The domain adaptation of satellite images has recently gained increasing attention to overcome the limited generalization abilities of machine learning models when segmenting large-scale satellite images. Most of the existing approaches seek for adapting the model from one domain to another. However, such single-source and single-target setting prevents the methods from being scalable solutions since, nowadays, multiple sources and target domains having different data distributions are usually available. Besides, the continuous proliferation of satellite images necessitates the classifiers to adapt to continuously increasing data. We propose a novel approach, coined DAugNet, for unsupervised, multisource, multitarget, and life-long domain adaptation of satellite images. It consists of a classifier and a data augmentor. The data augmentor, which is a shallow network, is able to perform style transfer between multiple satellite images in an unsupervised manner, even when new data are added over time. In each training iteration, it provides the classifier with diversified data, which makes the classifier robust to large data distribution difference between the domains. Our extensive experiments prove that DAugNet significantly better generalizes to new geographic locations than the existing approaches.
Satellite images from the same scene observed over time can be composed in an image stack, which could be modeled as a 3-D cube. To handle this type of remote sensing data, on the one side, unidimensional dynamical models have been considered, modeling each pixel separately along the time (pixel-based approach), and exploring the temporal correlation. On the other side, 2-D approaches have been considered to process each image at one date, exploring the spatial correlation. In this article, we propose a new 3-D autoregressive (AR) (3-D-AR) model useful for multitemporal image interpretation exploring the correlation in three dimensions altogether. The 3-D-AR model is statistically defined, and a robust parameter estimation method is discussed. The tools for filtering, forecasting, and detecting anomalies are also introduced. A Monte Carlo simulation study is performed to evaluate the finite signal length performance of the robust estimation and its sensitivity to outliers. The proposed model is applied to a multitemporal normalized difference vegetation index (NDVI) image stack for filtering, prediction, and anomaly detection purposes. The numerical results show the importance of the proposed 3-D-AR model for spatiotemporal remote sensing data interpretation.
In distributed passive radar, optimization of the receiver placement attracts much attention recently to improve the performance. Whereas most research optimizes receiver placement for best coverage or localization performance, the effect of one performance optimization on the other is ignored. In this article, the theoretical analysis on the conflict between the coverage and localization performance optimization is presented. Then, a joint coverage and localization-based receiver placement optimization is formulated, in which the detection probability and the localization accuracy are chosen as the corresponding metrics. To solve this optimization problem, a multiobjective neighborhood search algorithm with multineighborhood structure is proposed, by which a set of Pareto solutions corresponding to the optimal receiver placements is obtained. Compared with the traditional neighborhood search algorithms, the proposed algorithm is able to provide better receiver placements approaching the global Pareto optimum, which is validated by the simulations.
VIPR (vapor in-cloud profiling radar) is a tunable G-band radar designed for humidity and cloud remote sensing. VIPR uses all-solid-state components and operates in a frequency-modulated continuous-wave (FMCW) radar mode, offering a transmit power of 200–300 mW. Its typical chirp bandwidth of 10 MHz over a center-frequency tuning span of 167–174.8 GHz results in a nominal range resolution of 15 m. The radar’s measured noise figure over the transmit band is between 7.4 and 10.4 dB, depending on its frequency and hardware configuration, and its calculated antenna gain is 58 dB. These parameters mean that with typical 1 ms chirp times, single-pulse cloud reflectivities as low as −26 dBZ are detectable with unity signal-to-noise at 5 km. Experimentally, radar returns from ice clouds above 10 km in height have been observed from the ground. VIPR’s absolute sensitivity was validated using a spherical metal target in the radar antenna’s far-field, and a G-band switch has been implemented in an RF calibration loop for periodic recalibration. The radar achieves high sensitivity with thermal noise limited detection both by virtue of its low-noise RF architecture and by using a quasioptical duplexing method that preserves ultrahigh transmit/receive isolation despite operation in an FMCW mode with a single primary antenna shared by the transmitter and receiver.
Through-the-wall radar imaging is a sensing technology that can be used by first responders to see through obscure barriers during search-and-rescue missions or deployed by law enforcement and military personnel to maintain situational awareness during tactical operations. However, the strong reflections from the front wall and other obstacles render the detection of stationary targets very difficult. In this article, a learning-based approach is proposed to mitigate the effect of the wall and background clutter. A sparse autoencoder with a low-rank projection is developed to mitigate the wall clutter and recover the target signal. The weights of the proposed autoencoder are determined by solving an augmented Lagrange multiplier optimization problem, and the regularization parameters are estimated using the Bayesian optimization technique. Experiments using real data from a stepped-frequency radar were conducted to illustrate its effectiveness for wall clutter removal. The results show that the proposed method achieves superior performance compared with the existing approaches.
