Synthetic Aperture Radar Image Formation Research Articles

Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers.

Studies on High-Resolution Airborne Synthetic Aperture Radar Image Formation with Pseudo-Random Agility of Interpulse Waveform Parameters

By means of alteration of the transmitted linear frequency modulation (LFM) signal waveform parameters, such as pulse width or chirp rate, initial phase, pulse repetition interval (PRI), and chirp rate polarity at every position of synthetic apertures, the pseudo-random agility technology of interpulse waveform parameters in airborne Synthetic Aperture Radar (SAR) actively increases the complexity and uncertainty of radar waveforms. This technology confuses jamming interception receivers, thus improving its anti-interference ability for active coherent jamming, which is one of the main research interests of airborne SAR technology. But the pseudo-random agility technology for interpulse waveform parameters faces certain challenges of large computation and complex system design, which need to be further studied and solved. To address these issues, a processing scheme of high-resolution SAR image formation which is appropriate for agile interpulse waveform parameters is proposed in this paper. This method can deal with multiple agile parameters, not only single ones as in most existing literature. Its computation load is nearly comparable to that of traditional SAR image formation with constant waveform parameters. The high-resolution SAR imaging results obtained by processing SAR raw data with agile interpulse waveform parameters demonstrate the effectiveness of the proposed method. In addition, real SAR images with resolutions of 0.5 m and 0.15 m, which are rarely found in the public literature, are shown under the circumstance of randomly changing the transmitted wideband LFM signal pulse parameters one by one.

Enhanced range-doppler algorithm for SAR image formation

A Synthetic Aperture Radar (SAR) system is a powerful source of information due to its capability to operate day and night and in all weather conditions. It is essential for military and civilian purposes. Pulse-focusing is employed by the SAR system for achieving both long-range detection and fine-range resolution. The Range-Doppler Algorithm (RDA) is the most popular pulse-focusing technique for creating images from coherent SAR data. Pulse compression techniques for SAR signal processing targets seek to improve map resolution, lower peak power, and increase the Signal-to-Noise Ratio (SNR) of the detected object. This paper demonstrates an enhanced RDA algorithm that uses a modified pulse compression technique based on mismatched filter optimization where Quadratic Constrained Quadratic Program (QCQP) is used. The performance evaluation of the proposed method is performed using visual assessment and the standard image quality metrics peak-side-lobe-ratio (PSLR), impulse-response-width (IRW), and integrated-side-lobe-ratio (ISLR). Simulated and real SAR raw data are used for performance evaluation. The experimental results demonstrate the proposed method’s robustness, efficiency, and reliability in providing a higher-quality SAR image than the traditional RDA algorithm.

A novel block compressive sensing algorithm for SAR image formation

Compressive Sensing (CS) theory has been used for Synthetic Aperture Radar (SAR) imaging due to the sparsity feature of SAR images. Therefore, some well-known CS algorithms like Orthogonal Matching Pursuit (OMP) and Regularized OMP (ROMP) methods have been employed for SAR image formation with a very small number of samples. On the other hand, it has been shown that the SAR signal is consistent with the definition of block sparsity. Hence, compressive sensing methods employing block structure, known as Block Compressive Sensing (BCS), are presented and used for SAR image formation to achieve more accuracy with a smaller number of samples. In this paper, first, a new BCS-based algorithm, namely, Block Norm Regularized Orthogonal Matching Pursuit (BNROMP), is introduced which can be used in all BCS applications. Then, this novel method is used for SAR image formation to achieve more accuracy and excellent resolution with a small number of samples. The simulation results for the synthesized data, as well as real data, show that by using the novel BNROMP method, we could form SAR images with higher quality, as compared to those for the standard image formation algorithms and other CS-SAR or BCS-SAR methods.

Sub-aperture SAR imaging with uncertainty quantification

In the problem of spotlight mode airborne synthetic aperture radar (SAR) image formation, it is well-known that data collected over a wide azimuthal angle violate the isotropic scattering property typically assumed. Many techniques have been proposed to account for this issue, including both full-aperture and sub-aperture methods based on filtering, regularized least squares, and Bayesian methods. A full-aperture method that uses a hierarchical Bayesian prior to incorporate appropriate speckle modeling and reduction was recently introduced to produce samples of the posterior density rather than a single image estimate. This uncertainty quantification information is more robust as it can generate a variety of statistics for the scene. As proposed, the method was not well-suited for large problems, however, as the sampling was inefficient. Moreover, the method was not explicitly designed to mitigate the effects of the faulty isotropic scattering assumption. In this work we therefore propose a new sub-aperture SAR imaging method that uses a sparse Bayesian learning-type algorithm to more efficiently produce approximate posterior densities for each sub-aperture window. These estimates may be useful in and of themselves, or when of interest, the statistics from these distributions can be combined to form a composite image. Furthermore, unlike the often-employed -regularized least squares methods, no user-defined parameters are required. Application-specific adjustments are made to reduce the typically burdensome runtime and storage requirements so that appropriately large images can be generated. Finally, this paper focuses on incorporating these techniques into SAR image formation process, that is, for the problem starting with SAR phase history data, so that no additional processing errors are incurred. The advantage over existing SAR image formation methods are clearly presented with numerical experiments using real-world data.

