Synthetic Aperture Radar Speckle Research Articles

SAR Image Despeckling Based on Denoising Diffusion Probabilistic Model and Swin Transformer

The speckle noise inherent in synthetic aperture radar (SAR) imaging has long posed a challenge for SAR data processing, significantly affecting image interpretation and recognition. Recently, deep learning-based SAR speckle removal algorithms have shown promising results. However, most existing algorithms rely on convolutional neural networks (CNN), which may struggle to effectively capture global image information and lead to texture loss. Besides, due to the different characteristics of optical images and synthetic aperture radar (SAR) images, the results of training with simulated SAR data may bring instability to the real-world SAR data denoising. To address these limitations, we propose an innovative approach that integrates swin transformer blocks into the prediction noise network of the denoising diffusion probabilistic model (DDPM). By harnessing DDPM’s robust generative capabilities and the Swin Transformer’s proficiency in extracting global features, our approach aims to suppress speckle while preserving image details and enhancing authenticity. Additionally, we employ a post-processing strategy known as pixel-shuffle down-sampling (PD) refinement to mitigate the adverse effects of training data and the training process, which rely on spatially uncorrelated noise, thereby improving its adaptability to real-world SAR image despeckling scenarios. We conducted experiments using both simulated SAR image datasets and real SAR image datasets, evaluating our algorithm from subjective and objective perspectives. The visual results demonstrate significant improvements in noise suppression and image detail restoration. The objective results demonstrate that our method obtains state-of-the-art performance, which outperforms the second-best method by an average peak signal-to-noise ratio (PSNR) of 0.93 dB and Structural Similarity Index (SSIM) of 0.03, affirming the effectiveness of our approach.

Dual Consistency Alignment Based Self-Supervised Learning for SAR Target Recognition With Speckle Noise Resistance

Deep learning based on Convolutional Neural Networks (CNN) has been widely applied in Synthetic Aperture Radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called Dual Consistency Alignment based Self-Supervised Learning(DCA-SSL). Firstly, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pre-training is performed on unlabeled data. During this period, we combine instance pseudo-label consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pre-trained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on MSTAR data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition and maintains a high recognition rate even in small sample learning. Our code is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Jordan-Liao/DCA-SSL</uri> .

CFOG-like image registration algorithm based on 3D-structural feature descriptor for suburban optical and SAR

Owing to nonlinear radiation differences between optical and synthetic aperture radar (SAR) images, and the inevitable SAR speckle noise, the registration of optical and SAR images is challenging work. This paper proposes a novel pixel-wise 3D-structural feature descriptor based on channel-features-of-oriented-gradients (CFOG), thus, it inherits the fast and robust advantages of CFOG. First, the Block-Harris and grid points feature extraction method is used to obtain sufficient uniformly distributed keypoints from the reference images. Then, the new feature descriptor based on the combination of first-order oriented gradients and second-order gradients (FOSG) is proposed. Specifically, two different operators, the Sobel and the ratio of exponentially weighted averages are utilized to calculate the gradient for the optical and SAR images, respectively. On this basis, the first-order oriented gradients and second-order gradients are calculated by a 3D-Gaussian filter and then normalized along the Z-direction to form the FOSG by superposition. Finally, template matching based on the sum of squared differences similarity metric is implemented in the frequency domain. Our method is experimentally compared with five state-of-the-art methods using six pairs of suburban optical and SAR images. The results show that the proposed algorithm is robust to nonlinear radiation differences and SAR speckle noise, and achieves high accuracy.

Self-calibrated dilated convolutional neural networks for SAR image despeckling

ABSTRACT Synthetic aperture radar (SAR) imaging process is essentially disturbed by speckle noise due to its unique mechanism. Speckle noise causes severe degradation of SAR image quality, which significantly limits its practical application. Recently, convolutional neural networks (CNNs) have indicated good potential for various image processing tasks. In this article, we propose a self-calibrated dilated convolutional neural network for SAR image despeckling called SAR-SCDCNN. The main body of SAR-SCDCNN is formed by seven self-calibrated blocks (SeCaBlock). Firstly, in each SeCaBlock, the input features are split into two branches: one represents the contextual features in the original space, and another represents those in the long-range space. Then, the down-up sampling operation and the convolutions with hybrid dilated rates are employed to enlarge the receptive field. The weights for calculating features themselves are adaptively extracted in the second branch. And then, two branch features are concatenated and fused through a convolution. Finally, a skip connection is used between the input and output of each SeCaBlock to give full play to the expressive power of the deep neural network and enhance training stability. Experiments on synthetic speckled and real SAR images are conducted to perform objective quantitative and subjective visual evaluations of image quality. Results show that our proposed method can effectively suppress speckle noise and adequately preserve detailed features.

