Real SAR Data Research Articles

Ensemble One-Class Support Vector Machine for Sea Surface Target Detection Based on k-Means Clustering

Sea surface target detection is a key stage in a typical target detection system and directly influences the performance of the whole system. As an effective discriminator, the one-class support vector machine (OCSVM) has been widely used in target detection. In OCSCM, training samples are first mapped to the hypersphere in the kernel space with the Gaussian kernel function, and then, a linear classification hyperplane is constructed in each cluster to separate target samples from other classes of samples. However, when the distribution of the original data is complex, the transformed data in the kernel space may be nonlinearly separable. In this situation, OCSVM cannot classify the data correctly, because only a linear hyperplane is constructed in the kernel space. To solve this problem, a novel one-class classification algorithm, referred to as ensemble one-class support vector machine (En-OCSVM), is proposed in this paper. En-OCSVM is a hybrid model based on k-means clustering and OCSVM. In En-OCSVM, training samples are clustered in the kernel space with the k-means clustering algorithm, while a linear decision hyperplane is constructed in each cluster. With the combination of multiple linear classification hyperplanes, a complex nonlinear classification boundary can be achieved in the kernel space. Moreover, the joint optimization of the k-means clustering model and OCSVM model is realized in the proposed method, which ensures the linear separability of each cluster. The experimental results based on the synthetic dataset, benchmark datasets, IPIX datasets, and SAR real data demonstrate the better performance of our method over other related methods.

Compensation of Background Ionospheric Effect on L-Band Geosynchronous SAR with Fully Polarimetric Data

The L-band geosynchronous synthetic aperture radar (GEO-SAR) has been widely praised for its advantages of short revisit time, wide coverage and stable backscattering information acquisition. However, due to the ultra-long integrated time, the echo will be affected by the time-variant background ionosphere, leading in particular to defocusing in the azimuth direction. Existing compensation methods suitable for low Earth orbit SAR (LEO-SAR) are based on the SAR image or the semi-focused image at the ionospheric phase screen, assuming that the ionosphere is time-frozen for a short integrated period; thus, accurate reconstruction of the time-variant characteristics for the ionosphere in GEO-SAR cannot be achieved. In this paper, a compensation method of background ionospheric effects on L-band GEO-SAR with fully polarimetric data is proposed. Considering the continuous variation of the ionosphere within the synthetic aperture, a decompression processing is proposed to reconstruct the echo by recovering the temporal sampling according to the imaging geometry. By virtue of the Faraday rotation angle, the time-variant total electron content (TEC) is accurately estimated with the reconstructed echo. Based on the established error model, the ionospheric effects are well compensated with the estimated TEC. Simulations with the real SAR data from ALOS-2 and the measured time-variant TEC from USTEC validate the effectiveness and performance of the proposed method. The impacts from thermal noise and polarimetric calibration error are also quantitatively analyzed. From this, the error thresholds are given to guarantee compensation accuracy, namely 18.96 dB for SNR, −15.63 dB for crosstalk and −1.02 dB to 0.31 dB for the amplitude of the channel imbalance, and the argument of the channel imbalance is suggested to be maintained as close to zero as possible.

Moving Targets Artifacts Removal in Multiaspect SAR Imagery Based on Logarithm Background Subtraction

Multiaspect SAR has the capability of providing a high-resolution image due to its long synthetic aperture feature. However, a moving target can generate long and complex signatures in a multiaspect SAR image, which may hamper the applications like image interpretation and target detection. In this article, two methods are proposed to remove the moving target signature in a single-channel multiaspect SAR image. The two methods are all based on logarithm background subtraction. The first one is a fast scheme with a cost of reduced resolution. While the second one focuses on preserving the high resolution, it takes more time than the previous one. The first method utilizes the fact of target signal position changes in subaperture image sequence to obtain the static background. The second method combines the detection results to exclude the moving target signal in each complex-valued subaperture image, then obtaining the high resolution of static background by coherent summation. The methods are validated by synthetic and real airborne SAR data.

