Noisy Synthetic Aperture Radar Image Research Articles

Research on SAR image denoising method based on feature extraction

AbstractDue to the excellent characteristics of Synthetic Aperture Radar (SAR), it has become an important technical means for land and sea target detection applications worldwide. However, the SAR image imaging process is often accompanied by speckle noise, which affects the accuracy of target detection. For this problem, this paper proposes an SAR image reconstruction model based on image denoising and feature extraction. Given a noisy SAR image, at each pixel of the image, the value of the singularity index of a metric defined by the signal gradient norm density is calculated. Then through a hierarchical decomposition of these singular indices, a set of pixels containing the most informative feature set of the image is extracted, and a denoised image is reconstructed using the extracted features. In comparison to traditional filtering and denoising techniques such as non‐local filtering, this algorithm achieves remarkable local filtering and denoising effects while preserving the image's texture information. The denoising performance of the proposed method is evaluated through a series of quantitative indicators and visual comparisons. The results demonstrate that this method effectively reduces background clutter, resulting in a higher contrast between the target and the background.

Synthetic Aperture Radar Image Despeckling Based on a Deep Learning Network Employing Frequency Domain Decomposition

Synthetic aperture radar (SAR) images are inevitably interspersed with speckle noise due to their coherent imaging mechanism, which greatly hinders subsequent related research and application. In recent studies, deep learning has become an effective tool for despeckling remote sensing images. However, preserving more texture details while removing speckle noise remains a challenging task in the field of SAR image despeckling. Furthermore, most despeckling algorithms are designed specifically for a specific look and seriously lack generalizability. Therefore, in order to remove speckle noise in SAR images, a novel end-to-end frequency domain decomposition network (SAR−FDD) is proposed. The method first performs frequency domain decomposition to generate high-frequency and low-frequency information. In the high-frequency branch, a mean filter is employed to effectively remove noise. Then, an interactive dual-branch framework is utilized to learn the details and structural information of SAR images, effectively reducing speckles by fully utilizing features from different frequencies. In addition, a blind denoising model is trained to handle noisy SAR images with unknown noise levels. The experimental results demonstrate that the SAR−FDD achieves good visual effects and high objective evaluation metrics on both simulated and real SAR test sets (peak signal-to-noise ratio (PSNR): 27.59 ± 1.57 and structural similarity index (SSIM): 0.78 ± 0.05 for different speckle noise levels), demonstrating its strong denoising performance and ability to preserve edge textures.

Cuckoo Search Optimization-Based Bilateral Filter for Multiplicative Noise Reduction in Satellite Images

<div>Speckle noise degrades the visual appearance and the quality of a synthetic aperture radar (SAR) image. The reduction of speckle noise is the first step in any remote-sensing device. To improve the noisy SAR images, a variety of adaptive and nonadaptive noise reduction filters were used. In order to eliminate speckle noise present in SAR images, an adaptive cuckoo search optimization-based speckle reduction bilateral filter has been designed in this article. To test the ability to eliminate multiplicative noise, the suggested filter’s effectiveness was compared to that of several de-speckling approaches. It has been measured with different assessment metrics such as PSNR, EPI, SSIM, and ENL. When compared to conventional de-noising filters, the proposed filter shows promising results for lowering speckle noise and retaining edge properties. In addition, the PSNR value has increased as compared to the PMD method and this method has been shown to be efficient in reducing speckle noise in SAR images.</div>

Dark Spot Detection from SAR Images Based on Superpixel Deeper Graph Convolutional Network