SAR-DRDNet: A SAR image despeckling network with detail recovery

Synthetic aperture radar (SAR) image is affected by inherent speckle, greatly hindering its interpretation and subsequent applications. In SAR images despeckling tasks, it is still challenging to remove speckle while preserving spatial details. Traditional methods generally require a complicated design of relationships between the speckled and noise-free SAR images. The growing popularity of deep learning algorithms exhibits great potential in resolving this limitation. However, the existing deep learning-based despeckling methods need further improvement in speckle suppression and details preservation. Therefore, we propose an end-to-end SAR images despeckling residual network with detail recovery, named SAR-DRDNet, which is mainly composed of non-local blocks (NLBs) and detail recovery blocks (DRBs). NLB takes full advantage of the global information of the SAR image to suppress speckle. DRB is further employed to recover lost details in the process of NLBs, taking into account the multi-scale contextual information of pixels and has a larger receptive field without reducing the resolution of feature maps. We validate the proposed SAR-DRDNet on the simulated and real SAR data. Both quantitative and qualitative comparisons demonstrate the superiority of the proposed SAR-DRDNet over the many mainstream methods, evidenced by its capability to achieve a great balance between speckle suppression and textural details preservation.

Wavelength-Resolution SAR Speckle Model

This study investigates both fully and nonfully developed speckle models for wavelength-resolution synthetic aperture radar (SAR). The resolution of the wavelength-resolution SAR systems is on the order of wavelengths of the radar signal. Therefore, the equivalent number of independent scatterers per resolution cell is so small that the speckle is not fully developed. Based on the central limit theorem, the relationship between the number of scatterers and the nonfully developed speckle is first clarified in detail by using a characteristic function and moment generating function. Considering the surface scattering and volume scattering for the radar observations, both fully and nonfully developed speckles are demonstrated in wavelength-resolution SAR images by testing three probability density functions (pdfs), namely, K-distribution, Rayleigh, log-normal, and Weibull distributions. The use of airborne coherent all radio band sensing II (CARABAS-II) very high frequency (VHF) (20–90 MHz) SAR data for the nonfully developed speckle has been investigated. This study discovers that the speckle is not fully developed when the equivalent number of independent scatterers is less than eight. Wavelength-resolution SAR data exhibit nonfully developed speckles on regions of interest in heterogeneous surface scattering and volume scattering. In contrast, for homogeneous surfaces with specular scattering on lakes and some roads, the data follow a Rayleigh distribution due to systematic background thermal noise and very little reflected received signal. In this case, it corresponds to the absence of effective independent scatterers within the resolution cell.

An Advanced SAR Image Despeckling Method by Bernoulli-Sampling-Based Self-Supervised Deep Learning

As one of the main sources of remote sensing big data, synthetic aperture radar (SAR) can provide all-day and all-weather Earth image acquisition. However, speckle noise in SAR images brings a notable limitation for its big data applications, including image analysis and interpretation. Deep learning has been demonstrated as an advanced method and technology for SAR image despeckling. Most existing deep-learning-based methods adopt supervised learning and use synthetic speckled images to train the despeckling networks. This is because they need clean images as the references, and it is hard to obtain purely clean SAR images in real-world conditions. However, significant differences between synthetic speckled and real SAR images cause the domain gap problem. In other words, they cannot show superior performance for despeckling real SAR images as they do for synthetic speckled images. Inspired by recent studies on self-supervised denoising, we propose an advanced SAR image despeckling method by virtue of Bernoulli-sampling-based self-supervised deep learning, called SSD-SAR-BS. By only using real speckled SAR images, Bernoulli-sampled speckled image pairs (input–target) were obtained as the training data. Then, a multiscale despeckling network was trained on these image pairs. In addition, a dropout-based ensemble was introduced to boost the network performance. Extensive experimental results demonstrated that our proposed method outperforms the state-of-the-art for speckle noise suppression on both synthetic speckled and real SAR datasets (i.e., Sentinel-1 and TerraSAR-X).