Conversion from multi-spectral data into SAR data with Deep Convolution Neural Architecture using Generative Adversarial Network

Synthetic Aperture Radar (SAR) is a high-resolution radar extensively used for aerial and terrestrial images in numerous applications. The SAR images are all weather and day/night capable. It is extensively used in defense/military systems for surveillance, target detection and target tracking. In current times, the need for deep learning algorithms has increased due to its capability of generating SAR images, as it is very intensive and expensive task for the acquisition and formation of SAR images through sensors. Thus, alternative methods are required to produce SAR image data. In this paper, generative adversarial networks (GAN) are used to generate SAR images from a limited pre-existing dataset. This paper presents a novel way of translating optical images to SAR images, for the generation of paired, unpaired data set. Due to the unavailability of an open-source paired, unpaired image dataset, a synthetic paired image dataset is created for proving the concepts of CycleGAN and Pix-to-Pix algorithm by fine tuning the algorithms using generated datasets. The paper tried tackling this problem in two ways, both paired and unpaired image-to-image translation.

Sparse Synthetic Aperture Radar Imaging From Compressed Sensing and Machine Learning: Theories, applications, and trends

Synthetic aperture radar (SAR) image formation can be treated as a class of ill-posed linear inverse problems, and the resolution is limited by the data bandwidth for traditional imaging techniques via matched filter (MF). The sparse SAR imaging technology using compressed sensing (CS) has been developed for enhanced performance, such as superresolution, feature enhancement, etc. More recently, sparse SAR imaging from machine learning (ML), including deep learning (DL), has been further studied, showing great potential in the imaging area. However, there are still gaps between the two groups of methods for sparse SAR imaging, and their connections have not been established.

A Rationale for Backprojection in Spotlight Synthetic Aperture Radar Image Formation

A Rationale for Backprojection in Spotlight Synthetic Aperture Radar Image Formation

Synthetic Aperture Radar Image Formation and Processing on an MPSoC

Satellite remote sensing acquisitions are usually processed after downlink to a ground station. The satellite travel time to the ground station adds to the total latency, increasing the time until a user can obtain the processing results. Performing the processing and information extraction onboard of the satellite can significantly reduce this time. In this study, synthetic aperture radar (SAR) image formation as well as ship detection and extreme weather detection were implemented in a multiprocessor system on a chip (MPSoC). Processing steps with high computational complexity were ported to run on the programmable logic (PL), achieving significant speed-up by implementing a high degree of parallelization and pipelining as well as efficient memory accesses. Steps with lower complexity run on the processing system (PS), allowing for higher flexibility and reducing the need for resources in the PL. The achieved processing times for an area covering 375 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> were approximately 4 s for image formation, 16 s for ship detection, and 31 s for extreme weather detection. These developments combined with new downlink concepts for low-rate information data streams show that the provision of satellite remote sensing results to end users in less than 5 min after acquisition is possible using an adequately equipped satellite.

Efficient SAR Imaging Integrated With Autofocus via Compressive Sensing

In synthetic aperture radar (SAR) imaging, perturbations in the motion of the moving platform induce an undesired phase error due to imprecise knowledge of the motion, which results in the significant degradations in the quality of SAR images. In this paper, we present an efficient compressive sensing (CS)-based SAR imaging integrated with autofocus technique. The novel approach is based on an estimation-theoretic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm-based approach coupled with Tikhonov-type regularization which combines an observation model of the SAR image formation process with the CS reconstruction problem of the SAR image regarding the sparsity. The optimization problem derived by considering spatially variant phase errors along azimuth domain and the dataset sampled at low rates can be effectively addressed by an efficient iterative method, wherein each iteration both SAR image formation and phase error correction are simultaneously carried out. The simulations and experimental results are presented to validate the effectiveness of the proposed method in terms of reliable image recovery and efficient computational complexity.