Despeckling Multitemporal Polarimetric SAR Data Based on Tensor Decomposition

Despeckling is an essential task in polarimetric synthetic aperture radar (PolSAR) image processing. Most existing filters developed for multi-temporal SAR images make use of either real or complex information. Real information refers to amplitude or intensity values, whereas complex information refers to complex covariance matrix (CCM) derived from either interferometric SAR (InSAR) or PolSAR data. The InSAR CCM is formed using images of the same polarimetric channel but acquired at different dates, and the PolSAR CCM contains information acquired simultaneously in different polarimetric channels. Therefore, these despeckling methods may present a good performance in some applications and scenes but fail in other cases, due to differences in input sources. In order to achieve a more robust result in all cases, we develop a method for multi-temporal polarimetric SAR data filtering based on tensor decomposition (TD-MPF), which aims at improving the identification of homogeneous pixels for spatially adaptive filtering. The key element of this approach consists of exploiting tensor theory to construct a new CCM that contains both polarimetric and interferometric information, as well as multi-temporal information for each pixel. The effectiveness of the proposed method and its performance are evaluated with simulated and real SAR data in comparison with several established methods.

A Novel Lightweight Attention-Discarding Transformer for High-Resolution SAR Image Classification

Vision Transformer (ViT) has been introduced in high-resolution synthetic aperture radar (HR SAR) image classification due to its excellent global feature extraction ability. However, small samples of SAR images make it difficult to fit the ViT with excessive trainable parameters, which easily results in over-fitting in training. Meanwhile, poor capability in capturing local features of ViT limits its accuracy in SAR image classification. To solve these problems, this letter proposes a new Lightweight Attention-Discarding Transformer (LAD Transformer) for the classification of HR SAR images. In the proposed model, the backbone of the advanced Swin transformer is used to model global information and extract hierarchical features. Moreover, the vital feature extraction part of the LAD Transformer completely discards the self-attention mechanism and extracts local features of SAR images by introducing lighter group convolution and channel shuffle (GC-CS Block). In addition, to address the estimation shift caused by consecutive batch normalization (BN) layers, a new composite normalization method consisting of Batch normalization and Layer Normalization (BLN) in GC-CS Block is proposed. The experiments show that the proposed network has fewer parameters and higher classification accuracy on two real HR SAR data.

Super-Resolution of Synthetic Aperture Radar Complex Data by Deep-Learning

One of the greatest limitations of Synthetic Aperture Radar imagery is the capability to obtain an arbitrarily high spatial resolution. Indeed, despite optical sensors, this capability is not just limited by the sensor technology. Instead, improving the SAR spatial resolution requires large transmitted bandwidth and relatively long synthetic apertures that for regulatory and practical reasons are impossible to be met. This issue gets particularly relevant when dealing with Stripmap mode acquisitions and with relatively low carrier frequency sensors (where relatively large bandwidth signals are more difficult to be transmitted). To overcome this limitation, in this paper a deep learning based framework is proposed to enhance the spatial resolution of low-resolution SAR images while retaining the complex image accuracy. Results on simulated and real SAR data demonstrate the effectiveness of the proposed framework.

Phase Estimation for Distributed Scatterers by Alternating Projection

Decorrelation is a major obstacle to the application of multitemporal interferometric synthetic aperture radar (InSAR) in areas with low coherence. Distributed scatterers (DSs) with similar backscattering in the spatial neighborhood are the key to improving the observational density and accuracy of deformation estimation in fast decorrelation regions. Phase series estimation from all possible interferograms is expected to improve the signal-to-noise ratio (SNR) and further enhance the sensitivity of deformation measurement. The coherence bias and the efficiency of the phase estimation raise concerns. In this article, we propose a computationally attractive algorithm for the interferometric phase estimation, namely alternating projection (AP), which is a combination of the alternating maximization and the projection matrix decomposition methods. The homogenous pixel selection and coherence estimation bias correction are conducted by the FaSHPS algorithm and DSIpro software toolbox. Results of simulations and real SAR data show that the proposed AP method could reconstruct credible phase series comparable to the quasi-Newton optimization algorithm [Broyden–Fletcher–Goldfarb–Shanno (BFGS)] while having three times the efficiency gain.

