Synthetic Aperture Radar Despeckling Research Articles

SAR Despeckling Using a Denoising Diffusion Probabilistic Model

Speckle is a type of multiplicative noise that affects all coherent imaging modalities including Synthetic Aperture Radar (SAR) images. The presence of speckle degrades the image quality and can adversely affect the performance of SAR image applications such as automatic target recognition and change detection. Thus, SAR despeckling is an important problem in remote sensing. In this paper, we introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method employs a Markov chain that transforms clean images to white Gaussian noise by successively adding random noise. The despeckled image is obtained through a reverse process that predicts the added noise iteratively, using a noise predictor conditioned on the speckled image. Additionally, we propose a new inference strategy based on cycle spinning to improve the despeckling performance. Our experiments on both synthetic and real SAR images demonstrate that the proposed method leads to significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods. The code is available at: https://github.com/malshaV/SAR_DDPM.

Unpaired Speckle Extraction for SAR Despeckling

Speckle suppression is a critical step in synthetic aperture radar (SAR) imaging. Since speckle-free SAR images are inaccessible, supervised denoising methods are not suitable for this task. To exploit the strong capabilities of convolutional neural networks (CNNs), we propose Unpaired Speckle Extraction (SAR-USE), an unsupervised method for SAR despeckling. Our method utilizes unpaired SAR and clean optical images to extract “real” speckle for learning despeckling. First, a CNN that has never seen clean SAR images is employed to extract speckle from the SAR image. Then, the extracted speckle is multiplied with a random optical image to synthesize paired data for learning speckle removal. Through a Siamese network, speckle extraction and learning despeckling are performed alternately and promote each other. To make the extracted speckle more visually and statistically realistic, it is constrained by a noise correction module to be unit mean while maintaining spatial correlation. After convergence, the CNN is a good denoiser that can effectively extract speckle from SAR images. Experiments on synthetic datasets show that the denoising ability of the proposed method is as good as its supervised counterpart. More importantly, SAR-USE is very efficient for removing the spatially correlated speckle in real data that supervised learning methods cannot.

Mapping the 2021 October Flood Event in the Subsiding Taiyuan Basin by Multitemporal SAR Data

A flood event induced by heavy rainfall hit the Taiyuan basin in north China in early October of 2021. In this study, we map the flood event process using the multi-temporal synthetic aperture radar (SAR) images acquired by Sentinel-1. First, we develop a spatiotemporal filter based on low-rank tensor approximation (STF-LRTA) for removing the speckle noise in SAR images. Next, we employ the classic log-ratio change indicator and the minimum error threshold algorithm to characterize the flood using the filtered images. Finally, we relate the flood inundation to the land subsidence in the Taiyuan basin by jointly analyzing the multi-temporal SAR change detection results and interferometric SAR (InSAR) time-series measurements (pre-flood). The validation experiments compare the proposed filter with the Refined-Lee filter, Gamma filter, and an SHPS-based multi-temporal SAR filter. The results demonstrate the effectiveness and advantage of the proposed STF-LRTA method in SAR despeckling and detail preservation, and the applicability to change scenes. The joint analyses reveal that land subsidence might be an important contributor to the flood event, and the flood recession process linearly correlates with time and subsidence magnitude.

SAR Despeckling Based on CNN and Bayesian Estimator in Complex Wavelet Domain

We propose a hybrid algorithm for despeckling the Synthetic Aperture Radar (SAR) images using the Convolutional Neural Network (CNN) denoising and complex wavelet shrinkage. In particular, we perform the speckle reduction process in the complex wavelet domain. We first despeckled the approximation complex wavelet coefficients using the MUltichannel LOgarithm with the Gaussian denoising algorithm (MuLoG) based on a pre-trained CNN model named FFDNet. Next, we despeckled the log-transformed details of the complex wavelet coefficients using the averaged version of the Maximum a Posteriori (AMAP) estimator. The experimental results on simulated and real SAR images showed that the proposed method achieved better speckle suppression in the homogeneous areas while preserving edges and point targets than other state-of-the-art methods.

Analysis on the Building of Training Dataset for Deep Learning SAR Despeckling

In the framework of deep learning for synthetic aperture radar (SAR) speckle reduction, the methods presented in the literature mainly focus on the definition of new architectures and cost functions for better catching and preserving the properties of a real SAR image. The achieved results are interesting and promising but with many left open issues. The main critical problem, shared by all the methods, is the construction of a training dataset. This is due to the lack of a noise-free reference. In this work, a comparison among different training approaches (synthetic, multitemporal, and hybrid) is carried out in order to analyze their benefits and drawbacks. Four convolutional neural network (CNN)-based methods have been trained with the three different datasets for their assessment. Results on real SAR images have been carried out showing the peculiarities of each training approach.