A Robust SAR Speckle Tracking Workflow for Measuring and Interpreting the 3D Surface Displacement of Landslides

We present a workflow for investigating large, slow-moving landslides which combines the synthetic aperture radar (SAR) technique, GIS post-processing, and airborne laser scanning (ALS), and apply it to Fels landslide in Alaska, US. First, we exploit a speckle tracking (ST) approach to derive the easting, northing, and vertical components of the displacement vectors across the rock slope for two five-year windows, 2010–2015 and 2015–2020. Then, we perform post-processing in a GIS environment to derive displacement magnitude, trend, and plunge maps of the landslide area. Finally, we compare the ST-derived displacement data with structural lineament maps and profiles extracted from the ALS dataset. Relying on remotely sensed data, we estimate that the thickness of the slide mass is more than 100 m and displacements occur through a combination of slumping at the toe and planar sliding in the central and upper slope. Our approach provides information and interpretations that can assist in optimizing and planning fieldwork activities and site investigations at landslides in remote locations.

A Rotation-Invariant Optical and SAR Image Registration Algorithm Based on Deep and Gaussian Features

Traditional feature matching methods of optical and synthetic aperture radar (SAR) used gradient are sensitive to non-linear radiation distortions (NRD) and the rotation between two images. To address this problem, this study presents a novel approach to solving the rigid body rotation problem by a two-step process. The first step proposes a deep learning neural network named RotNET to predict the rotation relationship between two images. The second step uses a local feature descriptor based on the Gaussian pyramid named Gaussian pyramid features of oriented gradients (GPOG) to match two images. The RotNET uses a neural network to analyze the gradient histogram of the two images to derive the rotation relationship between optical and SAR images. Subsequently, GPOG is depicted a keypoint by using the histogram of Gaussian pyramid to make one-cell block structure which is simpler and more stable than HOG structure-based descriptors. Finally, this paper designs experiments to prove that the gradient histogram of the optical and SAR images can reflect the rotation relationship and the RotNET can correctly predict them. The similarity map test and the image registration results obtained on experiments show that GPOG descriptor is robust to SAR speckle noise and NRD.

3D SAR Speckle Offset Tracking Potential for Monitoring Landfast Ice Growth and Displacement

This study investigates the growth and displacement of landfast ice along the shoreline of the Mackenzie Delta in Northwest Territories, Canada, by synthetic aperture radar (SAR) speckle offset tracking (SPO). Three-dimensional (3D) offsets were reconstructed from Sentinel-1 ascending and descending SAR images acquired on the same dates during the November 2017–April 2018 and October 2018–May 2019 annual cycles. The analysis revealed both horizontal and vertical offsets. The annual horizontal offsets of up to ~8 m are interpreted as landfast ice displacements caused by wind and ocean currents. The annual vertical offsets of approximately −1 to −2 m were observed from landfast ice, which are likely due to longer radar penetration up to the ice–water interface with increasing landfast ice thickness. Numerical ice thickness model estimates supported the conclusion that the cumulative vertical negative offsets correspond to the growth of freshwater ice. Time-series analysis showed that the significant growth and displacement of landfast ice in the Mackenzie Delta occurred between November and January during the 2017–2018 and 2018–2019 cycles.

A Practical Solution for SAR Despeckling With Adversarial Learning Generated Speckled-to-Speckled Images

In this letter, we aim to address a synthetic aperture radar (SAR) despeckling problem with the necessity of neither clean (speckle-free) SAR images nor independent speckled image pairs from the same scene, and a practical solution for SAR despeckling (PSD) is proposed. First, an adversarial learning framework is designed to generate speckled-to-speckled (S2S) image pairs from the same scene in the situation where only single speckled SAR images are available. Then, the S2S SAR image pairs are employed to train a modified despeckling Nested-UNet model using the Noise2Noise (N2N) strategy. Moreover, an iterative version of the PSD method (PSDi) is also presented. Experiments are conducted on both synthetic speckled and real SAR data to demonstrate the superiority of the proposed methods compared with several state-of-the-art methods. The results show that our methods can reach a good tradeoff between feature preservation and speckle suppression.

