation and the Sentinel-1 satellite SAR images. Compared to the traditional notch filtering method, ISEDnet can successfully suppress different types of SAR interference and improve interference suppression performance.

In Interferometric Synthetic Aperture Radar (InSAR) data processing, phase filtering has a great impact on the accuracy of the resulting DEM and is therefore an inevitable step. Recently, convolutional neural networks are applied to InSAR phase filtering and show excellent performance, however, most of these deep learning-based methods do not make full use of the self-similarity of phase map, that is, pixels in different or far regions have a close relationship in values or distribution. In this paper, we propose a phase filtering method based on transformer network, which has the advantage of capturing the long-range dependency or exploiting the global features of the phase map, moreover, the deformable convolution is introduced to our method to further extract the local phase features. Experiments validate the efficiency and effectiveness of the proposed method to InSAR phase filtering.

The compressed sensing (CS) method is widely utilized in the field of radar sparse imaging. However, it always encounters enormous iterations and low generalizability. To solve these problems, in this paper, we propose a novel learning-based sparse imaging network architecture, i.e., Split Unfolding Sparsity-Driven Network (SSD-Net), for 3D synthetic aperture radar (SAR) imaging. By combining the model-based SAR imaging method and data-driven deep learning method, SSD-Net has favorable explainability and generalization abil-ity to produce 3D SAR images. The deep hierarchical ar-chitecture of SSD-Net is obtained by combiningthe radar nonlinear operator and the split Bregman method. The exper-iments demonstrate that the proposed SSD-Net outperforms other state-of-the-art methods in the field of SAR imaging.

Moving target shadows among video synthetic aperture radar (Video-SAR) images are always interfered by low scattering backgrounds and cluttered noises, causing poor detection-tracking accuracy. Thus, a shadow-background-noise 3D spatial decomposition (SBN-3D-SD) model is proposed to enhance shadows for higher detection-tracking accuracy. It leverages the sparse property of shadows, the low-rank property of backgrounds, and the Gaussian property of noises to perform 3D spatial three-decomposition. It separates shadows from backgrounds and noises by the alternating direction method of multipliers (ADMM). Results on the Sandia National Laboratories (SNL) data verify its effectiveness. It boosts the shadow saliency from the qualitative and quantitative evaluation. It boosts the shadow detection accuracy of Faster R-CNN, RetinaNet and YOLOv3. It also boosts the shadow tracking accuracy of TransTrack, FairMOT and ByteTrack.

Huge imbalance of different scenes’ sample numbers seriously reduces synthetic aperture radar (SAR) ship detection accuracy. Thus, to solve this problem, this letter proposes a balance scene learning mechanism (BSLM) for offshore and inshore ship detection in SAR images. BSLM involves three steps: 1) based on unsupervised representation learning, a generative adversarial network (GAN) is used to extract the scene features of SAR images; 2) using these features, a scene binary cluster (offshore/inshore) is conducted by${K}$-means; and 3) finally, the small cluster’s samples (inshore) are augmented via replication, rotation transformation or noise addition to balance another big cluster (offshore), so as to eliminate scene learning bias and obtain balanced learning representation ability that can enhance learning benefits and improve detection accuracy. This letter applies BSLM to four widely used and open-sourced deep learning detectors, i.e., faster regions-convolutional neural network (Faster R-CNN), Cascade R-CNN, single shot multibox detector (SSD), and RetinaNet, to verify its effectiveness. Experimental results on the open SAR ship detection data set (SSDD) reveal that BSLM can greatly improve detection accuracy, especially for more complex inshore scenes.

The wide applications of 3-D synthetic aperture radar (SAR) imaging bring higher requirements for resolution and computational efficiency. The stepped frequency linear frequency modulated signal achieves high range resolution imaging by fusing multiple sub-pulses. However, its wide sub-pulse bandwidth results in a large amount of echo data to be processed, which results in a significant increase in the time consumption of the bandwidth synthesis algorithm. To achieve fast high range resolution 3-D SAR imaging, we propose an inter-array frequency-hopping linear frequency modulated signal model and a 3-D variable carrier frequency back projection algorithm. The proposed signal model transmits only one narrow bandwidth sub-pulse with hopping carrier frequency in each array element, which allows the receiver to sample the echo at a lower frequency. The lower sampling frequency and number of sub-pulse significantly reduce the amount of echo data. The proposed algorithm not only focuses the along-track direction and the cross-track direction of SAR image, but also fuses the low range resolution imaging results obtained by each sub-pulse into a high range resolution imaging result. Benefiting from the fusion of bandwidth synthesis algorithm and imaging algorithm, the computational efficiency is greatly improved. The experimental results demonstrate that the proposed algorithm achieves the comparable resolution and imaging quality as the ideal 3-D back projection (BP) algorithm with a large bandwidth chirp signal. Moreover, the time consumption of the proposed algorithm has been reduced to only 2.25% to 3.02% of that of the advanced high range resolution 3-D BP algorithm.

The success of deep learning in synthetic aperture radar (SAR) automatic target recognition (ATR) relies on a large number of labeled samples; however, there are often wrong (noisy) labels in a large-scale dataset. In this article, we propose a loss curve-fitting-based method, which can identify the noisy labels and train the classification network effectively. We propose to model label noise by unsupervised clustering via fitting loss curve to identify whether the sample’s label is clean or noisy. Then, we train the network using augmented samples with clean labels to correct noisy labels further. The experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset prove that our proposed method can deal with the situation when training a network with different ratios of noisy labels and correct noisy labels effectively. When the noise ratio is small (40%) in the training dataset, our method can correct 97.9% of noisy labels and train the classification network with 98.8% classification accuracy. While the noise ratio is large (80%), our method can correct 78.1% of noisy labels and train the classification network with 79.6% classification accuracy.

Integrating compressed sensing (CS) with millimeter-wave (mmW) holography has shown great potential to achieve lightweight onboard hardware, low sampling ratio, and high-speed sensing. However, conventional CS-driven algorithms are always limited by nontrivial adjusting of parameters and excessive computational cost caused by plenty of iterations. To address this problem, we propose a lightweight model-based deep learning framework (LFIST-Net) for mmW 3-D holography, by combining the interpretability of fast iterative shrinkage-thresholding algorithm (FISTA) and tuning-free merit of data-driven deep neural network. First, the single-frequency (SF) holographic imaging technique is integrated into FISTA, which serves as the sensing kernels, to avoid large-scale matrix multiplications. Subsequently, the kernel-based FISTA (KFISTA) is mapped into layer-fixed and parameter-learnable LFIST-Net, whose weights are relaxed to be layer-varied. The updating of key parameters in LFIST-Net, including step sizes, thresholds, and momentum coefficients, are regularized by soft-plus function to ensure the non-negativity and monotonicity. As for 3-D holography implementation, the “1-D + 2-D” scheme is adopted, where the matched filtering (MF) and well-trained LFIST-Net are used for range focusing and reconstructions of azimuth slices. Without losing efficiency, the range-focused subechoes are processed parallelly in 3-D cube form. Experiments, including both simulated and measured tests based on a commercial mmW radar, prove that LFIST-Net is capable of reconstructing the imaging scene precisely. In particular, in near-field mmW 3-D holography tests, both numerical and visual results demonstrate LFIST-Net yields compelling reconstruction performance while maintaining high computational speed compared with MF-based, conventional CS-driven, and network-based methods.