Multistatic radar is a promising option for the low-cost collection of multiple-Doppler weather observations. However, due to the use of low-directivity antennas at the receivers in these systems, they typically suffer from extremely high two-way sidelobe levels compared to monostatic radars. Doppler velocity estimation biases induced by sidelobe contamination have proved to be a significant obstacle to more widespread adoption of this technology. It has been noted in the existing literature that the technique of sidelobe whitening, first developed for use in monostatic systems, has the potential to mitigate this issue. However, the existing sidelobe whitening algorithm is not suitable for use in this application, as it is only capable of achieving whitening in the two-way antenna pattern, whereas an algorithm to be used in the multistatic case must be able to achieve this result in the transmit pattern alone. This article proposes an alternate sidelobe whitening technique based on the method of alternating projections which allows for effective whitening in the one-way antenna pattern. A multistatic weather radar time-series simulator is used in conjunction with numerical weather prediction data to demonstrate the effectiveness of this method in mitigating multiple-Doppler measurement biases.
A frequency-modulated continuous-wave (FMCW) radar, operated at the central frequency of 27.75 MHz and the bandwidth of 300 kHz has been established on the seashore near the Taichung harbor ( $24^{circ } 18.591^prime $ N, $120^{circ } 31.389^prime $ E), Taiwan. Sixteen vertical dipole antennas were located linearly and attached with 16 receiving channels. One purpose of the radar is to monitor the ships that navigate toward, away, and around the harbor. In this article, we applied the radar beamforming methods that transform the temporal radar signals as brightness on the 2-D range-azimuthal domain, making the ship echoes visible directly on the spatial domain. Three beamformers, linear Fourier, directionally constrained minimum power (DCMP), and norm-constrained DCMP (NC-DCMP) algorithms, were employed to produce range–angle (RA) brightness distribution that is different from the conventionally used range–Doppler (RD) spectra in ship detection. Both DCMP and NC-DCMP are adaptive beamforming methods. With the auxiliary of a band-stop filter to suppress the sea echoes, the NC-DCMP beamformer was demonstrated to surpass the other two beamformers and could provide more visible ship echoes in the RA brightness distribution. Automatic Identification System (AIS) information was also used to validate the radar-determined ship locations from the RA brightness distribution. Although some ships having the AIS information were not observed clearly by the radar, the radar detected some targets without AIS information.
This article shows how the array of corner reflectors (CRs) in Queensland, Australia, together with highly accurate geodetic synthetic aperture radar (SAR) techniques—also called imaging geodesy—can be used to measure the absolute and relative geometric fidelity of SAR missions. We describe, in detail, the end-to-end methodology and apply it to TerraSAR-X Stripmap (SM) and ScanSAR (SC) data and to Sentinel-1 interferometric wide swath (IW) data. Geometric distortions within images that are caused by commonly used SAR processor approximations are explained, and we show how to correct them during postprocessing. Our results, supported by the analysis of 140 images across the different SAR modes and using the 40 reflectors of the array, confirm our methodology and achieve the limits predicted by theory for both Sentinel-1 and TerraSAR-X. After our corrections, the Sentinel-1 residual errors are 6 cm in range and 26 cm in azimuth, including all error sources. The findings are confirmed by the mutual independent processing carried out at University of Zurich (UZH) and German Aerospace Center (DLR). This represents an improvement of the geolocation accuracy by approximately a factor of four in range and a factor of two in azimuth compared with the standard Sentinel-1 products. The TerraSAR-X results are even better. The achieved geolocation accuracy now approaches that of the global navigation satellite system (GNSS)-based survey of the CRs positions, which highlights the potential of the end-to-end SAR methodology for imaging geodesy.