A Robust Algorithm Based on Phase Congruency for Optical and SAR Image Registration in Suburban Areas

Automatic registration of optical and synthetic aperture radar (SAR) images is a challenging task due to the influence of SAR speckle noise and nonlinear radiometric differences. This study proposes a robust algorithm based on phase congruency to register optical and SAR images (ROS-PC). It consists of a uniform Harris feature detection method based on multi-moment of the phase congruency map (UMPC-Harris) and a local feature descriptor based on the histogram of phase congruency orientation on multi-scale max amplitude index maps (HOSMI). The UMPC-Harris detects corners and edge points based on a voting strategy, the multi-moment of phase congruency maps, and an overlapping block strategy, which is used to detect stable and uniformly distributed keypoints. Subsequently, HOSMI is derived for a keypoint by utilizing the histogram of phase congruency orientation on multi-scale max amplitude index maps, which effectively increases the discriminability and robustness of the final descriptor. Finally, experimental results obtained using simulated images show that the UMPC-Harris detector has a superior repeatability rate. The image registration results obtained on test images show that the ROS-PC is robust against SAR speckle noise and nonlinear radiometric differences. The ROS-PC can tolerate some rotational and scale changes.

SAR Speckle Removal Using Hybrid Frequency Modulations

Synthetic aperture radar (SAR) images often interfere with speckle artifacts that have a great impact on subsequent processing and analysis operations. To remove speckle artifacts, this article introduces a hybrid denoising approach by using a convolutional neural network (CNN) and consistent cycle spinning (CCS) in the nonsubsample shearlet transform (NSST) domain. First, we apply NSST to a noisy SAR image to gain low- and high-frequency coefficients. Second, we adopt a learned deep CNN model to eliminate the speckle noise in the low-frequency coefficients, which retains more contour information. Third, we employ CCS to enhance the high-frequency coefficients, which preserves more details of the original SAR image. Finally, we obtain the denoised image by using inverse NSST applied to the denoised coefficients. Compared with state-of-the-art algorithms, the results of the experiment indicate that our method not only achieves better speckle removal performance but also maintains more detailed information retention.

SAR Image Despeckling by Deep Neural Networks: from a Pre-Trained Model to an End-to-End Training Strategy

Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free/speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data. The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian denoising). No training on SAR images is performed, the network is readily applied to speckle reduction tasks. The second strategy considers a novel approach to construct a reliable dataset of speckle-free SAR images necessary to train a CNN model. Finally, a hybrid approach is also analyzed: the CNN used to remove additive white Gaussian noise is trained on speckle-free SAR images. The proposed methods are compared to other state-of-the-art speckle removal filters, to evaluate the quality of denoising and to discuss the pros and cons of the different strategies. Along with the paper, we make available the weights of the trained network to allow its usage by other researchers.

A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images

Although unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to performance degradation. In this paper, an unsupervised multi-scale convolution auto-encoder (MSCAE) was proposed which can simultaneously obtain the global features and local characteristics of targets with its U-shaped architecture and pyramid pooling modules (PPMs). The compact depth-wise separable convolution and the deconvolution counterpart were devised to decrease the trainable parameters. The PPM and the multi-scale feature learning scheme were designed to learn multi-scale features. Prior knowledge of SAR speckle was also embedded in the model. The reconstruction loss of the MSCAE was measured by the structural similarity index metric (SSIM) of the reconstructed data and the images filtered by the improved Lee sigma filter. A speckle suppression restriction was also added in the objective function to guarantee that the speckle suppression procedure would take place in the feature learning stage. Experimental results with the MSTAR dataset under the standard operating condition and several extended operating conditions demonstrated the effectiveness of the proposed model in SAR object classification tasks.

SAR Image Speckle Filtering With Context Covariance Matrix Formulation and Similarity Test

Speckle filtering of synthetic aperture radar (SAR) image is a necessary pre-processing for many subsequent applications. The challenge lies in how to adaptively select a sufficient number of similar pixels for an unbiased estimator generation. A novel SAR speckle filter is proposed and the core idea contains two aspects. Firstly, a context covariance matrix representation is developed within a local neighborhood to characterize the contexture information. Then, the Wishart statistic test is extended to examine the similarity of context covariance matrices. The extended similarity test indicator derived from context covariance matrices is verified to be sensitive for similar pixel localization. Thereafter, a sample averaging estimator is adopted based on the similar samples determined by the context covariance matrices similarity test (the proposed method is named as the CCM+SimiTest). Furthermore, a fast similarity test computation scheme is established which can handle large images smoothly even with a normal laptop. Intensive experimental studies with Radarsat-2, MiniSAR and ALOS-2 datasets are carried out. Comparisons with several state-of-the-art methods from both subjective and objective viewpoints demonstrate the superiority of the proposed method.