Compressed sensing (CS) demonstrates significant potential to improve image quality in 3-D millimeter-wave imaging compared with conventional matched filtering (MF). However, existing sparsity-driven 3-D imaging algorithms always suffer from large-scale storage, excessive computational cost, and nontrivial tuning of parameters due to the huge-dimensional matrix–vector multiplication in complicated iterative optimization steps. In this article, we present a novel range migration (RM) kernel-based iterative-shrinkage thresholding network, dubbed as RMIST-Net, by combining the traditional model-based CS method and data-driven deep learning method for near-field 3-D millimeter-wave (mmW) sparse imaging. First, the measurement matrices in ISTA optimization steps are replaced by RM kernels, by which matrix–vector multiplication is converted to the Hadamard product. Then, the modified ISTA optimization is unrolled into a deep hierarchical architecture, in which all parameters are learned automatically instead of manually tuned. Subsequently, 1000 pairs of oracle images with randomly distributed targets and their corresponding echoes are simulated to train the network. A well-trained RMIST-Net produces high-quality 3-D images from range-focused echoes. Finally, we experimentally prove that RMIST-Net is capable process$512 \times 512$large-scale imaging tasks within 1 s. Besides, we compare RMIST-Net with other state-of-the-art methods in near-field 3-D imaging applications. Both simulations and real-measured experiments demonstrate that RMIST-Net produces impressive reconstruction performance while maintaining high computational speed compared with conventional and sparse imaging algorithms.

Compressed sensing (CS) shows significant potential in the field of active millimeter-wave (mmW) synthetic aperture radar (SAR) imaging due to the merits of reducing system complexity and achieving high-speed sensing. However, most CS-driven imaging methods suffer from the excessive computational burden, since the calculative steps always rely on vectorization and consequently lead to extremely large-scale matrix operations. To address this issue, we propose an efficient alternating direction method of multipliers (ADMMs) framework for mmW 3-D SAR imaging. In our scheme, we utilize the single-frequency holographic (SFH) technique and construct SFH-based forward/inverse sensing operators rather than converting the imaging process into a special case of “linear inverse problems,” by which the large-scale matrix inversions are avoided and consequently the computational complexity is reduced. Based on the SFH functional measurement model, the SFH-ADMM is derived to reconstruct the 3-D image from sparsely sampled measurement echo while suppressing noisy clutters and ambiguities. Besides, the SFH-ADMM iteration steps undergird a neural network design, yielding a tailored SFH-ADMM-Net with trainable parameters and layer-fixed structures, which further shorten the execution time and improve reconstruction performance. The network is trained by simulated data, which are generated according to the radar signal model. Extensive experiments, including simulations and laboratory tests, demonstrate the superiority of the proposed algorithms in terms of both reconstruction accuracy and computational speed.

In the research topic of three-dimensional (3D) SAR imaging, the sparsity-enforcing techniques offer promise in shortening sensing time and improving reconstruction accuracy. However, many of them only explore the sparse prior of 3D SAR images, which leads to biased estimations in cases of non-sparse scenarios. To remedy this problem, we propose a new network with learned low-rank and sparse priors, i.e., LLRS-Net, to obtain improved reconstructions from sparsely sampled 3D SAR echoes. In our scheme, a two-stage reconstruction algorithmic framework (LSRA) is derived based on sparse and low-rank priors. Wherein, the first stage recovers the measurements from their limited observations by exploring the low-rank prior, while the second estimates the final 3D SAR images with a fast-iterative optimization. Theoretically inspired by LRSA, the LLRS-Net is designed into a cascaded network structure. In LLRS-Net, the trainable weights serve as independent variables and control the algorithmic hyper-parameters via regularizing functions, ensuring a well-conditioned updating tendency. By end-to-end training, the network weights are updated automatically under the guidance of a compound loss function constraining both the outputs of two stages. Finally, the methodology is validated on simulations and measured experiments. These results show that the proposed framework outperforms many state-of-the-art imaging algorithms in recovering 3D SAR images from incomplete echo data.

Inevitable inaccuracies of 3-D synthetic aperture radar (3-D SAR) imaging geometry may cause undesired blurs in reconstructed images. Recent advances show impressive results in integrating error estimation into sparse imaging. However, the concept is still challenging in 3-D SAR due to the cumbersome high-dimensional processing. To address this problem, we propose a model-driven 3-D SAR autofocusing network with learned sparsity (AFLS-Net) by applying the recent emerging deep unfolding technique. In our scheme, we first construct a kernel-based observation model with consideration of motion-induced phase errors, which avoids the memory-consuming matrix calculations in the conventional matrix–vector form. Then, a joint sparse imaging and autofocusing algorithm is derived based on the framework of block coordinate descent. In addition, by mapping the computational steps, the AFLS-Net is designed to further improve the autofocusing accuracy and efficiency in which a shallow two-path convolutional neural network (CNN) is embedded to explore the implicit sparse prior, by which the reconstruction accuracy can be improved. Meanwhile, the batchwise autofocusing module is designed to obtain a robust estimation by jointly optimizing subcost functions associated with a batch of independent measurements. Finally, the methodology is validated in both simulations and laboratory 3-D SAR experiments. The experimental results suggest that the proposed method obtains better autofocusing quality compared to other comparison baselines in reconstructing 3-D SAR images from incomplete and error-polluted echoes.

Inverse synthetic aperture radar (ISAR) imaging and autofocusing are challenging under sparse aperture (SA) conditions. Traditional imaging or autofocusing methods fail to obtain satisfying results due to the nonuniform and incomplete data caused by SA. To address this problem, a novel compressive sensing (CS)-based imaging and autofocusing framework is proposed to obtain high cross-range resolution for SA ISAR. To achieve well-focused imaging results of better performance and higher efficiency simultaneously, we merge the phase error estimation into the CS framework, then iteratively solve the compound CS problem in matrix form with approximate message-passing (AMP), dubbed as AF-AMP. Moreover, a deep learning approach is also proposed by mapping AF-AMP into a deep network, dubbed as AF-AMPNet, with extensive modifications to further improve the efficiency. The adaptively and layer-wisely optimal parameters learned by the training process are also promising to enhance the performance and robustness against noise. Besides, the loss function for training is subjoined with regularized$\ell _{1} $and$\ell _{2} $constraints to ensure the sparsity and quality of imaging results. Furthermore, the proposed AF-AMP and corresponding network-based AF-AMPNet are verified by simulated and measured experiments, both of which show superior performance, robustness, and higher efficiency than other state-of-the-art methods. AF-AMPNet can achieve the best performance in much less computational time.

Nonline-of-sight (NLOS) radar imaging is a novel technique that can inverse the scattering characteristics of targets in the NLOS area, which has been one of the hot pots of radar imaging field. However, the existing NLOS radar mainly focuses on 1-D or 2-D imaging, which inevitably suffers from the geometric loss of real 3-D scenes, and its applications are restricted in the urban environment. In this article, we propose an NLOS radar 3-D imaging model and method for looking around corner (LAC) situation by multi-input–multioutput (MIMO) millimeter-wave (mmW) array antennas. In this scheme, first, the model of NLOS radar 3-D imaging with mmW MIMO antennas is established and the multipath scattering of targets with this model is analyzed. Then, the theoretical resolution of LAC 3-D imaging is derived and discussed. Second, exploiting the three bounces of LAC and extraction of linear structure, an effective imaging algorithm with mirror projection theory and Radon transform, dubbed as mirror symmetry backprojection (MSBP), is proposed for 3-D image focusing. Moreover, to suppress the uncertainties of phase caused by both LAC and system error, the minimum entropy principle is introduced to MSBP. Finally, an NLOS 3-D imaging system with 77-GHz mmW MIMO radio frequency module and 2-D rails is developed. Different types of targets, such as metal balls and ornaments, are tested in LAC. The results demonstrate that our NLOS technique can not only provide a high-quality 3-D focusing of the hidden targets but also extract positions of targets without prior knowledge of the NLOS area.