Error analysis and 3D reconstruction using airborne array InSAR images

Multi-temporal synthetic aperture radar interferometry (MT-InSAR) is able to detect surface deformation and reconstruct a 3D surface model with high precision but requires a long observation period to accumulate the multi-baseline SAR images. The airborne array InSAR system is able to acquire a stack of multi-baseline SAR images in a single acquisition, which significantly improves the 3D modeling capability. However, processing the images obtained by the low-altitude platform using the conventional model will lead to geometric approximation (GA) errors, such as flattened phase error and reference error, which degrade the precision of the 3D reconstruction. In this paper, we quantitatively analyze the error sources of the array-InSAR interferograms and design a hybrid 3D phase unwrapping approach for 3D reconstruction. A hypothesis test is developed to identify the phase ambiguity by comparing the initial solution of the least-square with that of the beam-forming. Three indicators are proposed to identify the reliable arcs, achieving a reliable phase unwrapping. The L1 norm approach is adopted to detect the unwrapping errors during the spatial unwrapping and a two-tie network strategy is used to process the data in the individual blocks from the perspective of global optimization. Furthermore, an iterative scheme is recommended to compensate the geometric approximation errors. The main advantage of the proposed algorithm is the compensation of the GA error and reliable phase unwrapping. The experimental results by both simulated and real SAR data show that the proposed algorithm can eliminate the GA error and provide a viable solution to rapid 3D SAR imaging with an airborne platform.

On the Derivation of Volume Decorrelation From TanDEM-X Bistatic Coherence

The bistatic interferometric coherence is affected by different sources of error, among which volume decorrelation, which quantifies the amount of noise caused by volume scattering mechanisms. The magnitude of volume decorrelation can be derived from the total interferometric coherence by properly compensating for all other decorrelation sources. In the scientific community, it is common practice to approximate the volume decorrelation with the coherence or to compute it by compensating for the signal-to-noise ratio (SNR) decorrelation only, which typically represents the predominant decorrelation component. The aim of this work is to assess the impact of different decorrelation sources in detail and to provide the readers with a practical procedure for a precise computation of the volume decorrelation from TanDEM-X bistatic data. In particular, we concentrate on the two most relevant decorrelation components: the SNR and the quantization components. Regarding the former, we estimate the noise equivalent sigma nought directly from real SAR data and we provide the users with a set of polynomial coefficients for the retrieval of the system noise floor for each operational TanDEM-X StripMap beam used for the generation of the global Digital Elevation Model (DEM). Concerning the latter, we analyze its dependency on the backscatter local statistics and quantization rate and we provide the reader with a set of empirical look-up-tables (LUT) for quantifying its impact on the coherence. Finally, we provide reasonable assumptions for all other remaining decorrelation sources, discussing two application scenarios.

Coprime Sensing for Airborne Array Interferometric SAR Tomography

In airborne array interferometric SAR (Array-InSAR) tomography, the measurements acquired by conventional uniform sampling array are always restricted by the number of physical baseline elements and the size of baseline aperture. It is desirable to capture new acquisitions and enlarge the aperture with virtual signal processing instead of actually adding array baselines. For this motivation, we utilize the disparity of a pair of coprime sampling sub-arrays to enlarge the baseline aperture and construct new observations virtually. The generation of virtual measurements is equal to estimating cross-correlation matrices in real SAR data. Due to the spatial target variation, we adopted an adaptive filtering method to estimate the cross-correlation matrix. We call the above-mentioned processing of generating virtual measurements as a <i>coprime sensing technique</i>. The newly generated virtual measurements have more degrees of freedom, a larger baseline aperture, and a higher signal-to-noise ratio (SNR) than the physical measurements. These advantages offer the possibility to obtain competitive three-dimensional (3-D) imaging results without increasing the hardware cost of the Array-InSAR. We demonstrate the effectiveness of the proposed method by the coprime acquisitions selected from AIRCAS Array-InSAR data.