Video synthetic-aperture radar (ViSAR) can obtain high-resolution images of a region of interest at a high frame rate. This feature of ViSAR is helpful for real-time detection and tracking of moving targets. Moving-target tracking using ViSAR images is a typical dim-target-tracking problem. In the context of this article, dim targets correspond to the shadows of the moving vehicles cast onto the stationary background scene, which appear at lower gray levels compared with the background clutter. To detect and track multiple slowly maneuvering targets in the ViSAR imagery, we propose a novel algorithm, the expanding and shrinking strategy-based particle filter/dynamic programming-based track-before-detect (ES-TBD) algorithm. To the best of our knowledge, our work represents the first algorithm to deal with the ViSAR-detection and tracking problem using the TBD method. Furthermore, to detect and track a time-varying number of targets, we also propose a novel region-partitioning-based ES-TBD (RP-TBD) algorithm. By exploiting the common information shared between the batches of measurement data and the modeling merit-function-integrated particle filters (PFs), the RP-TBD partitions the observation region into a predicted subregion and an innovative subregion. The RP-TBD algorithm detects newborn targets in the innovative subregion, while maintains tracks of known targets in the predicted subregion. Experimental results using real ViSAR images show that the proposed algorithms outperform the state-of-the-art algorithms on detecting and tracking multiple dim targets in terms of location accuracy and false-alarm suppression.
Synthetic aperture radar (SAR) image classification is a fundamental research direction in image interpretation. With the development of various intelligent technologies, deep learning techniques are gradually being applied to SAR image classification. In this study, a new SAR classification algorithm known as the multiscale convolutional neural network with an autoencoder regularization joint contextual attention network (MCAR-CAN) is proposed. The MCAR-CAN has two branches: the autoencoder regularization branch and the context attention branch. First, autoencoder regularization is used for the reconstruction of the input to regularize the classification in the autoencoder regularization branch. Multiscale input and an asymmetric structure of the autoencoder branch cause the network more to be focused on classification than on reconstruction. Second, the attention mechanism is used to produce an attention map in which each attention weight corresponds to a context correlation in attention branch. The robust features are obtained by the attention mechanism. Finally, the features obtained by the two branches are spliced for classification. In addition, a new training strategy and a postprocessing method are designed to further improve the classification accuracy. Experiments performed on the data from three SAR images demonstrated the effectiveness and robustness of the proposed algorithm.
Geosynchronous spaceborne–airborne bistatic synthetic aperture radar (GEO-SA-BiSAR) can achieve high-resolution Earth observation with superior system flexibility and efficiency, which offers huge potential for advanced SAR applications. In this article, the echo characteristics of GEO-SA-BiSAR are analyzed in detail, including range history, the Doppler parameters, and spatial variance. The distinct features of GEO-SAR and airborne receiver result in the failure of the traditional bistatic SAR range model and imaging methods. In order to deal with these problems and achieve high-precision data focusing on GEO-SA-BiSAR, this article first proposes a novel range model based on one-stationary equivalence (RMOSE) to accommodate the distinctiveness of the GEO-SA-BiSAR echo, which changes with orbit positions of GEO transmitter. Then, a 2-D frequency-domain imaging algorithm is put forward based on RMOSE, which solves the problem of the 2-D spatial variance of GEO-SA-BiSAR. Finally, simulations are presented to demonstrate the effectiveness of the proposed range model and algorithm.
Speckle noise inherent in synthetic aperture radar (SAR) images seriously affects the visual effect and brings great difficulties to the postprocessing of the SAR image. Due to the edge-preserving feature, total variation (TV) regularization-based techniques have been extensively utilized to reduce the speckle. However, the strong scatters in SAR image with radiometry several orders of magnitude larger than their surrounding regions limit the effectiveness of TV regularization. Meanwhile, the ${ell _{1}}$ -norm first-order TV regularization sometimes causes staircase artifacts as it favors solutions that are piecewise constant, and it usually underestimates high-amplitude components of image gradient as the ${ell _{1}}$ -norm uniformly penalizes the amplitude. To overcome these shortcomings, a new hybrid variation model, called Fisher–Tippett (FT) distribution- ${ell _{p}}$ -norm first-and second-order hybrid TVs (HTpVs), is proposed to reduce the speckle after removing the strong scatters. Especially, the FT-HTpV inherits the advantages of the distribution based data fidelity term, the nonconvex regularization, and the higher order TV regularization. Therefore, it can effectively remove the speckle while preserving point scatters and edges and reducing staircase artifacts well. To efficiently solve the nonconvex minimization problem, an iterative framework with a nonmonotone-accelerated proximal gradient (nmAPG) method and a matrix-vector acceleration strategy are used. Extensive experiments on both the simulated and real SAR images demonstrate the effectiveness of the proposed method.