The Effects of Dry Snow on the SAR Impulse Response and Feasibility for Single Channel Snow Water Equivalent Estimation

Snow water equivalent (SWE) is an important surface parameter for understanding a number of Earth system processes. Synthetic aperture radar (SAR) has considerable potential for measuring SWE of dry-snow because SAR can penetrate through the snow to the ground surface and is both amplitude- and phase-sensitive to refraction from the snow. Previous work on refraction-based SWE measurement by SAR has utilized the repeat-pass InSAR phase signal to estimate changes in SWE that occur between SAR acquisitions. These are subject to temporal decorrelation effects and consider only the refraction that occurs along the SAR beam center rather than the entire synthetic aperture. This study examines the refractive effect of dry-snow along the synthetic aperture and its impact on SAR image formation including defocusing and phase bias of the system impulse response. Snow phase compensation during time domain processing to recover the snow-free impulse response function (IRF) is described and demonstrated. The feasibility of using the mapdrift and image sharpness autofocus methods to estimate SWE is examined, and the effect of key system parameters on the estimation performance is derived. Experimental validation of the method was conducted by acquiring L-band data with the Simon Fraser University (SFU) Airborne SAR System over a pair of corner reflectors installed on the Kluane icefield in northwestern Canada. Results from both simulations and the icefield experiment are presented and compared including an analysis of errors affecting the estimation.

Sensitivity of back‐projection algorithm (BPA) synthetic aperture radar (SAR) image formation to initial position, velocity, and attitude navigation errors

The Back-Projection Algorithm (BPA) is a time-domain-matched filtering technique to form synthetic aperture radar (SAR) images. To produce high-quality BPA images, precise navigation data for the radar platform must be known. Errors in position, velocity, or attitude result in improperly formed images that are corrupted by shifting and blurring. The contribution of this paper is the development of analytical expressions that characterise the relationship between navigation errors and image formation errors from an inertial navigation point of view, where trajectory estimation errors in position, velocity, and attitude propagate through time and cause compounding errors in the vehicle state vector. These analytical expressions are verified via simulated image formation and real-data image formation.

SAR image formation enhancement using effective velocity estimation method

Synthetic Aperture Radar (SAR) presents powerful tools for grounding mapping and remote sensing applications. Effective velocity is a vital index that controls the quality of SAR image formation. An accurate calculation of effective velocity provides a particular value of azimuth frequency modulated (FM) rate. The resultant azimuth FM rate could be used to produce a focused SAR image with sharp details. In this paper, SAR image formation enhancement is proposed using two guided methods based on precise effective velocity estimation. Firstly, effective velocity is estimated based on Sentinel-1data parameters extracted from selected image raw data. Secondly, an iteration method applies output image contrast, sharpness and entropy measurements to estimate the optimum value of the effective velocity based on the initial velocities calculated in the first method. Results are compared with extracted SAR images ignoring the effect of the effective velocity, to identify the performance of the proposed methods.

Fixed-Point Processing of the SAR Back-Projection Algorithm on FPGA

Time-domain back-projection (BP) is a widely known method used in synthetic aperture radar (SAR) image formation. Despite its advantages over other image formation algorithms, the BP method is hindered due to its computational complexity and its requirement of higher number of operations and processing power. Recently, field-programmable gate array (FPGA) devices have been used for BP acceleration mainly due to their parallel processing capabilities, reconfigurability, scalability, and low power requirement. This article presents a new fixed-point based BP (FxBP) design for FPGA devices and a floating-point-based BP (FlBP) design to compare performance. Both designs are developed with N -dimensional range (NDR) structure and single-work item (SWI) structure using OpenCL. The FPGA performance is evaluated using an FPGA performance metric. It is shown that FxBP-NDR and FxBP-SWI designs generate high-quality back-projected images compared to FlBP designs, while saving 16.87% and 42.54% on logic resources and gaining 17.90% and 91.62% on FPGA performance in NDR and SWI, respectively. Obtained results clearly indicate that FPGA devices perform significantly better with FxBP designs compared to FlBP designs, even with hardened FPUs.

SAR Image Formation Method with Azimuth Periodically Missing Data Based on RELAX Algorithm

Synthetic aperture radar (SAR) is a widely used remote sensing observation technique. However, SAR raw echo data may be lost during the process of data acquisition by radar platform. In this paper, the imaging problem of SAR echo signal with periodically missing data along the azimuth is analyzed and a novel imaging method is proposed. Firstly, the problem of artificial artifact targets caused by periodically missing data is explained in detail, and the corresponding mathematical model is established. Then, the recovery method based on the RELAX algorithm with periodic notches data is proposed. In addition, when the size of two-dimensional (2D) echo data are large, block restoration along the azimuth is proposed to reduce the amount of calculation. Finally, the advantages of the algorithm proposed in this paper is demonstrated by the points target simulated SAR echo data processing and the real raw SAR echo data processing. When the azimuth periodically missing data rate is 50%, the SAR echo data can be recovered and the well-focused image can be obtained. Comparing the image entropy value and structural similarity index (SSIM) of the focused image, it proves the superiority of the proposed algorithm in solving the imaging problem of SAR azimuth periodically missing data.

SodSAR: A Tower-Based 1-10 GHz SAR System for Snow, Soil and Vegetation Studies.