Synthetic Aperture Radar (SAR) is the primary equipment used to detect oil slicks on the ocean’s surface. On SAR images, oil spill regions, as well as other places impacted by atmospheric and oceanic phenomena such as rain cells, upwellings, and internal waves, appear as dark spots. Dark spot detection is typically the initial stage in the identification of oil spills. Because the identified dark spots are oil slick candidates, the quality of dark spot segmentation will eventually impact the accuracy of oil slick identification. Although certain sophisticated deep learning approaches employing pixels as primary processing units work well in remote sensing image semantic segmentation, finding some dark patches with weak boundaries and small regions from noisy SAR images remains a significant difficulty. In light of the foregoing, this paper proposes a dark spot detection method based on superpixels and deeper graph convolutional networks (SGDCNs), with superpixels serving as processing units. The contours of dark spots can be better detected after superpixel segmentation, and the noise in the SAR image can also be smoothed. Furthermore, features derived from superpixel regions are more robust than those derived from fixed pixel neighborhoods. Using the support vector machine recursive feature elimination (SVM-RFE) feature selection algorithm, we obtain an excellent subset of superpixel features for segmentation to reduce the learning task difficulty. After that, the SAR images are transformed into graphs with superpixels as nodes, which are fed into the deeper graph convolutional neural network for node classification. SGDCN leverages a differentiable aggregation function to aggregate the node and neighbor features to form more advanced features. To validate our method, we manually annotated six typical large-scale SAR images covering the Baltic Sea and constructed a dark spot detection dataset. The experimental results demonstrate that our proposed SGDCN is robust and effective compared with several competitive baselines. This dataset has been made publicly available along with this paper.

SAR Image Despeckling Based on Block-Matching and Noise-Referenced Deep Learning Method

The noise2noise-based despeckling method, capable of training the despeckling deep neural network with only noisy synthetic aperture radar (SAR) image, has presented very good performance in recent research. This method requires a fine-registered multi-temporal dataset with minor time variance and uses similarity estimation to compensate for the time variance. However, constructing such a training dataset is very time-consuming and may not be viable for a certain practitioner. In this article, we propose a novel single-image-capable speckling method that combines the similarity-based block-matching and noise referenced deep learning network. The denoising network designed for this method is an encoder–decoder convolutional neural network and is accommodated to small image patches. This method firstly constructs a large number of noisy pairs as training input by similarity-based block-matching in either one noisy SAR image or multiple images. Then, the method trains the network in a Siamese manner with two parameter-sharing branches. The proposed method demonstrates favorable despeckling performance with both simulated and real SAR data with respect to other state-of-the-art reference filters. It also presents satisfying generalization capability as the trained network can despeckle well the unseen image of the same sensor. The main advantage of the proposed method is its application flexibility. It could be trained with either one noisy image or multiple images. Furthermore, the despeckling could be inferred by either the ad hoc trained network or a pre-trained one of the same sensor.

Despeckling of SAR Images Using BEMD-Based Adaptive Frost Filter

In image processing, removal of speckle noise from a satellite image is a challenging task for the researchers. There are various approaches for speckle noise reduction. Generally, the speckle noises are scattered, in satellite images, medical images and synthetic aperture radar (SAR) images. This paper introduces a bidimensional empirical mode decomposition (BEMD)-based adaptive filtering method for despeckling of SAR image. The noisy SAR image is decomposed into different bidimensional intrinsic mode function (BIMF) levels using BEMD and then filtering is performed on the first BIMF level, as it contains the high-frequency noise component. This adaptation process effectively filters out the noisy image component without destroying the original image component. A BEMD-based adaptive Frost filter is introduced in this paper for despeckling of SAR images. The despeckling performances of our proposed filtering method are further analyzed by visual evaluation and also using performance parameters comparatively. Our reconstructed images show better performance quantitatively and qualitatively compared to other filters.

Enhancement algorithm for separability of inland water body in synthetic aperture radar image via sparse representation and image fusion

ABSTRACT In synthetic aperture radar (SAR) images, inland water bodies generally appear as dark textures, but due to the interference of thermal noise, speckle noise, and azimuth blur, inland water bodies can be easily confused with weakly scattered areas such as roads, wetlands, and sand. Most of the existing denoising methods have been proposed for removing speckle noise. However, the presence of thermal noise and azimuth blur still makes it difficult to distinguish inland water bodies. The denoising method based on the Doppler spectrum can effectively remove thermal noise, speckle noise, and azimuth blur, but it reduces the resolution, which blurs the contour of the water body, and it is difficult to apply to the detection and processing of small inland water bodies. Fusing a noisy high-resolution image with a low-resolution image with less noise makes it possible to remove the speckle noise and thermal noise of the SAR image while maintaining the edge texture of the water body. Based on the idea of image fusion, sparse representation is used to fuse the original noisy SAR image (HR) and the low-precision image (LR) processed by the denoising algorithm to maximise the use of all the information in HR and LR. According to this idea, an enhancement algorithm for separability of inland water body based on sparse representation is proposed. The experimental results show that the proposed model significantly improves the separability of inland water bodies in SAR images.