The application of the compressed sensing (CS) method in the radar field enables the radar imaging system to satisfy both low data cost and high reconstruction quality, however, it is accompanied by enormous iterative operations and difficult adjustments of parameters. In this paper, we propose a learning-based split unfolding framework, dubbed as split iterative sparse reconstruction network (SISR-Net), for near-field 3-D millimeter-wave (mmW) radar sparse imaging. Firstly, a sparse reconstruction algorithm, i.e., SISRA, is proposed to theoretically guide the structure of the imaging framework. Subsequently, by combining the model-based CS method and data-driven deep learning method, SISR-Net is constructed by SISRA to produce 3-D mmW radar images efficiently with excellent explainability and generalization ability. Joint the radar-imaging kernel, echo-generation kernel, and the split Bregman method, the efficiency and stability of SISR-Net are guaranteed, all parameters are layer-varied and learned steadily by end-to-end training to improve the convergence and robustness of the imaging network. Simulated data and the echo from a high-resolution mmW radar dataset 3DRIED, are used to train and test the SISR-Net based on the Adam optimizer. For both simulation and extensive 3-D mmW radar measured experiments, the proposed SISR-Net outperforms other state-of-the-art imaging methods in terms of imaging accuracy and generalization ability.

Ship instance segmentation of high-resolution SAR images is a valuable and challenging task due to the complex scattering and noise properties. In this article, we pioneered the construction of the low-level feature to discriminate the ships and complemented the super-resolution denoising techniques in the network modules, termed low-level feature guided network (LFG-Net), for precise ship instance segmentation in SAR images. LFG-Net consists of the low-level feature concerned pyramid (LFCP), the high-resolution interaction module (HR-FIM), and the compression recovery segmentation branch (CRSB). LFCP extends vanilla FPN with the P1layer and complements super-resolution techniques to capture the regional and texture information at the image level for small object segmentation. HR-FIM interacts the bounding box region of interest (RoI) feature and mask RoI feature at the instance level with high-resolution techniques to enhance the mask RoI feature. CRSB aims at recovering the high-resolution mask predictions to improve the ship segmentation performance. Comprehensive experiments on HRSID, PSeg-SSDD, and AirSARShip indicate that LFG-Net* achieves 11.7%, 6.3%, and 12.7% AP increments compared with the Mask R-CNN baseline, respectively. Besides, it receives 9.5%, 4.9%, and 7.3% AP increments compared with state-of-the-art method, respectively, which bridges the gap of instance segmentation precision in SAR images. In terms of the visualized instance segmentation results, LFG-Net* is capable of segmenting the complex scenes, e.g, the adjacent distributed ships and ships with strong reflection noise interference, in SAR images. Code is available at: https://github.com/Evarray/LFG-Net.

This article extends the shadow tracking for video-synthetic aperture radar (SAR) from a single-target framework to a multitarget framework, which is crucial for SAR ground moving targets’ identification. Inspired by FairMOT, the multitarget tracking framework for SAR shadow tracking is improved by using the triplet attention (TriAtt) mechanism and the lightweight multiscale network. By employing the ability to fuse spatial and feature dimensions of TriAtt and combining the lightweight network optimized by multiscale encoder–decoder and dilated convolution, a fast multiscale feature extraction module (FMsFEM) embedded with TriAtt is proposed for better tracking efficiency and performance. Experiments on the Sandiego video-SAR dataset validate that the TriAtt mechanism can improve the tracking performance of deep layer aggregation (DLA)-34, DLA-18, and FMsFEM significantly. FMsFEM with embedded TriAtt outperforms the state-of-the-art network (FairMOT with backbones of DLA-34 and DLA-18) with much faster frame rates. The average frame rates of FMsFEM and FMsFEM-TriAtt reach 60.32 and 56.13 fps for datasets with an image size of$1088\times 608$, which are about three times higher than the frame rates of others.

Ship classification in synthetic aperture radar (SAR) images is a fundamental and significant step in ocean surveillance. Recently, with the rise of deep learning (DL), modern abstract features from convolutional neural networks (CNNs) have hugely improved SAR ship classification accuracy. However, most existing CNN-based SAR ship classifiers overly rely on abstract features, but uncritically abandon traditional mature hand-crafted features, which may incur some challenges for further improving accuracy. Hence, this article proposes a novel DL network with histogram of oriented gradient (HOG) feature fusion (HOG-ShipCLSNet) for preferable SAR ship classification. In HOG-ShipCLSNet, four mechanisms are proposed to ensure superior classification accuracy, that is, 1) a multiscale classification mechanism (MS-CLS-Mechanism); 2) a global self-attention mechanism (GS-ATT-Mechanism); 3) a fully connected balance mechanism (FC-BAL-Mechanism); and 4) an HOG feature fusion mechanism (HOG-FF-Mechanism). We perform sufficient ablation studies to confirm the effectiveness of these four mechanisms. Finally, our experimental results on two open SAR ship datasets (OpenSARShip and FUSAR-Ship) jointly reveal that HOG-ShipCLSNet dramatically outperforms both modern CNN-based methods and traditional hand-crafted feature methods.

This article proposes a novel framework by combining a modified real-time recurrent regression (mRe³) network and a newly designed trajectory smoothing long short-term memory (LSTM) network for refocusing the ground moving target (GMT) in the synthetic aperture radar (SAR) image. The mRe^3 network that consists of a convolutional neural network (CNN) backbone and two LSTM modules is designed to track the GMT's shadow in an SAR video. Furthermore, we find that the complex trajectory obtained by the tracking network cannot directly be used for refocusing the GMT because of the estimation error. To address the abovementioned problem, a β-order total variation loss-based smoothing LSTM (TVβ-LSTM) is proposed to recover the GMT's trajectory to meet the requirement of refocusing. Besides, the effect of TVβ on the performance of smoothing LSTM is analyzed. By the experiments on simulated and real SAR videos, we find that the mRe^3 has stronger robustness and a better trajectory reconstruction precision compared with the existing tracking methods, especially for the strong interference cases. In addition, the smoothing LSTM can recover the trajectory of the GMT with higher precision and better smoothness. When β is set to 3, with the TVβ-LSTM, the center distance error of a recovered complex trajectory can be reduced from 0.82 to 0.782, while its fluctuation can be suppressed from 6 to 1 mm. By using our framework, the focused GMT with bountiful geometrical features can be obtained even for the K_a-band SAR.

The sparse imaging method based on compressed sensing (CS) is widely used in the field of millimeter-wave (MMW) synthetic aperture radar (SAR) imaging. However, 3D sparse imaging is limited by the difficult parameter tuning, the huge computational load, and the low processing efficiency. In addition, due to the motion errors and model mismatch, it is difficult to obtain well-focused results without error correction techniques. To address these issues, we propose a deep learning framework that integrates 3D sparse imaging and autofocusing, named 3D Sparse Autofocusing Network (SAF-3DNet) for MMW SAR data processing. The network is constructed based on an auto-encoder, which can optimize parameters without effective ground truth. The backbone structure of the encoder is expanded by approximate message-passing (AMP), and the operators in the frequency domain are used to replace the traditional matrix-vector CS model, which avoids large-scale matrix multiplication and other operations, and greatly improves the operation efficiency. In addition, the 2D phase error estimation in the cross-range plane is embedded into the sparse imaging models, enabling simultaneous 3D imaging and autofocusing. The decoder is designed as a mapping from the autofocusing results to the echo data. Experimental results based on both simulated and measured data demonstrate the proposed SAF-3DNet can achieve well-focused 3D reconstruction within an ephemeral time, which expresses the potential of 3D MMW SAR real-time and high-quality imaging.

Convolutional neural network (CNN) has become the mainstream method in the field of image recognition for its excellent ability to feature extraction. Most of the CNNs increase the classification accuracy for the rotational objects by imposing the network with rotation invariance or equivariance property, which causes the loss of the target's orientation information. In this work, a rotation-mapping network (RM-Net) that can achieve objects recognition and angle or orientation estimation simultaneously without additional network training is constructed. Besides, an octagona convolutional kernel is introduced to improve the network's performance. The experiments on the simulation SAR datasets show that the proposed RM-CNN can achieve state-of-the-art results in target recognition and angle estimation.