A Novel Channel Errors Calibration Algorithm for Multichannel High-Resolution and Wide-Swath SAR Imaging

For a spaceborne high-resolution and wide-swath synthetic aperture radar (HRWS-SAR) system, it usually uses the digital beamforming technology. However, in practice, because of the influences of temperature, antenna pattern, receiving antenna, and other error factors, there may exist the range synchronization time errors, amplitude errors, and phase errors among different spatial channels. These nonideal factors will significantly degrade the multichannel data reconstruction performance, resulting in a smeared SAR image. To address this issue, in this article we propose a novel channel error correction algorithm based on the orthogonal projection theory. First, the optimal weight of each Doppler ambiguity component is calculated by the orthogonal projection. Then, the cost function is constructed based on the power maximization criterion, from which the channel phase errors can be obtained. Finally, the HRWS-SAR imaging can be finely realized after performing the channel balancing. Compared with the conventional phase error estimation method, the proposed algorithm does not require to perform the matrix eigenvalue decomposition, avoiding the signal leakage phenomenon under low SNR case. The effectiveness of the proposed algorithm is validated by both airborne and space-borne real SAR data.

Phase unwrapping based on fusion of ant colony and genetic algorithms

Interferometric Synthetic Aperture Radar (InSAR) is a microwave imaging system with all-weather earth observation. Because of its wide observation area, high precision, day and night operational capabilities, it has a significant advantage in monitoring large-scale surface deformation. Phase unwrapping is a key step in InSAR data processing. The core of Goldstein traditional branch unwrapping method is the establishment of branch-cutting lines. The shorter the overall length of the branch line, the solution is more accurate. Based on the idea of solving the shortest path of Travelling Salesman Problem (TSP), a new algorithm combining ant colony algorithm and genetic algorithm is proposed. Based on the advantages of these two algorithms, we avoid the disadvantages of excessive parameters, slow calculation speed and low efficiency in ant colony algorithm, reduce the time consumed by ant colony algorithm in solving local optimal solution, improve the local search ability of ant colony algorithm, establish shorter branch line than traditional branch method, prevent islanding effect and improve the precision of phase unwrapping. The tests performed on real and simulated interferometric SAR data confirm the validity of the proposed method.

A Novel Algorithm Based on Compressive Sensing to Mitigate Phase Unwrapping Errors in Multitemporal DInSAR Approaches

In this work, we present a new method based on the compressive sensing (CS) theory to correct phase unwrapping (PhU) errors in the multitemporal sequence of interferograms exploited by advanced differential interferometric synthetic aperture radar (DInSAR) techniques to generate deformation time series. The developed algorithm estimates the PhU errors by using a modified L₁-norm estimator applied to the interferometric network built in the temporal/spatial baseline plane. Indeed, in order to search the minimum L₁-norm sparse solution, we apply the iterative reweighted least-squares method with an improved weight function that takes account of the baseline characteristics of the interferometric pairs. Moreover, we also introduce a quality function to identify those solutions that have no physical meaning. Although the proposed approach can be applied to different multitemporal DInSAR approaches, our analysis is tailored to the full-resolution small baseline subset (SBAS) processing chain that we properly modify to implement the proposed CS-based algorithm. To assess the performance of the developed technique, we carry out an extended experimental analysis based on simulated and real SAR data. In particular, we process two wide SAR datasets acquired by Sentinel-1 and COSMO-SkyMed constellations over central Italy between 2011 and 2019. The achieved experimental results clearly demonstrate the effectiveness of the developed approach in retrieving PhU errors and generating displacement time series related to strongly nonlinear deformation phenomena. Indeed, the developed CS-based technique significantly increases the number of detected coherent points and improves the accuracy of the retrieved deformation time series.

