Relaxed generalized minimum-error thresholoding for unsupervised change detection from SAR amplitude images

Abundant datasets are critical to train models based on deep learning technologies for ship detection applications. Compared with optical images, ship detection based on synthetic aperture radar (SAR) (especially the high-Earth-orbit spaceborne SAR launched recently) lacks enough training samples. A novel cross-domain attention GAN (CDA-GAN) model is proposed for optical-to-SAR translation, which can generate high-quality SAR amplitude training samples of a target by optical image conversion. This high quality includes high geometry structure similarity of the target compared with the corresponding optical image and low background noise around the target. In the proposed model, the cross-domain attention mechanism and cross-domain multi-scale feature fusion are designed to improve the quality of samples for detection based on the generative adversarial network (GAN). Specifically, a cross-domain attention mechanism is designed to simultaneously emphasize discriminative features from optical images and SAR images at the same time. Moreover, a designed cross-domain multi-scale feature fusion module further emphasizes the geometric information and semantic information of the target in a feature graph from the perspective of global features. Finally, a reference loss is introduced in CDA-GAN to completely retain the extra features generated by the cross-domain attention mechanism and cross-domain multi-scale feature fusion module. Experimental results demonstrate that the training samples generated by the proposed CDA-GAN can obtain higher ship detection accuracy using real SAR data than the other state-of-the-art methods. The proposed method is generally available for different orbit SARs and can be extended to the high-Earth-orbit spaceborne SAR case.

A constant false alarm rate (CFAR) detecting method for ships in high-resolution dual-polarization synthetic aperture radar (SAR) amplitude images has been proposed in this paper. First, by the production of amplitude images from two polarimetric channels, a novel detector simply called the PMA detector has been constructed. We testified that the PMA detector could improve the signal-to-clutter ratio (SCR) and make the discrimination of a ship from clutter more easily. Second, the PMA detector’s statistical model has been described by the well-known distribution when facing complex sea background. The experiments performed on measured dual-polarization TerraSAR-X images demonstrate the good performance of the proposed CFAR detecting method.

This paper presents a modified version of the information-theoretic feature in [1] for change detection in multitemporal synthetic aperture radar (SAR) imagery. The proposed method is capable of capturing small-area structural changes between the two images, by maintaining at the same time the capability of rejecting statistical changes due to speckle patterns or co-registration inaccuracies. This improvement is obtained by bootstrapping the original procedure by means of an adaptive preliminary selection of potentially changed pixels driven by the logarithm of the pixel ratio. Experimental results have been carried out on true SAR images acquired by the COSMO-SkyMed constellation.

As an essential parameter in synthetic aperture radar (SAR) images, the equivalent number of looks (ENL) not only indicates the speckle noise level in multi-look SAR data but also can be used for evaluating the region homogeneity level. Currently, time-series polarimetric (interferometric) SAR (TSPol(In)SAR) data are increasingly abundant, but traditional equivalent number of looks (ENL) estimators only use polarimetric information from a mono-temporal observation and do not consider the temporal characteristics or interferometric coherence of ground targets. Therefore, this paper puts forward four novel ENL estimators to overcome the restrictions of inadequate observation information. Firstly, based on the traditional trace moment estimator for polarimetric SAR data (TM-PolSAR), we extend it to both PolInSAR and TSPolInSAR data and then propose both TM-PolInSAR and TM-TSPolInSAR estimators, respectively. Secondly, for both TSPolSAR and single-reference TSPolInSAR data, we estimate the ENL by stacking the trace moments (STM) of multitemporal coherency matrices, called STM-TSPolSAR and STM-TSPolInSAR estimators, respectively. Therefore, these proposed ENL estimators can effectively deal with most of the requirements of TSPol(In)SAR data types in practical applications, mainly including statistical distribution modeling and region homogeneity evaluation. The simulation and real experiments detailedly compare the proposed four ENL estimators to the classical TM-PolSAR estimator and quantitatively analyze the estimation performance. The proposed estimators have obtained the ENL with less bias and standard deviation than the traditional estimator, especially in case of small spatial samples coherency matrices. Additionally, these STM-TSPolSAR, STM-TSPolInSAR, and TM-TSPolInSAR estimators have provided more effective statistical characteristics with the increase of the time-series size. It has been demonstrated that the proposed STM-TSPolSAR estimator considers the time-varying polarimetric characteristics of the crop and detects many edges that the traditional estimator cannot discover, which means a superior capability of region homogeneity evaluation.