With the rise of Deep Learning (DL), numerous DL-based SAR ship detectors, represented by Faster R-CNN, is constantly breaking the record of detection accuracy. However, these detectors still face huge challenges in modeling the geometric transformation of shape-changeable ships, due to their used conventional convolution kernels whose structure is fixed. Therefore, to address this problem, we propose an improved Faster R-CNN by using deformable convolution kernels for SAR ship detection. We substitute some conventional shape-changeless convolution kernels in Faster R-CNN with deformable convolution ones that can adaptively learn additional 2-D offsets of the raw convolution kernels, to better model the geometric transformation of shape-changeable ships. Finally, the experimental results on the open SAR Ship Detection Dataset (SSDD) reveal that our improved Faster R-CNN achieves a 2.02% mean Average Precision (mAP) improvement than the raw Faster R-CNN.

In this paper, a novel slow moving target detection method based on YOLO is proposed for the dual-beam SAR. Firstly, YOLO network is used to detect targets under strong clutter. That is, the trained YOLO network is used to detect and classify targets in the fore- and aft-beam SAR images, so as to effectively distinguish background clutter from targets. At the same time, the YOLO network is used to carry out the bounding box regression of the target in the fore- and aft-beam SAR image to realize the extraction of the target position in the SAR image. Furthermore, aiming at the problem that the detection results of YOLO network have both stationary targets and moving targets, we excluded stationary targets according to whether there is an azimuth location offset of the target in between the fore-and aft-beam SAR images, and finally obtained detection results of the moving target. Simulation results verify the effectiveness of the proposed method.

Deep neural networks have been widely applied and researched in synthetic aperture radar (SAR) object detection and achieved a great success. However, deep supervised networks heavily rely on a large amount of labeled data, while the annotation is difficult and time-consuming to obtain. But the unlabeled data are comparably easier to get. Considering that, we introduce a semi-supervised learning framework for SAR object detection, which is built via label propagation and consistent augmentation. The experiments on a SAR ship dataset prove that the introduced semi-supervised training framework can achieve higher detection performance with utilizing the unlabeled data compared with the corresponding supervised object detection network.

Shadows of ground moving targets in video synthetic aperture radar (SAR) has been found very useful in ground moving target indication (GMTI) for they can indicate the real positions of moving targets at different times, which is significant for SAR reconnaissance and surveillance. However, nearly all the shadow-based SAR GMTI methods only focused on detecting shadows in every separate frame and failed to make full use of the continuous observation ability of video SAR. In this paper, we propose to apply a deep learning-based multi-target tracking method to solve this problem and find that the FairMOT network which jointly detects and re-identifies objects in sequential frames is suitable for this task. To verify its performance, video SAR datasets that contain shadows of ground moving targets are obtained by simulation. The experiments on the simulation datasets show that the introduced network in this work can achieve a state-of-the-art result, for instance, the multiple object tracking accuracy (MOTA) can reach 83.4%.

Non-line-of-sight (NLOS) radar imaging technique aims to reconstruct hidden targets that illuminated wave cannot reach directly, which can greatly expand the range of radar detection. In this paper, inspired by synthetic aperture radar (SAR), an effective two-dimensional (2-D) NLOS imaging technique via multiple input multiple output (MIMO) millimeter-wave (MMW) radar is proposed. In the scheme, a 2-D virtual antenna array is synthesized by MIMO antenna scanning, and the multi-bounces echoes is used to obtain 2-D NLOS imaging. Then an algorithm via mirror symmetry back-projection (MSBP) is presented for 2-D high-precision focusing of these NLOS echoes. Moreover, a cost-effective 79GHz MMW NLOS experiment system is developed for technical validation. The effectiveness of MMW NLOS radar imaging is verified by near-field multi-targets experiment, and high-precision 2-D imaging results of hidden knives are obtained by MSBP method.

Ship classification in Synthetic Aperture Radar (SAR) images is a fundamental and important step in ocean surveillance. Recently, with the rise of Deep Learning (DL), Convolutional Neural Network (CNN)-based SAR ship classifiers have made a huge accuracy progress compared with traditional hand-crafted feature methods. However, existing most CNN-based classification models uncritically abandon traditional mature hand-crafted features, but excessively rely on abstract features extracted by deep networks, which possibly brings great challenges in further improving classification performance. Therefore, to address this problem, this paper proposes a Histogram of Oriented Gradient (HOG) feature fusion method to improve CNN-based SAR ship classification accuracy. Experimental results on the open SAR ship classification dataset OpenSARShip reveal that when combining HOG feature fusion, the classification accuracy can achieve a 7.64% improvement.

In synthetic aperture radar (SAR) automatic target recognition, it is expensive and time-consuming to annotate the targets. Thus, training a network with a few labeled data and plenty of unlabeled data attracts attention of many researchers. In this article, we design a semisupervised learning framework including self-consistent augmentation rule, mixup-based mixture, and weighted loss, which allows a classification network to utilize unlabeled data during training and ultimately alleviates the demand of labeled data. The proposed self-consistent augmentation rule forces the samples before and after augmentation to share the same labels to utilize the unlabeled data, which can ensure the prominent effect of supervised learning part of the framework for training by balancing amounts of labeled and unlabeled samples in a minibatch, and makes the network achieve better performance. Then, a mixture method is introduced to mix the labeled, unlabeled, and augmented samples for the better involvement of label information in the mixed samples. By using cross-entropy loss for the mixed-labeled mixtures and mean-squared error loss for the mixed-unlabeled mixtures, the total loss is defined as the weighted sum of them. The experiments on the MSTAR data set and OpenSARShip data set show that the performance of the method is not only far better than the state of the art among current semisupervised-based classifiers but also near to the state of the art among the supervised learning-based networks.

The emerging field of combining compressed sensing (CS) and three-dimensional synthetic aperture radar (3D SAR) imaging has shown significant potential to reduce sampling rate and improve image quality. However, the conventional CS-driven algorithms are always limited by huge computational costs and non-trivial tuning of parameters. In this article, to address this problem, we propose a two-path iterative framework dubbed TPSSI-Net for 3D SAR sparse imaging. By mapping the AMP into a layer-fixed deep neural network, each layer of TPSSI-Net consists of four modules in cascade corresponding to four steps of the AMP optimization. Differently, the Onsager terms in TPSSI-Net are modified to be differentiable and scaled by learnable coefficients. Rather than manually choosing a sparsifying basis, a two-path convolutional neural network (CNN) is developed and embedded in TPSSI-Net for nonlinear sparse representation in the complex-valued domain. All parameters are layer-varied and optimized by end-to-end training based on a channel-wise loss function, bounding both symmetry constraint and measurement fidelity. Finally, extensive SAR imaging experiments, including simulations and real-measured tests, demonstrate the effectiveness and high efficiency of the proposed TPSSI-Net.

Convolutional Neural Networks (CNNs) have excellent ability in image recognition, however, the requirement of a large amount of labeled dataset limits its application in the field of synthetic aperture radar (SAR) image processing. In this paper, a kernel rotational network (KR-Net) for SAR target recognition is constructed. When the labeled dataset is small, the KR-net can achieve higher classification rate than standard CNNs benefit from its inherent rotational convolution units. Also, weights sharing strategy is introduced to increase network capacity without multiplying the number of weights parameters. Meanwhile, a simple and feasible multi-branch feature converging method for the KR-Net is proposed to fuse features of rotational convolution units. Experimental results show that our network can achieve state-of-art result in the MSTAR dataset, especially when the training set is small.