A Blind SAR Image Despeckling Method Based on Improved Weighted Nuclear Norm Minimization

Coherent imaging of synthetic aperture radar (SAR) systems generates multiplicative speckle noise, severely impairs SAR images’ interpretability. Although numerous despeckling methods have been proposed over the past three decades, SAR despeckling remains an unsolved problem due to its uniqueness and complexity. To address these issues, we propose a novel SAR image despeckling method based on the framework of weighted nuclear norm minimization (WNNM). First, a Gaussian function is used to approximate the distribution of good similar patches (GSP). Clustering is then used to select the optimal patches for the GSP matrix. WNNM can then estimate the underlying clean component of the GSP matrix. To increase the speed of the WNNM, a modified version of the singular value decomposition (SVD) is introduced. Additionally, we developed a noise variance estimation method that enables blind despeckling with the proposed method. Extensive experimental results demonstrate that the proposed method yields superior objective indices and subjective visual inspection.

RETRACTED ARTICLE: Image denoising and despeckling methods for SAR images to improve image enhancement performance: a survey

The synthetic aperture radar (SAR) images are playing an essential role in remote sensing. Various types of internal, external, and environmental noise are affecting the SAR images. Coherent speckle noise is the primary source of noise in SAR images. Such noise can be removed by using a single filter or combination of filters and transform signals. SAR image denoising has been attracting the attention of researchers for the past three decades. The target area and application type are influencing the choice of denoising method. In this paper, the basics of SAR imaging, steps in the pipeline of SAR despeckling process, filters like Lee filter, Frost filter, Kuan Filter and Gamma Maximum a posteriori (MAP) filter, various state of the art despeckling methods and deep learning approaches for SAR despeckling are discussed. Five transforms for despeckling are discussed with literature. The data sets from different radars, the applications, area of importance, and the quality metrics used to evaluate the despeckling quality are discussed in detail that has been available in the literature of the past two decades.

Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives

Synthetic aperture radar (SAR) images are affected by a spatially-correlated and signal-dependent noise called speckle, which is very severe and may hinder image exploitation. Despeckling is an important task that aims at removing such noise, so as to improve the accuracy of all downstream image processing tasks. The first despeckling methods date back to the 1970's, and several model-based algorithms have been developed in the subsequent years. The field has received growing attention, sparkled by the availability of powerful deep learning models that have yielded excellent performance for inverse problems in image processing. This paper surveys the literature on deep learning methods applied to SAR despeckling, covering both the supervised and the more recent self-supervised approaches. We provide a critical analysis of existing methods with the objective to recognize the most promising research lines, to identify the factors that have limited the success of deep models, and to propose ways forward in an attempt to fully exploit the potential of deep learning for SAR despeckling.

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.

SPB-Net: A Deep Network for SAR Imaging and Despeckling With Downsampled Data

Synthetic aperture radar (SAR) typically faces both large-scale data and speckle noise problems, which, respectively, induce enormous strains on transmission and storage and interfere with the analysis and interpretation of SAR images. To tackle these, we present a real-time processing deep network, called SPB-Net, to implement imaging and speckle suppression simultaneously. First, a novel imaging-despeckling observation model with the nonlogarithmic additive speckle noise is established. Subsequently, guided by the statistical properties of noise and sparse and detail-preserved requirements in SAR imaging and despeckling, we formulate an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{2}$ </tex-math></inline-formula> along with two <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> regularizations as the fidelity, sparse, and image detail-preserved constraints, respectively. Convolution layers are employed to improve the feature representation capability in the latter <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> term as well. Based on this, we construct a corresponding convex optimization problem. Then, the complex-valued split Bregman method, focusing on the complex-variable convex problem, is unfolded into a parameter-learnable and architecture-fixed SPB-Net to solve the proposed problem effectively and efficiently. Experimental results with the downsampled Radarsat-1 raw data demonstrate the validity in imaging and speckle suppression and the real-time processing capability of the proposed SPB-Net.