ABSTRACTThe speckle noise of synthetic aperture radar (SAR) images limits its application in change detection. Compared with improved ratio (IR) and log-ratio (LR) operators, the neighborhood-based ratio (NR) technique can restrain the influence of speckle noise and is more suitable for change detection in SAR images. However, we find three drawbacks of NR by analyzing this method carefully. To overcome these defects, we propose an improved neighborhood-based ratio (INR) approach for change detection in SAR images. INR restructures the NR operator to exploit the neighborhood information more reasonably and is expected to reduce the impact of speckle noise better. IR, LR, mean ratio operator, NR, and INR are tested on two data sets to compare their performances in change detection of SAR images. Experimental results show that the proposed method can obtain better difference image than other state-of-art methods and improve the accuracy of change detection in SAR images effectively.

In this paper, speckle removal from synthetic aperture radar (SAR) images using subspace-based technique is proposed. The fundamental principle is to decompose the vector space of the noisy image into signal-plus-noise subspace and the noise subspace. Noise reduction is achieved by removing the noise subspace and estimating the clean image from the remaining image subspace. Linear estimation of the clean image is performed by minimizing image distortion while maintaining the residual noise energy below some given threshold. Since the noise is considered to be additive with subspace technique, a homomorphic framework is used to convert the multiplicative speckle noise into additive. The performance of the proposed approach is tested with simulated images and with real SAR images, and compared with Lee filter. The results indicated significant improvements by the proposed technique in terms of structural similarity index measure (SSIM) and equivalent number of looks (ENL).

This work proposes new speckle reduction filters for multi-look, amplitude-detected Synthetic Aperture Radar (SAR) images based on the maximum a posteriori (MAP) approach and compares their performance. The new filters use an adaptive approach based on the one-dimensional k-means clustering algorithm over the variance ratio and also a region-growing procedure. The trade-off between the loss of radiometric resolution and edge preservation is evaluated in the filtered images. In order to obtain quantitative measures of the speckle reduction and of the edge blurring, we used some parameters such as the classical equivalent number of looks and the Hough transform. Experiments have been carried out with natural images corrupted with synthetic speckle noise following the Rayleigh and square root of gamma distributions and with real SAR images.

In this paper, we propose a synthetic aperture radar (SAR) image despeckling method based on patch ordering and transform-domain filtering. Logarithmic transformation with bias correction is applied to the original SAR image to transform the multiplicative noise model into the additive model. Then, we adopt a two-stage filtering strategy. The first stage is coarse filtering which can suppress speckle effectively. In this stage, we extract the sliding patches from the logarithmic SAR image, and order them in a smooth way by a simplified patch ordering algorithm specially for SAR images. The ordered patches are filtered by learned simultaneous sparse coding (SSC), a technology recently advanced in image processing. Then, the coarse filtering result is reconstructed from the filtered patches via inverse permutation and subimage averaging. The second stage is refined filtering which can eliminate small artifacts generated by the coarse filtering. In this stage, the sliding patches are extracted from the coarse filtering result and ordered in the same way. Then, we apply 2-D wavelet hard-thresholding to the ordered patches and reconstruct the refined filtering result. The final result is obtained by taking exponential transformation to the refined filtering result. An algorithm based on the proposed strategy is presented in detail and the parameters are selected for fast and effective realization. Experimental results with both simulated images and real SAR images demonstrate that the proposed method achieves state-of-the-art despeckling performance in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM) index, equivalent number of looks (ENLs), and ratio image.