Compressive Sensing(CS) has been widely utilized in Inverse synthetic aperture radar(ISAR) imaging since real ISAR data is easier to be non-completed, and CS-based methods can obtain high-quality imaging results using under-sampled data. However, traditional CS-based methods need pre-defined parameters, sparse transforms and iterative reconstruction processes. Optimal parameters as well as transforms are tough to be hand-crafted, and iterative reconstruction consumes plenty of time, which limit practical applications in ISAR imaging. Given that Convolution Neural Network(CNN) has great power to learn rapidly, we compose CNN with traditional Iterative Shrinkage-Thresholding Algorithm(ISTA) to propose CNN-ISTA(CIST)-based ISAR imaging method. CIST is capable of learning optimal parameters and transforms throughout the training (i.e. the optimization process is interpretable) instead of manually defined. Compared with traditional state-of-the-art CS imaging methods, the experimental results demonstrate that our proposed CIST-based imaging method is superior in both imaging quality and computational efficiency.

Traditional dual-beam along-track interferometric synthetic aperture radar(DB-AT-InSAR) system uses along-track inter-ferometry(ATI) technique to calculate the radial velocity. However, the interferometric phase acquired by ATI can be easily affected by the noise and static clutter, which may reduce the accuracy of radial velocity estimation. In this paper, a novel ground moving target radial velocity estimation method is proposed for DB-AT-InSAR. First, the azimuth squint angle of the DB-AT-InSAR is reduced to make the fore and aft beams overlap. Then, only the overlapping subaperture echoes are used to reconstruct the SAR images by back projection algorithm. Finally, clutter suppression interferome-try(CSI) technique is applied to acquire high-accuracy radial velocity estimation. Since CSI technique can be able to suppress the clutter, it can obtain better interferometric phase than ATI, which improves the accuracy of radial velocity estimation. Simulation results show that the proposed method can obtain higher accuracy in radial velocity estimation than ATI method for DB-AT-InSAR system.

Deep neural networks have been widely applied and researched in remote sensing image scene classification and achieved a great success. However, deep supervised network heavily relies on a large amount of labeled data. The annotation is difficult and time-consuming to obtain but the unlabeled data are comparably easier to get. Considering that, we introduce a semi-supervised learning framework for remote sensing image scene classification. The network is trained by a novel adaptive perturbation training method. The experiments on NWPU-RESISC45 dataset prove that the introduced semi-supervised classification method can achieve higher classification accuracy with unlabeled data compared with the corresponding supervised classifier, and the designed adaptive perturbation training can further improve the performance of the semi-supervised learning-based classification network.

Compressed sensing theory has attracted extensive attention in the field of linear array 3-D Synthetic Aperture Radar (SAR) sparse imaging. However, conventional CS-based algorithms always suffer from quite huge computational cost. In this paper, we propose a new method for 3-D SAR sparse imaging based on convolutional neural network (CNN). Inspired by the work of ISTA-NET, a complex-valued version for imaging tasks is modified. Furthermore, we introduce a approximate phase correction scheme for 3-D imaging, it makes the proposed method works with only a constant measurement matrix corresponding to any slice. Moreover, Using a random training strategy, ISTA-NET networks for 3-D SAR imaging are effectively trained. Experimental results demonstrate that the proposed method outperforms conventional ISTA large margins in both accuracy and speed.

With the rise of Artificial Intelligence (AI), many previous studies have already applied Deep Learning (DL) for ship detection from Synthetic Aperture Radar (SAR) imagery. However, these network scale and model size are both rather huge, leading to more computation costs. As a result, ship detection speed is bound to decline due to more computation costs, and FPGA/DSP transplantation also becomes more challenging coming from huge mode size. Therefore, to solve these problems, this paper proposes a novel lightweight deep learning network for SAR ship detection named ShipDeNet-18 (only 18 convolution layers). Essentially, fewer layers and fewer kernels jointly contribute to ShipDeNet-18's light-weight characteristic. In addition, to compensate for the severe detection accuracy's sacrifice, we also propose a Deep and Shallow Feature Fusion Module (DSFF-Module) and a Feature Pyramid Module (FP-Module), which can effectively improve its detection accuracy. Experimental results on the open SAR Ship Detection Dataset (SSDD) reveal that ShipDeNet-18's detection speed is largely superior to the other state-of-the-art detectors, meanwhile its detection accuracy is only slightly inferior to others. ShipDeNet-18 is a brand-new deep learning network built from scratch, more light-weight than the other detectors, with fewer parameters (228,246), lower computation costs (456,042 FLOPs), and smaller model size (1 MB). It is of great value in some real-time SAR application, and is also convenient for future hardware transplantation (FPGA/DSP).

It's difficult to detect and estimate parameters for the slow moving target in clutter using conventional methods.To solve the problem, this paper proposes a method based on dual-beam interferometer SAR imaging mode(DBI).The moving target can be detected by the azimuth offset caused by the time delay of the forward-looking and backward-looking beams.The clutter is suppressed by displace phase center antenna (DPCA) after back projection(BP)algorithm.Then the radial velocity of the moving target can be obtained by the interferometric processing technology. Finally, using the azimuth pixel offset in the image to estimate the azimuth velocity of the slow moving target. With this method, the detection and velocity estimation of the slow moving target can be realized after good clutter cancellation. This method is suitable for the slow-moving and the micro-moving target in clutter, which is hardly possible for conventional SAR.Besides it is not limited by the conventional DPCA condition. The effectiveness of the proposed method is validated by the simulation.

For traditional ground moving target indication, multiple channels are necessary to cancel ground clutter. For high-speed aircraft, slow moving target detection is a difficult problem because ground clutter cannot be eliminated completely by channel cancellation. In this paper, we propose a method, which is implemented by single-channel SAR images and improved Faster R-CNN, to detect the moving target and the stationary target. Synthetic aperture radar image which contains amplitude and phase information is put into the neural network to detect the moving and stationary target. We make a dataset to verify the availability of the proposed method. In order to increase the credibility of the dataset, we use FEKO to calculate the target electromagnetic scattering characteristics and use measured data scattering characteristics to generate the ground echo. The simulation proves that the proposed method has good performance in moving target detection and the performance of the proposed method is better than Faster R-CNN.

In this paper, to remove the speckle noise of SAR images, we propose a modified method for SAR image despeckling based on Convolutional Neural Networks (CNNs). The network uses dilated convolutions for feature extraction, which can extend the receptive field and prevent too many layers that may result in computational burden and low efficiency. The network also uses residual learning to accelerate training procedure and improve performance for SAR image despeckling. Experimental results show that the proposed method achieve good performance for SAR image despeckling both on simulated and real data. And compared with the traditional despeckling methods, the proposed method has better performance and higher efficiency.

Object detection in very high-resolution (VHR) remote sensing images is a fundamental and challenging problem due to the complex environments. In this paper, a precise mask region convolutional neural network (precise Mask R-CNN) is presented for object detection and instance segmentation in VHR remote sensing images. This method generates bounding boxes and segmentation masks for each instance of an object in the image. Contrary to regions of interest (RoI) Align whose sample points is pre-defined and not adaptive the size of the bin, the proposed precise RoI pooling can directly compute the two-order integral based on the continuous feature map to avoid loss of precision. The experiments on NWPU VHR-10 dataset show that the presented precise Mask R-CNN improves the accuracy of object detection and instance segmentation for VHR remote sensing images. Furthermore, it promotes the application of instance segmentation in VHR remote sensing.

Spaceborne airborne bistatic linear array synthetic aperture radar (SA-BiLASAR) down-looking imaging is a novel and promising three-dimensional (3-D) radar imaging technique. To improve the imaging quality and resolution, a sparse imaging method is proposed for SA-BiLASAR down-looking 3-D imaging based on the sparse Bayesian reconstruction (SBR) theory. The bistatic geometric model and the echo model of SA-BiLASAR down-looking sparse imaging are derived. Then, a sparse expression of target by Laplace distribution is exploited, and an iterative optimization estimation method is applied for sparse target reconstruction. In addition, to correct the geometric distortion of 3-D image due to the bistatic observed mode of SA-BiLASAR, a geometric correction method is presented. Numerical simulation results demonstrate the effectiveness of the presented SBR method for SA-BiLASAR down-looking high-resolution 3-D sparse imaging.