Multi-Objective CNN-Based Algorithm for SAR Despeckling

Deep learning (DL) in remote sensing has nowadays become an effective operative tool: it is largely used in applications such as change detection, image restoration, segmentation, detection and classification. With reference to synthetic aperture radar (SAR) domain the application of DL techniques is not straightforward due to non trivial interpretation of SAR images, specially caused by the presence of speckle. Several deep learning solutions for SAR despeckling have been proposed in the last few years. Most of these solutions focus on the definition of different network architectures with similar cost functions not involving SAR image properties. In this paper, a convolutional neural network (CNN) with a multi-objective cost function taking care of spatial and statistical properties of the SAR image is proposed. This is achieved by the definition of a peculiar loss function obtained by the weighted combination of three different terms. Each of this term is dedicated mainly to one of the following SAR image characteristics: spatial details, speckle statistical properties and strong scatterers identification. Their combination allows to balance these effects. Moreover, a specifically designed architecture is proposed for effectively extract distinctive features within the considered framework. Experiments on simulated and real SAR images show the accuracy of the proposed method compared to the State-of-Art despeckling algorithms, both from quantitative and qualitative point of view. The importance of considering such SAR properties in the cost function is crucial for a correct noise rejection and details preservation in different underlined scenarios, such as homogeneous, heterogeneous and extremely heterogeneous.

Spatial and Transform Domain CNN for SAR Image Despeckling

The speckle interference seriously degrades the quality of synthetic aperture radar (SAR) image. The existing despeckling algorithms still struggle to remove noise and preserve details simultaneously. In order to enhance the noise suppression and detail restoration performance, this article specially presents a spatial and transform domain convolutional neural network (STD-CNN) model, which yields an integrated feature representation and learning framework for despeckling. In addition, an innovative feature refinement strategy is proposed to further reduce the detail loss by isolating detail features from noise features. Extensive experiments on synthetic and real SAR images demonstrate that the proposed method outperforms the existing SAR despeckling methods on both quantitative and qualitative assessments. With partial modification, the STD-CNN model can still be extended to other image restoration tasks.

SAR2SAR: A Semi-Supervised Despeckling Algorithm for SAR Images

Speckle reduction is a key step in many remote sensing applications. By strongly affecting synthetic aperture radar (SAR) images, it makes them difficult to analyse. Due to the difficulty to model the spatial correlation of speckle, a deep learning algorithm with self-supervision is proposed in this paper: SAR2SAR. Multi-temporal time series are leveraged and the neural network learns to restore SAR images by only looking at noisy acquisitions. To this purpose, the recently proposed noise2noise framework has been employed. The strategy to adapt it to SAR despeckling is presented, based on a compensation of temporal changes and a loss function adapted to the statistics of speckle. A study with synthetic speckle noise is presented to compare the performances of the proposed method with other state-of-the-art filters. Then, results on real images are discussed, to show the potential of the proposed algorithm. The code is made available to allow testing and reproducible research in this field.

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

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

SAR Image Despeckling Based on Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization

Regularization method is an effective tool for synthetic aperture radar (SAR) image despeckling. Design of the effective regularization terms describing the image priors plays a vital role in this kind of method. In this article, a new combinational regularization model for speckle reduction (CRM-SR) is proposed, in which a regularization term is elaborately designed to contain both a fractional-order total variation (FrTV) regularization and a nonlocal low rank (NLR) regularization. The new regularization model inherits both the advantages of FrTV and NLR and improves the performance of SAR despeckling and, therefore, better preserves the edges and geometrical features of the images during the despeckling process. An efficient algorithm based on alternating direction optimization is derived to solve the proposed combinational regularization model. Experimental results show that the proposed model can effectively remove SAR image speckle and preserve the geometrical features of images according to both subjective visual assessment of image quality and objective evaluation.

Removing Speckle Noise in Synthetic Aperture Radar Images using Linear Filters

Speckle is a granular aggravation, typically demonstrated as a multiplicative noise that influences Synthetic aperture radar (SAR) pictures, just as every single cognizant picture. In the course of the most recent three decades, a few techniques have been proposed for the decrease of spot, or despeckling, in SAR pictures. The examination begins with the linear filtering, non-linear filtering, adaptive filtering, and hybrid filtering. In spite of the fact that the old style straight separating strategies have lower execution similarly, the hybridization between them beats than the as of late proposed techniques. Be that as it may, the cautious determination of such filters and their impacting request exceptionally influences the presentation of such filtering methodologies. In this paper, Hybrid filtering is proposed for SAR despeckling, which involves the improved variants of frost, median and mean filters. The presentation of the proposed framework is broke down and contrasted and the as of late SAR despeckling strategies. The outcomes demonstrate that the hybrid filters are focused as they can despeckle the SAR pictures superior to the current methods