Adaptive Channel Balancing Algorithm Based on 2-D Gaussian Kernel Function

The inherent magnitude and phase errors between channels in the multichannel synthetic aperture radar/ground moving target indication (SAR/GMTI) system will affect the clutter suppression and moving target detection performance of the system. To solve this problem, this letter proposes an adaptive channel balancing algorithm based on the 2-D Gaussian kernel function. First, the iterative reweighted least squares (IRLS) algorithm is used to estimate and compensate the inherent linear phase error that varies with the Doppler frequency in the range-Doppler domain. Then the Gaussian statistical analysis of the residual phase errors is performed in the image domain after the azimuth processing. According to the coupling characteristics of the range and azimuth of the SAR image, the correlation coefficient and the standard deviations of the phase errors in the range and azimuth directions are computed, and a 2-D Gaussian kernel function is constructed to estimate and compensate the residual phase errors. Finally, a mean filter is used to compensate the 2-D magnitude errors. This algorithm can eliminate the magnitude and phase errors and improve the coherence between different channels. The real airborne SAR data demonstrate the effectiveness of the proposed algorithm.

Change Detection in Multilook Polarimetric SAR Imagery With Determinant Ratio Test Statistic

In this article, we propose a determinant ratio test (DRT) statistic to measure the similarity of two covariance matrices for unsupervised change detection in polarimetric radar images. The multilook complex covariance matrix is assumed to follow a scaled complex Wishart distribution. In doing so, we provide the distribution of the DRT statistic that is exactly Wilks’s lambda of the second kind distribution, with density expressed in terms of Meijer G-functions. Due to this distribution, the constant false alarm rate (CFAR) algorithm is derived in order to achieve the required performance. More specifically, a threshold is provided by the CFAR to apply to the DRT statistic producing a binary change map. Finally, simulated and real multilook polarimetric SAR (PolSAR) data are employed to assess the performance of the method and is compared with the Hotelling–Lawley trace (HLT) statistic and the likelihood ratio test (LRT) statistic.

A Novel Channel Phase Error Calibration Method Based on Hybrid AFSA-GSO-GA for Multichannel HRWS-SAR Imaging

The spaceborne high-resolution wide-swath synthetic aperture radar (HRWS-SAR) system generally does not meet the optimal SAR imaging configuration, and thus, it is necessary to apply digital beam-forming filtering technology to restore the nonuniformly sampled signal into the uniform grids. However, in practice, because of the influences of temperature, receiving machine, and other error factors, the channel errors may possibly exist, causing the SAR image to be smeared. To address this issue, this letter proposes a novel algorithm based on the hybrid artificial fish school algorithm–glowworm swarm optimization–genetic algorithm (AFSA-GSO-GA) to address the channel imbalance issue. First, coarse HRWS-SAR imaging processing is performed to obtain the positions of the Doppler ambiguity components. Then, according to the designed cost function, the hybrid AFSA-GSO-GA algorithm is used to realize the channel phase error estimation. Finally, a well-focused SAR image can be obtained after channel balance. The effectiveness of the proposed method is validated by both simulated and real SAR data.

Joint Down-Range and Cross-Range RFI Suppression in Ultra-Wideband SAR

Radio frequency interference (RFI) is a critical problem for ultra-wideband synthetic aperture radars (UWB SAR) because the VHF/UHF band used by them is shared by other systems as well. A number of solutions have been proposed over the years. Recently, sparsity and low-rank estimation-based solutions were shown to perform better than traditional methods such as adaptive notch filtering. These algorithms model the SAR signal to be sparse and the RFI to be either sparse or low-ranked in nature and solve an optimization problem to estimate the SAR signal and RFI simultaneously. Algorithms in this class share the common characteristic that the SAR signal sparsity is captured by modeling each data vector as a linear combination of shifted SAR pulses. This data model addresses the structure of SAR signals in the down-range direction, but the inter-aperture cross-range structure, i.e., the fact that SAR signals add coherently across the cross-range, has been completely ignored. In this work, we incorporate this “global” 2-D structure of the SAR data into the RFI mitigation problem. Two algorithms are proposed: 1) (2-D) sparse SAR and sparse RFI estimation and 2) (2-D) sparse SAR and low-rank RFI estimation. The experimental results demonstrate that the 2-D model does a much better job of capturing the sparsity of SAR and the 2-D algorithms consistently perform better than the “local” 1-D algorithms. The level of improvement rises significantly in challenging cases-when the noise level and/or the number of RFI bands increases. Experiments are conducted extensively on simulated data sets as well as real SAR and RFI data sets collected by the U.S. Army Research Laboratory (ARL) to validate the proposed framework.