Conventional synthetic aperture radar (SAR) reconstructs the illuminated scene via fast Fourier transform (FFT), which results in high sidelobe level, and poor cross-range resolution due to the finite synthetic aperture length. In this paper, we formulate a sparse reconstruction method for SAR imaging based on the covariance fitting criterion, which assumes that only a few strong scatters exist in the whole scene. The method is able to fully control over the sparsity level and reconstruct the scenario in an adaptive manner. Experimental results with real SAR data show the better performance of our method compared with the conventional methods in terms of resolution improvement and sidelobe suppression.

In this paper, we propose to apply a deep multi-scale encoder-decoder neural network (MsEN-Net) for SAR images enhancement method based on scale-recurrent network (SRN), which consists of encoder and decoder modules trained by the coarse to fine strategy. Simulation with fixed speed errors and experiments with real data are implemented and evaluated by peak signal to noise ratio and structural similarity. Experimental results with both visual and quantitative analysis demonstrate the competitive performance of our proposed method.

Autofocus method is a vital technology for high resolution and wide swath airborne Synthetic Aperture Radar (SAR) imaging. The autofocus algorithms via phase errors estimation and traditional Antenna Phase Centers (APC) errors estimation cannot completely compensate for the phase error of each pixel for the large scene ignoring the spatial variance, which results in corrupted SAR imagery for some part of the scene. In this paper, an autofocus algorithm through precise APC errors estimation based on joint multi-region is proposed to compensate motion error for the whole scene greatly. We established an image intensity model for strong point targets in multi-region with the weight coefficient to estimate APC errors. Moreover, the partial derivative of image intensity is simplified which can easily derive higher order criterion like image sharpness and Conjugate Gradient (CG) is utilized to solve the optimization problem. The simulation and experimental examples verify the effectiveness of the proposed method compared with traditional methods.

Array synthetic aperture radar (SAR) is one of the hot areas in radar imaging field because of its three-dimensional (3-D) imaging ability. Combining the advantages of linear array SAR in aspect of side-lobe suppression and circular SAR in aspect of high resolution, a new kind of annular array synthetic aperture radar (AASAR) mode is employed for 3-D microwave imaging. Based on the mathematical derivation of AASAR model, the sparse layout of the annular array in the cross-track direction can acquire 3-D high resolution and effective side-lobe suppression ability. Then on this basis, a proto-type AASAR experiment system is built, and some 3-D AASAR imaging outdoor experiments are conducted. Through the experiment result, the validity of 3-D AASAR imaging can be demonstrated.

High-speed maneuvering synthetic aperture radar (SAR) moves with a high speed and complex trajectory. It's difficult for it to detect the ground slow moving target using the conventional detection method. To solve this problem, a slow moving target detection method via bidirectional imaging mode (BiDi) is proposed in this paper. The influence of the motion parameters on the moving target's imaging position is discussed, and the location relationship of the moving target between the two SAR images acquired via BiDi mode is also analyzed. The along track separation in BiDi mode can make an azimuth offset of the moving target between the two SAR images. On the other hand, the moving target's opposite imaging position offset in azimuth direction will further increase this azimuth offset. While there is no offset in the range direction of the moving target due to it's azimuth velocity. According to the position differences of the moving target in the two SAR images, the ground slow moving target can be detected successfully. Simulation results have verified the effectiveness of the proposed method.

The influence of phase error in echo signal is rarely considered or corrected by most classical compressed sensing (CS) algorithms, and reduces the quality of imaging results. In order to improve the quality of array synthetic aperture radar (ASAR) imaging, a new CS algorithm called Iterative Adaptive Reweighted Norm Minimization Sparsity Autofocus algorithm via Bayesian Recovery (IARNSABR) was proposed in this paper. Based on the principle of Bayesian Recovery, the iterative adaptive reweighted norm minimization method has been used in the process of reconstruction. The theoretical model and the process of imaging of IARNSABR has been established. And the proposed algorithm can correct the influence of phase error more effectively, and has stronger ability of eliminating the false targets. Through simulation and experiment results, IARNSABR can achieve higher quality imaging than SAFBRIM.

In this paper, an efficient registration algorithm for InSAR large scale image via discrete Fourier transform (DFT) model of the maximum correlation and image quadtree segmentation is proposed. In the scheme, a DFT-based sub-pixel registration model of InSAR complex images is constructed. Then, efficient sub-pixel registration for InSAR large-scale image is achieved by joint quadtree segmentation and DFT-based interpolation registration. Simulation and experimental results are presented to confirm the effectiveness of the proposed algorithm. The results demonstrate that the algorithm not only can achieve sub-pixel registration of InSAR large-scale image, but also has higher computational efficiency compared with the traditional maximum correlation registration method.

This paper presents an efficient sparse autofocusing algorithm for 3-D SAR imaging based on joint criterion optimization. Exploiting by the least square (LS) regularization sparse recovery technique, an autofocus model combined with minimum mean square error criterion and maximum sharpness criterion, is constructed for 3-D SAR sparse image formation via linear measurement expression. Moreover, the adaptive weighted factor for phase error estimation is derived. Then, a joint iterative estimated method is introduced to efficiency estimate the phase errors. Numerical simulation and experimental results are provided to demonstrate the effectiveness of the proposed algorithm with different types of phase error.

For the drawbacks of the synthetic bandwidth method based on time-domain back projection, a novel synthetic bandwidth method based on frequency-domain back projection is proposed in this article for stepped-frequency synthetic aperture radar to improve the computation efficiency and to realize the automatic spatial spectra cutting. To give a direct and clear comprehension for wideband synthesizing in the spatial image space, the bandwidth and centre frequency for spatial image are defined for the first time. The simulation results validate the effectiveness of the proposed method.

This paper discusses the digital elevation model (DEM) estimation problem for the linear array synthetic aperture radar based on the variational model. Compared with the sparse recovery model, the one-to-one mapping between the horizontal grid nodes and the elevations is preserved explicitly, which is important for the topographic surveying and mapping mission. During the research, we find that since the mean square error criterion is insensitive to the amount of the elevation offsets, the numerical method by solving the Euler-Lagrange equation is unreliable and the global optimization method is necessary to solve the variational problem. With the ambiguity function localization and the sliding-window architecture, the global optimal path can be obtained by solving a series of local optimization problems provided that the observation matrix is row full rank. Furthermore, the local optimization problem can be relaxed as a sparse recovery problem and can be solved by a modified orthogonal matching pursuit (OMP) method (named as Var-OMP), whose computational cost is acceptable for the actual data processing. By a series of numerical experiments, we show that the performance of Var-OMP is influenced by both the resolution enhancement factor (L) and the signal-to-noise ratio (SNR). The larger the SNR is, the better the performance is; the smaller L is, the more stable and faster the Var-OMP algorithm is. Compared with the sparse recovery methods, the variational model and the Var-OMP algorithm are more suitable for the DEM estimation application in the face of all kinds of terrains.

Due to uncertainties of the platform motion, the trajectory of airborne millimeter-wave interferometric synthetic aperture radar (MMW-InSAR) usually demonstrates highly non-linear, which cause dynamic baseline to height inversion. In such cases, traditional InSAR methods may suffer from serval difficulties for imaging and height inversion. In this paper, a novel back projection imaging algorithm via terrain height prediction, named as THP-BP algorithm, is proposed. In this theme, an iterated approximating method is used. In each iteration, the MMW-InSAR data is projected into an estimated terrain surface to producing interferogram, and then the terrain height of the observed scene can be predicted via minimizing of the interferometric phase value of MMW-InSAR. The effectiveness of the proposed method is testified by both simulation and experiment data, the results demonstrate that it can improve the quality of both image focusing and height inversion compared with conventional BP algorithm.