We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic Aperture Radar (SAR) aimed at snow, soil and vegetation studies. The instrument is located in the Arctic Space Centre of the Finnish Meteorological Institute in Sodankylä, Finland. The system is based on a Vector Network Analyzer (VNA)-operated scatterometer mounted on a rail allowing the formation of SAR images, including interferometric pairs separated by a temporal baseline. We present the description of the radar, the applied SAR focusing technique, the radar calibration and measurement stability analysis. Measured stability of the backscattering intensity over a three-month period was observed to be better than 0.5 dB, when measuring a target with a known radar cross section. Deviations of the estimated target range were in the order of a few cm over the same period, indicating also good stability of the measured phase. Interforometric SAR (InSAR) capabilities are also discussed, and as a example, the coherence of subsequent SAR acquisitions over the observed boreal forest stand are analyzed over increasing temporal baselines. The analysis shows good conservation of coherence in particular at L-band, while higher frequencies are susceptible to loss of coherence in particular for dense vegetation. The potential of the instrument for satellite calibration and validation activities is also discussed.

Optimal decision fusion using sparse representation‐based classifiers on monogenic‐signal dictionaries for SAR ATR

Sparse representation-based classification (SRC) possesses remarkable characteristics for application in synthetic aperture radar (SAR) automatic target recognition (ATR), for instance, inherent feature extraction and robustness to articulation, and so on. However, the performance of SRC is highly sensitive to parameters such as sufficient training samples, SAR images quality, and targets’ changing conditions in depression, pose, configuration, and so on. Unfortunately, the training sample resources for SAR ATR are often expensive and scarce. Further, the targets in SAR images, even with slightest changes in conditions, display mutable characteristics attributable to unique SAR image formation, and speckle noise corruption. To overcome these obstacles, this Letter proposes to establish several compact and complementary dictionaries using monogenic signal's components of SAR images and Fisher discriminative dictionary learning. Then, an optimal decision fusion (ODF) strategy is proposed, which utilises SRC and the latter dictionaries for robust SAR ATR. Compared with single classifiers or multiple parallel classifiers, the proposed ODF increases the accuracy of recognition, while at the same time, decreases the complexity of the system. The proposed methods have considerable features making them applicable in practical situations. Based on the experimental results, the proposed methods outperform state-of-the-art approaches.

On Solving SAR Imaging Inverse Problems Using Nonconvex Regularization With a Cauchy-Based Penalty

Synthetic aperture radar (SAR) imagery can provide useful information in a multitude of applications, including climate change, environmental monitoring, meteorology, high dimensional mapping, ship monitoring, or planetary exploration. In this article, we investigate solutions for several inverse problems encountered in SAR imaging. We propose a convex proximal splitting method for the optimization of a cost function that includes a nonconvex Cauchy-based penalty. The convergence of the overall cost function optimization is ensured through careful selection of model parameters within a forward-backward (FB) algorithm. The performance of the proposed penalty function is evaluated by solving three standard SAR imaging inverse problems, including super-resolution, image formation, and despeckling, as well as ship wake detection for maritime applications. The proposed method is compared to several methods employing classical penalty functions such as total variation (TV) and L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> norms, and to the generalized minimax-concave (GMC) penalty. We show that the proposed Cauchy-based penalty function leads to better image reconstruction results when compared to the reference penalty functions for all SAR imaging inverse problems in this article.

An Accelerated Algorithm Based on GO-PO/PTD and CWMFSM for EM Scattering From the Ship Over a Sea Surface and SAR Image Formation

This article proposes an accelerated ray-tracing algorithm to improve the computational efficiency of composite scattering from the 3-D ship target located on a random sea surface. The ray tracing is accelerated by using a new neighbor search technique, with a new 0-1 transformation rule and arrangement of octree nodes. It can reduce the code complexity and improve the computational efficiency. Combined with this technique, an accelerated algorithm based on the geometrical optics, physical optics with physical theory of diffraction (GO-PO/PTD) and capillary wave modification facet scattering model (CWMFSM) is further established. This is meaningful for the simulation of scattered echoes for wideband synthetic aperture radar (SAR), enabling SAR images to be formed using an imaging algorithm. The effectiveness of the proposed method was verified by comparing the simulation results with those produced by the FEKO-based multilevel fast multipole method (MLFMM). Further confirmation of its accuracy was obtained by comparing the simulated images with the measured ship image.

Localising vibrating scatterer phenomena in synthetic aperture radar imagery

Artefact phenomena resulting from synthetic aperture radar (SAR) image formation can pose a challenge for image interpretation. One such artefact is produced when a vibrating target is imaged. Suppression of these artefacts has previously been described, however little has been developed in the area of modelling the location and shape of such artefacts. The authors present an experimentally validated model that provides accurate location and shape of vibrating target paired echoes in both SAR near-field and SAR far-field imagery.