HDRANet: Hybrid Dilated Residual Attention Network for SAR Image Despeckling

In order to remove speckle noise from original synthetic aperture radar (SAR) images effectively and efficiently, this paper proposes a hybrid dilated residual attention network (HDRANet) with residual learning for SAR despeckling. Firstly, HDRANet employs the hybrid dilated convolution (HDC) in lightweight network architecture to enlarge the receptive field and aggregate global information. Then, a simple yet effective attention module, convolutional block attention module (CBAM), is integrated into the proposed model to constitute a residual HDC attention block through skip connection, which further enhances representation power and performance of the model. Extensive experimental results on the synthetic and real SAR images demonstrate the superior performance of HDRANet over the state-of-the-art methods in terms of quantitative metrics and visual quality.

Polarimetric SAR Despeckling by Integrating Stochastic Sampling and Contextual Patch Dissimilarity Exploration

Speckle reduction has been the longstanding task since the invention of synthetic aperture radar (SAR). For further image analysis and interpretation, it usually demands better speckle suppression to preserve spatial and polarimetric information of the polarimetric SAR (PolSAR) images. In this paper, a new PolSAR filtering algorithm which combines stochastic sampling based on nonlocal mean, random walk model, and contextual patch dissimilarity is proposed. The nonlocal mean suppresses the speckle effectively while preserving the details and polarimetric information well. However, the size of nonlocal search window is fixed without taking the homogeneous and heterogeneous areas into consideration. Thus, it usually leads to computational redundancy. Correspondingly, we propose to apply the random walk to reduce the search domain. Contextual patch is also proposed to represent the large surroundings of a patch in a compact fashion. More precisely, the random walk model is utilized to determine the sampling path. Then, the traditional center patch dissimilarity and contextual patch dissimilarity are employed to measure the transition probability of the random walk sequence. Finally, the denoised estimation of PolSAR image is obtained by weight function derived from the transition probability. Since the stochastic sampling combines spatial random walk and the polarimetric dissimilarity measurements, the proposed algorithm fully exploits both the spatial and polarimetric information. Experimental results on synthetic and real PolSAR data demonstrate the effectiveness of the proposed method in terms of spatial and polarimetric information maintenance.

Comparison of Transform Domain based SAR Despeckling Techniques

Objectives: Synthetic Aperture RADAR (SAR) is a satellite imaging technology which is affected by speckle noise having granular pattern. Speckle is multiplicative noise and occurs due to the interference of the signal with the backscattered echoes. Methods/Analysis: Speckle degrades the image quality and makes further segmentation and classification of images difficult. Despeckling can be done in spatial and transform domain. In this paper the various transform domain despeckling techniques like wavelet, shearlet, contourlet and curvelet are compared. The results are analyzed using performance parameter like ECF, SSIM and ENL. Findings: Comparison of the various methods is done by using synthetic images and real images. ECF and SSIM are used to evaluate synthetic images and ENL is used for real images. In the case of real images the ENL value is highest for curvelet compared to wavelet, shearlet and contourlet. In the case of synthetic images SSIM and ECF value is high for curvelet compared to other methods. ENL value is lowest for shearlet transform whereas SSIM and ECF values are lowest for contourlet transform. From the results, it can be concluded that curvelet outperforms all the other methods. Novelty/ Improvements: Transform Domain techniques has got wide spread applications in the field of denoising, segmentation and classification. Using curvelet for despeckling can improve the further segmentation and classification process.

SAR Image Despeckling by Sparse Reconstruction Based on Shearlets

Synthetic aperture radar (SAR) image is usually polluted by multiplicative speckle noise, which can affect further processing of SAR image. This paper presents a new approach for multiplicative noise removal in SAR images based on sparse coding by shearlets filtering. First, a SAR despeckling model is built by the theory of compressed sensing (CS). Secondly, obtain shearlets coefficient through shearlet transform, each scale coefficient is represented as a unit. For each unit, sparse coefficient is iteratively estimated by using Bayesian estimation based on shearlets domain. The represented units are finally collaboratively aggregated to construct the despeckling image. Our results in SAR image despeckling show the good performance of this algorithm, and prove that the algorithm proposed is robustness to noise, which is not only good for reducing speckle, but also has an advantage in holding information of the edge.