A novel synthetic aperture radar (SAR) sidelobe suppression method via a dual-Delta factorization (DDF) algorithm is proposed in this letter. Its basic idea is to divide the point spread function (PSF) into a group of different simple subsystems (dual-Delta operators) and to asymptotically approach the solution by the subsystem iterations based on the greedy strategy. The convergence of the DDF algorithm is discussed based on theoretical analyses and numerical experiments. We find that, to keep the algorithm convergent, the sidelobe sum should be soundly smaller than that of the main lobe during the iterations. Simulation experiments and actual SAR image results show that the DDF algorithm can deal with all kinds of PSFs without their exact expressions and is compatible with nonseparable cases, which makes it suitable to process the squint SAR and bistatic SAR images.

The back projection (BP) algorithm is an accurate time-domain imaging method for synthetic aperture radar. However, the influences of wind field and turbulence on the platform make the antenna phase centers (APCs) greatly deviate from the designed linear trajectory and degrade the BP performance. Although the inertial measurement unit can be used to measure the trajectory, the measurement error still affects the image quality to some extent. The autofocus BP algorithm under the criterion of maximum image sharpness has been proposed to compensate the motion error effectively. However, this method needs to compute and store the per-pulse back-projected values for all pixels, which results in the heavy burden for memory and time and limits its practical application. This letter demonstrates an improved way to overcome these two drawbacks without loss of focusing performance. In our new method, only minority pixels are selected for autofocus to estimate the phase error, which is used to obtain the APCs by solving a system of nonlinear equations with an optimization method. This procedure is particularly suitable for the wide application of the autofocus BP. The experimental results strongly validate the efficacy and efficiency of the improved autofocus BP algorithm.

The 3-D image of Linear array synthetic aperture radar (LASAR) usually exhibit high sparseness, so sparse imaging algorithms based on compressed sensing (CS) theory can be used for LASAR 3-D imaging. However, the conventional CS-based imaging scheme suffers from huge computational time, especially for large scene imaging, which requires a huge sensing matrix to reconstruct the whole scene. In this paper, a sparse locations prediction strategy is proposed for CS-based LASAR 3-D imaging. The sparse target cells of the scene is firstly estimated by location prediction method with the traditional image, and then the scene is split into subspaces and the echo data is segmented into subsets, the measurement matrix is constructed only using the sparse cells of the subspaces, so that the reconstruction time can be reduced significantly. Simulation and experiment results demonstrates the validity of the approach.

This paper presents an iterative autofocus approach to improve the performance of compressed sensing (CS) in synthetic aperture radar (SAR) imaging in the case of model error. Combined with the least square (LS) regularization technique and the minimum mean square error (MMSE) focusing method, the approach can solve a joint optimization problem to achieve model error parameter estimation and SAR image formation simultaneously. In each iterative of the approach, the SAR observation model is updated with the sensor platform positions obtained by a MMSE-based focusing cost function, after that, the image is reconstructed by LS regularization technique with the updated observation model. Numerical simulation results demonstrate the effectiveness of the approach for CS-based SAR imaging with observation model error.

Range cell migration (RCM) correction (RCMC) is the key process in the imaging formation of bistatic synthetic aperture radar (SAR) (BiSAR). Due to the existence of double square root in the bistatic range equation, the RCMC in the general BiSAR configuration is more complicated than the traditional monostatic method. In this letter, the RCM of BiSAR system is analyzed in detail, and a novel data transformation is derived. From the derivation, we find that the original keystone transform (KT) is only a special case of our proposed transformation, so that we called it the generalized KT (GKT). Compared with the original KT, this generalized method can correct more complex RCM nicely. After the GKT processing, the RCM is eliminated closely, and the focused image with full range and Doppler resolution can be obtained using the fast Fourier transform. Finally, a hybrid spaceborne/airborne BiSAR numerical simulation is performed to validate the proposed processing procedure.

Unlike 1-D and 2-D microwave images, 3-D microwave image behaves typical sparsity. Consequently, sparse recovery technique can be used for 3-D microwave signal processing. Three popular signal processing techniques, the time-domain correlation method (TDC), pseudo-inverse method (PI), and compressed sensing method (CS), are discussed in this paper. We find that PI and CS methods can eliminate the side-lobe coupling error of TDC method with the cost of additional noise gains. The performances of TDC, PI, and CS methods are influenced by the autocorrelation matrix of the measurement matrix, which is determined by the distribution of the sparse array and the number of receivers. In general case, the measurement matrix of microwave 3-D imaging cannot be considered as a group of independent identically distributed (i.i.d.) random variables with zero mean. As a result, many properties developed under the i.i.d. Gauss random variable and i.i.d. random variable with zero mean hypotheses cannot explain the microwave 3-D imaging problem accurately. Further discussions on the effects of the image sparsity and number of receivers on TDC, PI, and CS methods are presented in this paper. In usual case, the sparser the image is, the better the imaging result is. In the aspect of the number of receivers (assuming that array size is fixed), when the receiver number is relatively small, increasing it can reduce the coupling error of TDC method and the noise gains of PI and CS methods. When the number of receivers is large enough, increasing it makes less contribution to improving the coupling error or noise gains. Finally, we show that under ill condition, CS method is far more stable than PI method by numerical experiment.

In this paper, we present a fast imaging method based on subaperture approximation (SA) technology for 3-D microwave imaging. Compare to 2-D microwave imaging, one of main problems in 3-D microwave imaging is its high computational cost caused by dimension expansion from 2-D to 3-D. This problem limits the application of 3-D microwave imaging. In practice, many 3-D imaging regions contain no targets or are shadowed by other scatterers, which is the sparse character of 3-D imaging regions. Based on this character, we propose a fast imaging method using the SA technology. The basic concept of the SA technology is using subapertures to pick out the regions of interest, then image in the regions of interest. The computational cost of this method is analyzed, and some experimental results are conducted to demonstrate the feasibility of this method. We find that the computational cost of SA 3-D imaging method is far smaller than that of the 3-D BP imaging method.

With the ability of 3-D resolution, LASAR is more suitable for the reconnaissance and surveying applications in urban and mountain areas. However, there are some obstacles for airplane-borned LASAR. Compared with airplane, airship is more feasible for LASAR, because of its large size, long duration and huge loading capacity. Combined with MIMO and sparse array techniques, the system cost is affordable in practice. Sparsity of 3-D image should be highlighted during the course of image processing, which can reduce the algorithms' complexity and improve the image quality.

Because of the influence of large range walk and geometrical distortion, traditional synthetic aperture radar (SAR) imaging algorithms, such as range doppler (RD) etc., cannot be used for three demensional (3-D) forward looking SAR (F-SAR) imaging directly. In this paper, we first derive the chirp scaling algorithm (CSA) for 3-D F-SAR. Next, we analyze the geometrical distortion analytically and provide an effective approach to reconstruct the scatters to their exact positions without interpolation. Moreover, we briefly discuss the point spread function's isosurface shape and how geometrical distortion correction (GDC) influence on it. Finally, the simulation experiments about single point and multipoint verify the algorithm's validity.

The back projection (BP) algorithm is highly effective in bistatic SAR imaging. But it is time-consuming for the large scene imaging. In this paper, we propose a GPU-based parallel BP algorithm, the range compression and back projection are implemented on the graphics processing unit (GPU) using CUDA language. We also present some optimum methods including memory optimization, phase accumulator reduction and imaging scene segmentation to implement fast and large scene imaging. Numerical experiments demonstrate that the GPU-based method can significantly improve the computational efficiency of the original BP algorithm, about 80 times faster, while the imaging scene size same as the CPU-based BP algorithm.