Although numerous methods based on sequence image classification have improved the accuracy of synthetic-aperture radar (SAR) automatic target recognition, most of them only concentrate on the fusion of spatial features of multiple images and fail to fully utilize the temporal-varying features. In order to exploit the spatial and temporal features contained in the SAR image sequence simultaneously, this article proposes a sequence SAR target classification method based on the spatial–temporal ensemble convolutional network (STEC-Net). In the STEC-Net, the dilated 3-D convolution is first applied to extract the spatial–temporal features. Then, the features are gradually integrated hierarchically from local to global and represented as the united tensors. Finally, a compact connection is applied to obtain a lightweight classification network. Compared with the available methods, the STEC-Net achieves a higher accuracy (99.93%) in the moving and stationary target acquisition and recognition (MSTAR) data set and exhibits robustness to depression angle, configuration, and version variants.
Phase decorrelation, as one of the main error sources, limits the capability of interferometric synthetic aperture radar (InSAR) for deformation mapping over areas with low coherence. Although several methods have been realized to reduce decorrelation noise, for example, by phase linking and spatial and temporal filters, their performances deteriorate when coherence estimation bias exists. We present an arc-based approach that allows reconstructing unwrapped interval phase time-series based on iterative weighted least squares (WLS) in temporal and spatial domains. The main features of the method are that phase optimization and unwrapping can be jointly conducted by spatial and temporal iterative WLS and coherence matrix bias has negligible effects on the estimation. In addition, the linear formation makes the implementation suitable with small subset of interferograms, providing an efficient solution for future big SAR data. We demonstrate the effectiveness of the proposed method using simulated and real data with different decorrelation mechanisms and compare our approach with the state-of-art phase reconstruction methods. Substantial improvement can be achieved in terms of reduced root-mean-square error (RMSE) in the simulation data and increased density of coherent measurements in the real data.
We address the problem of high-resolution radar imaging in low signal-to-noise ratio (SNR) environments in an approximate Bayesian inference framework. First, the probabilistic graphical model is constructed by imposing the sparsity-promoting spike-and-slab prior to the distribution of scattering centers. Then, the model parameters and phase errors are estimated iteratively by expectation propagation (EP) and maximum likelihood (ML) estimation. Compared with the available imaging methods based on the numerical optimization and Bayesian inference, the proposed method has exhibited more flexibility in data representation and better performance in parameter estimation, particularly in sparse-aperture and low SNR scenarios.
This article investigates the presence of a new interferometric signal in multilooked synthetic aperture radar (SAR) interferograms that cannot be attributed to the atmospheric or Earth-surface topography changes. The observed signal is short-lived and decays with the temporal baseline; however, it is distinct from the stochastic noise attributed to temporal decorrelation. The presence of such a fading signal introduces a systematic phase component, particularly in short temporal baseline interferograms. If unattended, it biases the estimation of Earth surface deformation from SAR time series. Here, the contribution of the mentioned phase component is quantitatively assessed. The biasing impact on the deformation-signal retrieval is further evaluated. A quality measure is introduced to allow the prediction of the associated error with the fading signals. Moreover, a practical solution for the mitigation of this physical signal is discussed; special attention is paid to the efficient processing of Big Data from modern SAR missions such as Sentinel-1 and NISAR. Adopting the proposed solution, the deformation bias is shown to decrease significantly. Based on these analyses, we put forward our recommendations for efficient and accurate deformation-signal retrieval from large stacks of multilooked interferograms.
The performance of synthetic aperture radar is vulnerable to radio frequency interference (RFI). In many situations, the RFI has a low-rank property, since the frequency bands occupied by RFI usually remain stable during a short slow time period. Therefore, low-rank representation (LRR)-based methods can be applied to separate RFI and signal of interest (SOI), by minimizing the rank of RFI components with a regularization constraint to protect SOI. However, traditional methods use the sparsity of the raw data or range profile to formulate the regularization term, which fails to describe the properties of SOI accurately. In addition to the sparse property of range profiles, this article explores the common patterns hidden in the range profiles and proposes two new LRR-based RFI suppression optimization models with a well-designed regularization term to describe such common sparsity to protect the SOI. Four methods are proposed to solve the optimization problems based on the alternating direction multiplier (ADM) method, which provides tradeoff between efficiency and accuracy. Compared with traditional LRR-based RFI suppression methods, the proposed methods make a more precise description of the features of SOI, therefore can better protect the information of SOI during the RFI suppression process and improves the imaging quality. The superior performance of the proposed method is validated by measured data in both sparse and nonsparse scenes.