Enhancement of SAR Speckle Denoising Using the Improved Iterative Filter

The recent advancement in synthetic aperture radar (SAR) technology has enabled high-resolution imaging capability that calls for efficient speckle filtering algorithms to preprocess radar imagery. Since the introduction of the Lee sigma filter in 1980, the various versions of the minimum mean square error (MMSE) filter were developed, focusing essentially on how to estimate the processed pixels. For instance, the iterative MMSE (IMMSE) filter that is commonly initialized by the boxcar filter maintains the initially filtered homogeneous areas and corrects the initially blurred spatial details after a few iterations. In this article, an effort is made to enhance the performance of the IMMSE filter in terms of speckle reduction and spatial detail preservation by refining the choice of the initial filter, optimizing its parameters, and improving the estimation of local statistics. Compared with the basic version, results showed that the improved iterative filter considerably enhanced the filtering criteria. When the improved iterative filtering process was initialized by the nonlocal mean filter, for few iterations, the filtering performances were improved. Simulated, airborne (ESAR, Oberpfaffenhofen Germany) and spaceborne (Sentinel 1, Palm Jumeirah Dubai UAE) SAR data were used to assess the filtering performances of the studied filters.

A Bayesian Joint Decorrelation and Despeckling of SAR Imagery

Despeckling of synthetic aperture radar (SAR) is a known research challenge. A novel solution to this problem has been developed and evaluated via an iterative maximum a posterior estimation incorporating a Bayesian joint decorrelation and despeckling based on a correlation model. This model realistically explores the physical correlation process of SAR speckle noise and is determined automatically via Bayesian estimation in the log-Fourier domain. A patchwise computation is used to account for the spatial nonstationarity associated with SAR image data. The proposed approach is compared to the existing despeckling techniques using both simulated and real SAR data, and the experimental results demonstrate the improvement in preserving the structural details while suppressing speckle noise.

Recover Glacier Velocity Fields Derived From the SAR Speckle Tracking Technique Using Artificial Neural Network

The speckle tracking technique has demonstrated its great potential in glacier velocity field (GVF) mapping applications. It analyzes the cross correlation between two synthetic aperture radar (SAR) images, which is capable of providing 2-D glacier motion measurements with acceptable accuracy. Since the coherence between a SAR image pair illuminating glacier areas cannot be preserved everywhere in nearly all cases, inevitable no data areas will be presented in SAR speckle tracking products. In this letter, a relatively convenient method is proposed to recover a GVF generated by the speckle tracking technique. This method considers a GVF recovery problem to be a unitary supervised training problem and resolve it via an artificial neural network. A targeted architecture of the network for recovering a GVF is presented. Moreover, the parameters correlative with glacier motion mechanism are proposed to be introduced into the network, which is able to effectively improve the performance of GVF recovery. For the purpose of validation, the proposed method is compared with the well-known Kriging interpolation method based on real speckle tracking products. The experimental results demonstrate that the proposed method can effectively recover a GVF derived from the speckle tracking technique.

Automatic Target Recognition for Synthetic Aperture Radar Images Based on Super-Resolution Generative Adversarial Network and Deep Convolutional Neural Network

Aiming at the problem of the difficulty of high-resolution synthetic aperture radar (SAR) image acquisition and poor feature characterization ability of low-resolution SAR image, this paper proposes a method of an automatic target recognition method for SAR images based on a super-resolution generative adversarial network (SRGAN) and deep convolutional neural network (DCNN). First, the threshold segmentation is utilized to eliminate the SAR image background clutter and speckle noise and accurately extract target area of interest. Second, the low-resolution SAR image is enhanced through SRGAN to improve the visual resolution and the feature characterization ability of target in the SAR image. Third, the automatic classification and recognition for SAR image is realized by using DCNN with good generalization performance. Finally, the open data set, moving and stationary target acquisition and recognition, is utilized and good recognition results are obtained under standard operating condition and extended operating conditions, which verify the effectiveness, robustness, and good generalization performance of the proposed method.