This paper discusses the antenna phase center trajectory (APCT) design for the "one-active" linear-array 3D imaging SAR (LASAR). First, we discuss the principle of the one-active LASAR and demonstrate its feasibility by experiment. To describe the 3D spatial resolution of the one-active LASAR, the relationship between the 3D ambiguity function (AF) of the one-active LASAR and the system parameters is discussed in detail. Based on the analysis, we divide the APCT design into three topics: the direction of the linear array, the length of the linear array, and the switching mode of the active element [named as antenna phase center function (APCF)]. On the first topic, we conclude that, when the range, along-track, and cross-track directions are orthogonal to each other, the ambiguity region of the one-active LASAR attains minimum, and the 3D spatial resolution can be separated into the range, along-track, and cross-track resolutions. On the second topic, we find that the cross-track resolution is determined by the length of the linear array and the frequency of the carrier. To ensure that the length of the linear array is acceptable, the carrier should be W-band wave or millimeter wave. On the third topic, the effect of APCF is researched, and we find that both the periodic APCF and the pseudorandom APCF can produce 3D resolution, except for the periodic rectangle APCF. For the pseudorandom APCF and the periodic APCF with short period, the cross-range 2D AF is or can be approximated as the product of two 1D AFs in the along- and cross-track directions. Finally, the distribution of the pseudorandom APCF is optimized by the Lagrange multiplier method under the minimum variance criterion, and we find that, when the pseudorandom APCF obeys the parabolic distribution, the cross-range 2D AF is optimal.

The influences of the motion measurement errors (MMEs) to the 3D SAR imaging are analyzed based on the “one-active” LASAR system in this paper. Firstly, the principle and the spatial ambiguity function (AF) of the “one-active” LASAR are introduced. Then the 3D MMEs are introduced according to three forms: the 3D velocity errors and the 3D acceleration errors, the sine vibration errors and the array vibration errors. The 3D SAR system's maximum allowable MMEs are obtained and the influences of the 3D MMEs to the 3D AF are analyzed by the numerical simulation. Finally, the ground experiments and its results are presented, which validate the feasibility of the “one-active” LASAR.

This letter concerns the resolution-fusion method for linear array 3-D imaging SAR (LASAR). Limited by the length of the linear array, the cross-track resolution of LASAR is often lower than that in the along-track direction. To overcome this disadvantage, we assume that there are two LASAR systems whose trajectories are orthogonal to each other. Thus, we obtain a row low-resolution image and a column low-resolution image of the same scene. Using the orthogonal complement decomposition technique, we fuse the two images into one quasi-high-resolution image. Moreover, we find that the fusion distortion is unavoidable and contains the high-frequency component in both row and column directions. The information loss ratio is (N- 1)2/N2(Ndenotes the ratio of low resolution to high resolution). For a smooth image, the energy loss ratio is near to zero. With the increase of the noise energy, the energy loss ratio increases correspondingly. When the noise submerges the image completely, the energy loss ratio converges to the information loss ratio.

This paper discusses the antenna phase centre trajectory (APCT) design for the sparse linear array 3-D imaging SAR(LASAR). Firstly, we introduce the signal model of the sparse LASAR. Based on the model, we discuss the 3-D ambiguity function (AF) of the sparse LASAR, and reveal the relationship between the 3-D AF and the system parameters. Finally, the distribution of the pseudo-random APCF is optimized by the Lagrange multiplier method under the minimum variance criterion, and we find that when the pseudo random APCF obeys the parabolic distribution, the cross-range 2-D AF attains optimal, which has both good mainlobe and sidelobe performance.

In this paper, we present a fast 3-D imaging method for linear antenna synthetic aperture radar (LASAR). The basic idea of this technique is to consider the 3-D SAR imaging problem as tracing a surface in the observation region, since a great deal of 3-D image region contains no scatterer (such as atmosphere) or is shadowed by the other scatterers. The steps of the fast 3-D imaging method includes: Initiation, prediction, searching and recursion. Finally, some numerical experiments are presented to demonstrate the feasibility of this method. And we find that the computational cost of the fast 3-D imaging method varies according to the fluctuation of ground, and is about a dozen of times larger than that of 2-D BP algorithm.

A bistatic-based sparse linear array three dimensional (3D) imaging SAR (BSLASAR) is demonstrated and its resolution characteristic are analyzed in this paper. First, the principle of the BSLASAR is presented, the echo model is build and the imaging condition of BSLASAR is derived. The 3D BP (back projection) algorithm is introduced to focus the 3D SAR data. Then 3D PSF is analyzed, and the 3D spatial resolution expressions of BSLASAR are obtained. It is proved that the 2D horizontal PSF can be decomposed into two independent 1D PSF, the along track (AT) PSF and the cross track (CT) PSF, when the linear array direction is perpendicular to the AT direction. Compared to other configurations, this system inherits the advantages of conventional bistatic SAR and has these additional advantages: the receiver antenna phase center (APC) control precise is more flexibility than the curved SAR (CSAR), the hardware expenditure is saved and the couples between the elements are avoided.

This paper concerns the surface-tracing-based (STB) linear-array synthetic-aperture-radar (LASAR) 3-D imaging technique. The basic idea of this technique is to consider the 3-D SAR imaging problem as tracing a surface in the low height-resolution level. The STB 3-D imaging technique first initiates a low-resolution digital elevation map (DEM) using 3-D backprojection (BP) algorithm, predicts a higher resolution DEM from the known elevation using multivariate-interpolation technique, searches from the predicted elevation and obtains a higher resolution DEM, then repeats the prediction and searching recursively and obtains the fine-resolution DEM finally. By converting the 3-D LASAR imaging problem to a 2-D surface-tracing problem, the STB 3-D imaging technique can reduce the computational complexity by one order. The computational cost of STB 3-D imaging technique is analyzed, and we find out that the computational cost of STB 3-D LASAR imaging technique is determined by the surface prediction error and the fluctuation of ground. In particular, for normal distribution, when one of the earlier two factors is small, the computational cost is proportional to the other factor approximately. Finally, a new STB 3-D BP algorithm that implements the surface-prediction operation via multiresolution-approximation (MRA) technique (named as MRA 3-D BP algorithm) is presented. By operating the interpolation in frequency domain, the computational cost of MRA algorithm for sparse LASAR is near to that of RD algorithm for full-element LASAR.

In this paper, we discuss the mapping between the 3-D scene space and the bistatic synthetic aperture radar (SAR) image space and show that when the direction of the angular velocity of the bistatic SAR remains constant, the process of bistatic SAR imaging can be approximately modeled as a perspective operator from the 3-D scene space to the 2-D image space, and the perspective line is perpendicular to the plane determined by the composition direction of the T/R line of sight and the composition direction of the angular velocity of the T/R platform. Then, we show that the 2-D point spread function of the bistatic SAR is determined not only by the range and ldquoazimuthrdquo resolutions but also by the geometry of the bistatic SAR and the bases of the SAR image space, and the concept ldquoambiguity regionrdquo is introduced to describe the ambiguity problem in the 3-D scene space. Then, the range-Doppler algorithm is discussed, and a new translational-variant bistatic SAR imaging method is proposed, which uses the scaled inverse fast Fourier transform (IFFT) technique to eliminate the translational-variant feature of the SAR space resolution. The space truncation error of this new algorithm is discussed to analyze the depth of focus of the scaled IFFT bistatic SAR imaging algorithms, and we find that the upper bounce of the space truncation error is proportional to the square of the distance from the scatterer to the T/R platforms. Last, the effects of motion measurement errors are discussed in detail, and, through theoretical analysis and numerical experiments, we show that the absolute position measurement error, the baseline measurement error, the perpendicular (vertical) component of the absolute velocity measurement error (AVME), and the perpendicular component of the relative velocity measurement error (RVME) cause SAR image shifting in the image space mainly, and the parallel component of the AVME and the parallel component of the RVME cause the SAR image to severely defocus.

In this paper, we discuss the translational-variant feature of translational-variant bistatic SAR configuration using the space Taylor’s expansion in section II. In section III, a new translational-variant bistatic SAR imaging method is proposed, which uses scaled IFFT technique to eliminate the translational-variant feature of SAR space resolution. Finally, some numerical experiments are conducted to demonstrate the feasibility of this method and discuss the depth-of-focus of the scaled IFFT bistatic SAR imaging algorithms.