The azimuth phase coding (APC) technique is known for its very low implementation complexity and its effectiveness for point and distributed ambiguities in conventional synthetic aperture radar (SAR) systems. In recent years, as an extension, the APC technique has been briefly discussed for multichannel SAR systems. However, the properties of the APC technique are no longer guaranteed in the multichannel SAR systems based on the digital beamforming (DBF) on-receive, and only a slight APC gain in the suppression of the range ambiguity can be obtained. In this article, we first provide a more thorough analysis for an APC-multichannel SAR system with respect to a uniform pulse-repetition frequency (PRF). Then, the APC/multichannel SAR system with nonuniform spatial sampling is briefly discussed, and an improved reconstruction approach based on a quadratically constrained optimization model is proposed to increase greatly the APC gain with respect to existing multichannel reconstruction algorithms. This proposed approach allows the minimization of the range ambiguity with a given azimuth-ambiguity constraint. In particular, for some specific PRFs, the proposed method permits a cancellation of the odd-order range ambiguity. Finally, simulation experiments are performed to verify the advantages and effectiveness of the proposed approach.
Recently, deep-learning methods have been successfully applied to the ship detection in the synthetic aperture radar (SAR) images. It is still a great challenge to detect multiscale SAR ships due to the broad diversity of the scales and the strong interference of the inshore background. Most prevalent approaches are based on the anchor mechanism that uses the predefined anchors to search the possible regions containing objects. However, the anchor settings have a great impact on their detection performance as well as the generalization ability. Furthermore, considering the sparsity of the ships, most anchors are redundant and will lead to the computation increase. In this article, a novel detection method named feature balancing and refinement network (FBR-Net) is proposed. First, our method eliminates the effect of anchors by adopting a general anchor-free strategy that directly learns the encoded bounding boxes. Second, we leverage the proposed attention-guided balanced pyramid to balance semantically the multiple features across different levels. It can help the detector learn more information about the small-scale ships in complex scenes. Third, considering the SAR imaging mechanism, the interference near the ship boundary with the similar scattering power probably affects the localization accuracy because of feature misalignment. To tackle the localization issue, a feature-refinement module is proposed to refine the object features and guide the semantic enhancement. Finally, extensive experiments are conducted to show the effectiveness of our FBR-Net compared with the general anchor-free baseline. The detection results on the SAR ship detection dataset (SSDD) and AIR-SARShip-1.0 dataset illustrate that our method achieves the state-of-the-art performance.
Calibration of satellite-borne radiometer is a key issue for quantitative remote sensing. Its accuracy depends on the stability of the calibration source. Because of no atmosphere and biological activity, the Moon surface keeps stable in the long term and may be a good candidate for thermal calibration. Observation of microwave humidity sounder (MHS) onboard the NOAA-18 made measurements of the disk-integrated brightness temperature (TB) of the Moon for the phase angle between -800 and 500. The measurement of NOAA-18 has been studied to validate the TB model of lunar surface. In this article, the near side of the Moon surface is divided into 900 subregions with a span of 60 x 60 in longitude and latitude. By solving 1-D heat conductive equation with the thermophysical parameters validated by the Diviner data of the Lunar Reconnaissance Orbiter (LRO), the temperature profiles of the regolith media in all 900 subregions are obtained. The loss tangents are inversed from the Chang'e-2 (CE-2) 37-GHz microwave TB data at noontime. Employing the fluctuation-dissipation theorem and the Wentzel-Kramer-Brillouin (WKB) approach, the microwave and millimeter-wave TBs of each subregion are simulated. Then, the weighted average TB can be disk-integrated from 900 TBs of all subregions versus the phase angle. These simulations well demonstrate diurnal TB variation and its dependence upon the frequency channels. It is found that the disk-integrated TB of the Moon in MHS channels is sensitive to the full-width at half-maximum (FWHM) of the deep space view (DSV), which is corrected in our simulation, where the Moon is now taken as an extended target, instead of a point-like object. Simulated integrated TBs are compared with the corrected MHS TB data at 89, 157, and 183 GHz. The simulated TB is well consistent with these MHS TB data at 89 and 183 GHz at various phase angles. But the maximum TB of MHS data at 157 GHz is unusually lower than that of 89 GHz. The influence of the loss ta-
gent, emissivity, and the pointing error is analyzed. Some more careful design to observe the Moon TB and technical parameters, especially the FWHM should be well determined. Our model and numerical simulation provides a tool for TB calibration and validation.