Synthetic aperture radar (SAR) imaging is one of the radar NDE techniques used for remote sensing of civil infrastructures. SAR imaging has been used for remote detection of moisture content, chloride content, and steel rebar corrosion in concrete specimens. Parameters extracted from SAR images are used for condition assessment, including integrated SAR amplitude (Iint), average maximum SAR amplitude (Iavg), and critical contour area (Ac). The objective of this paper is to investigate the effects of moisture and chloride content on the interdependency of critical contour area with integrated SAR amplitude and average maximum SAR amplitude. Laboratory portland cement concrete panel specimens of different water-to-cement (w/c) ratios (0.4, 0.5, and 0.55) were manufactured and scanned inside an electromagnetic anechoic chamber during the drying process of the specimens. From our result, it was found that the interdependency of critical contour area with integrated SAR amplitude and average maximum SAR amplitude during moisture variation is different from the one during chloride variation for different w/c ratios.

This work aims to clarify the potential of incoherent and coherent change detection (CD) approaches for detecting and monitoring ground surface changes using sequences of synthetic aperture radar (SAR) images. Nowadays, the growing availability of remotely sensed data collected by the twin Sentinel-1A/B sensors of the European (EU) Copernicus constellation allows fast mapping of damage after a disastrous event using radar data. In this research, we address the role of SAR (amplitude) backscattered signal variations for CD analyses when a natural (e.g., a fire, a flash flood, etc.) or a human-induced (disastrous) event occurs. Then, we consider the additional pieces of information that can be recovered by comparing interferometric coherence maps related to couples of SAR images collected between a principal disastrous event date. This work is mainly concerned with investigating the capability of different coherent/incoherent change detection indices (CDIs) and their mutual interactions for the rapid mapping of “changed” areas. In this context, artificial intelligence (AI) algorithms have been demonstrated to be beneficial for handling the different information coming from coherent/incoherent CDIs in a unique corpus. Specifically, we used CDIs that synthetically describe ground surface changes associated with a disaster event (i.e., the pre-, cross-, and post-disaster phases), based on the generation of sigma nought and InSAR coherence maps. Then, we trained a random forest (RF) to produce CD maps and study the impact on the final binary decision (changed/unchanged) of the different layers representing the available synthetic CDIs. The proposed strategy was effective for quickly assessing damage using SAR data and can be applied in several contexts. Experiments were conducted to monitor wildfire’s effects in the 2021 summer season in Italy, considering two case studies in Sardinia and Sicily. Another experiment was also carried out on the coastal city of Houston, Texas, the US, which was affected by a large flood in 2017; thus, demonstrating the validity of the proposed integrated method for fast mapping of flooded zones using SAR data.

During forming synthetic aperture radar (SAR) image, the inherent speckle noise severely affects the application result of SAR images. To deal with this problem, based on the contour bougie morphology (CB morphology) and the generalized multiple structuring elements morphology, a novel series morphological filter was constructed to suppress the speckle noise in SAR images. Firstly, by use of the omnidirectional multiple structuring elements the generalized multi-scale morphology open-max filter was adopted to filter the noise at the cost of minimal loss of image geometrical details, and then a CB open and a CB close series filter were used to filter the remained speckle noise. Thus it can not only effectively suppress the speckle noise in images but also preserve more detailed information of the images. Lastly, the simulated SAR images and the actual SAR images are simulated, and the results prove that the algorithm presented in this paper can efficiently suppresses the speckle noise in SAR images.

One of the major factors plaguing the performance of synthetic aperture radar (SAR) imagery is the presence of signal-dependent speckle noise. Grainy in appearance, speckle noise is primarily due to the phase fluctuations of the electromagnetic return signals. Since inherent spatial-correlation characteristics of speckle in SAR images are not exploited in existing multiplicative models for speckle noise, a new approach is proposed here that provides a new mathematical framework for modeling and reduction of speckle noise. The contribution of this paper is twofold. First, a novel model for speckled SAR imagery is introduced based on Markov random fields (MRFs) in conjunction with statistical optics. Second, utilizing the model, a global energy-minimization algorithm, based on simulated annealing (SA), is introduced for speckle reduction. In particular, the joint conditional probability density function (cpdf) of the intensity of any two points in the speckled image and the associated correlation function are used to derive the cpdf of any center pixel intensity given its four neighbors. The Hammersley- Clifford theorem is then used to derive the energy function associated with the MRF. The SA, built on the Metropolis sampler, is employed for speckle reduction. Four metrics are used to assess the quality of the speckle reduction: the mean-square error, SNR, an edge-preservation parameter and the equivalent number of looks. A comparative study using both simulated speckled images as well as real SAR images indicates that the proposed approach performs favorably in comparison to existing filtering techniques such as the modified-Lee and the enhanced Frost-algorithms.