The performance of LS and SVD methods for SBAS InSAR deformation model solutions

ABSTRACT For the small baseline subset (SBAS) interferometric synthetic aperture radar (InSAR) technique, the construction and subsequent robust solution of a deformation model is a key factor in obtaining monitored surface deformation results with high precision and high reliability. Here, the performance of the least squares (LS) and singular value decomposition (SVD) methods for the robust solution of SBAS InSAR deformation models are compared via tests with simulation and real SAR data. The LS method is used to solve the SBAS InSAR deformation models of 62 and 48 multi-temporal differential interferogram series; the SVD method is used to solve the SBAS InSAR deformation models of 60, 41, 58 and 53 multi-temporal differential interferogram series; the solved deformation results of the six series by the LS and SVD methods are compared and verified with the simulated deformation values and global positioning system (GPS) measurements. The results indicate that there is a moderate ill-posed degree in solving the SBAS InSAR deformation model by the LS method. The LS method can correctly retrieve the deformation information without considering any errors; however, in the case of serious random error, the deformation information acquired through the LS method is different from that of the simulation and is affected by the error of the multi-temporal differential interferometric phase series. The LS-solved results of real SAR datasets of two series are consistent, but are not in good agreement with the results of five GPS measurements. When the number of subsets is two, all types of deformation information solved by the SVD method follow the same rules as the results solved by the LS method. However, when the number of subsets increases to three and four, the stability of the SVD method becomes very poor; the SVD method can then only correctly solve the distribution of deformation in the study area, and the other solved deformation information, such as deformation velocity, is no longer credible.

Can InSAR Coherence and Closure Phase Be Used to Estimate Soil Moisture Changes?

We studied the influence of the statistical properties of soil moisture changes on the Interferometric Synthetic Aperture Radar (InSAR) coherence and closure phase to determine whether the InSAR coherence and closure phase can be used to estimate soil moisture changes. We generated semi-synthetic multi-looked interferograms by pairing n real single-looked pixels of an observed SAR image with n synthetic single-looked pixels. The synthetic SAR data are generated from the real SAR data by applying soil moisture changes with a pre-defined mean and standard deviation of changes. Our results show that the diversity of soil moisture changes within the multi-look window gives rise to decorrelation, a multi-looked phase artifact, and a non-zero phase triplet. The decorrelation and closure phase increase by enlarging the diversity of soil moisture changes. We also showed that non-soil moisture changes can lead to larger decorrelations and closure phases. Furthermore, the diversity of phase changes, decorrelation, and closure phases are correlated with land cover type. We concluded that the closure phase and coherence are independent of the magnitude of soil moisture changes and are inappropriate tools to estimate soil moisture changes. Coherence, however, can be used as a proxy for soil moisture changes if the diversity and magnitude of soil moisture changes within a multi-looked pixel are strongly correlated.

SAR Target Recognition Based on Probabilistic Meta-Learning

Numerous synthetic aperture radar-automatic target recognition (SAR-ATR) methods require a large amount of training data. However, collecting SAR data is both expensive and complicated in practical applications. Recognition with the limited training data has become a vital issue in SAR-ATR. To solve this problem, we propose a recognition model combining probabilistic inference with meta-learning to transfer prior knowledge from simulated to real SAR data. First, we use various recognition tasks drawn from the simulated data to learn the global parameters of the model. Second, we draw new tasks from the real data and use the amortized inference to model a posterior distribution over task-specific parameters. Finally, we produce a predictive distribution indicating the confidence of the target classes. The experimental results demonstrate the superiority of the model in recognition tasks with a small amount of training data. We also show that introducing probabilistic inference can improve the prediction accuracy and prediction uncertainty of the model.