The statistical properties of Synthetic Aperture Radar (SAR) image texture reveal useful target characteristics. It is well-known that these images are affected by speckle and prone to extreme values due to double bounce and corner reflectors. The G <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</sub> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sup> distribution is flexible enough to model different degrees of texture in speckled data. It is indexed by three parameters: α, related to the texture, γ, a scale parameter, and L, the number of looks. Quality estimation of α is essential due to its immediate interpretability. In this letter, we exploit the connection between the G <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</sub> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sup> and Pareto distributions. With this, we obtain six estimators that have not been previously used in the SAR literature. We compare their behavior with others in the noisiest case for monopolarized intensity data, namely single look case. We evaluate them using Monte Carlo methods for noncontaminated and contaminated data, considering convergence rate, bias, mean squared error, and computational time. We conclude that two of these estimators based on the Pareto law are the safest choices when dealing with actual data and small samples, as is the case of despeckling techniques and segmentation, to name just two applications. We verify the results with an actual SAR image.

Moisture content in Portland cement concrete structures is commonly associated with many durability problems (e.g., steel corrosion) and can be used in structural health monitoring and nondestructive evaluation/testing (NDE/T) of concrete structures. While several intrusive techniques are available for quantifying moisture content inside concrete structures, it is a challenging task to estimate the moisture content of concrete in the field without using embedded moisture sensors. In this paper, synthetic aperture radar (SAR) imaging as a nonintrusive technique and the K-R-I (curvature-area-amplitude) transform are applied to concrete panel specimens made of two water-to-cement (w/c) ratios (w/c = 0.4 and 0.5) for moisture determination. Concrete panel specimens with dimensions of 0.3 m-by-0.3 m-by-0.05 m were manufactured and conditioned in a laboratory environment by air-drying for three months. Its time-dependent moisture variation was simultaneously monitored by a 10.5- GHz center frequency SAR imaging sensor inside an anechoic chamber. Quantitative analysis of SAR images was carried out by using the K-R-I transform to understand the simultaneous change of SAR amplitude and distribution (contour shape) at different moisture contents. It was found that SAR amplitude and its distribution increase with the increase of moisture content inside concrete panel specimens. Spatial distribution of SAR amplitudes can be used to indicate subsurface moisture distribution inside concrete. The area-amplitude (R-I) curve of SAR images can be used to quantify the relationship between moisture content and its distribution.

The synthetic aperture radar (SAR) images obtained with the Jet Propulsion Laboratory's L band system in the Tower Ocean Wave and Radar Dependence (TOWARD) oceanographic experiment are compared with images generated by a simulation program implementing a SAR ocean imaging model based on two‐scale hydrodynamic and electromagnetic scattering approximate models. A critically regarded test of a theory of SAR ocean imaging is its prediction of the best image focus dependence on surface motion. The primary means of comparison here is an estimate of the best focus parameter that uses a subimage cross‐correlation technique. The focus parameter estimates for both the actual and simulated images show (1) a reversal in sign with reversal in dominant longwave direction relative to the SAR direction, (2) a magnitude increase with an increase in magnitude of the angle between the dominent long wave and SAR axes, and (3) an independence of the altitude and also the range‐to‐velocity ratio. All equivalent velocity estimates are of the order of the dominant longwave phase velocity, normalized by the SAR vehicle velocity, and agree well qualitatively though there are some quantitative differences. These behaviors are in agreement with a related analytical prediction. The “visibility” of the long waves' SAR image artifacts, for this TOWARD data set, increased with increased altitude and also with increased range‐to‐velocity ratio for both the actual and simulated images, as was predicted by a related analysis. Agreement of spectral density estimates of the actual and simulated SAR images generally required an order of magnitude increase in the strength of the hydrodynamic interaction of the long and short waves. This may indicate, as have surface measurements in TOWARD and other experiments, that the two‐scale model does not fully describe this nonlinear interaction. With this interaction adjustment, a comparison of actual and simulated images using an alternative focus criterion showed very close agreement in some cases.