Coupling Denoising to Detection for SAR Imagery

Detecting objects in synthetic aperture radar (SAR) imagery has received much attention in recent years since SAR can operate in all-weather and day-and-night conditions. Due to the prosperity and development of convolutional neural networks (CNNs), many previous methodologies have been proposed for SAR object detection. In spite of the advance, existing detection networks still have limitations in boosting detection performance because of inherently noisy characteristics in SAR imagery; hence, separate preprocessing step such as denoising (despeckling) is required before utilizing the SAR images for deep learning. However, inappropriate denoising techniques might cause detailed information loss and even proper denoising methods does not always guarantee performance improvement. In this paper, we therefore propose a novel object detection framework that combines unsupervised denoising network into traditional two-stage detection network and leverages a strategy for fusing region proposals extracted from both raw SAR image and synthetically denoised SAR image. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. The proposed framework shows better performances when we compared the model with using only noisy SAR images and only denoised SAR images after despeckling under multiple backbone networks.

A Noisy SAR Image Fusion Method Based on NLM and GAN.

The unavoidable noise often present in synthetic aperture radar (SAR) images, such as speckle noise, negatively impacts the subsequent processing of SAR images. Further, it is not easy to find an appropriate application for SAR images, given that the human visual system is sensitive to color and SAR images are gray. As a result, a noisy SAR image fusion method based on nonlocal matching and generative adversarial networks is presented in this paper. A nonlocal matching method is applied to processing source images into similar block groups in the pre-processing step. Then, adversarial networks are employed to generate a final noise-free fused SAR image block, where the generator aims to generate a noise-free SAR image block with color information, and the discriminator tries to increase the spatial resolution of the generated image block. This step ensures that the fused image block contains high resolution and color information at the same time. Finally, a fused image can be obtained by aggregating all the image blocks. By extensive comparative experiments on the SEN1–2 datasets and source images, it can be found that the proposed method not only has better fusion results but is also robust to image noise, indicating the superiority of the proposed noisy SAR image fusion method over the state-of-the-art methods.

Speckle2Void: Deep Self-Supervised SAR Despeckling With Blind-Spot Convolutional Neural Networks

Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, and hence, despeckling is a crucial preliminary step in scene analysis algorithms. The recent success of deep learning envisions a new generation of despeckling techniques that could outperform classical model-based methods. However, current deep learning approaches to despeckling require supervision for training, whereas clean SAR images are impossible to obtain. In the literature, this issue is tackled by resorting to either synthetically speckled optical images, which exhibit different properties with respect to true SAR images, or multitemporal SAR images, which are difficult to acquire or fuse accurately. In this article, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained by employing only noisy SAR images and can, therefore, learn features of real SAR images rather than synthetic data. Experiments show that the performance of the proposed approach is very close to the supervised training approach on synthetic data and superior on real data in both quantitative and visual assessments.

Multilevel Wavelet-SRNet for SAR Target Recognition

Speckle noise is an important factor affecting the accuracy of synthetic aperture radar (SAR) target recognition. Traditional speckle reduction methods based on transform domain and spatial filtering usually require professional experience to set the threshold, which will also affect the recognition accuracy. This letter proposes a multilevel wavelet speckle reduction network (Wavelet-SRNet) for noisy SAR images target recognition. First, the method designs the wavelet soft threshold denoising method as a trainable neural network module in the convolutional neural network (CNN) framework. Then, a two-level wavelet denoising branch is constructed and fused with the original noisy image. Finally, we cascade a CNN-based classification model on the above structure to form an SAR image target recognition network whose denoising threshold can be automatically learned. Experiments on the moving and stationary target acquisition and recognition database show that the classification accuracy of the proposed method for target recognition in noisy SAR images is better than the compared state-of-the-art methods. Also, the method achieved high test accuracy in the noise augmentation experiment.

SAR image despeckling using deep CNN

Synthetic aperture radar (SAR) images are contaminated with noise called speckle that is multiplicative in nature. The presence of speckles in SAR images makes it impossible to understand and interpret for extensive range of applications. However, certain characteristics of SAR and the ability to function irrespective of weather conditions, are making such images worth processing in order to be able to extract relevant information. A despeckling model is proposed that uses deeper convolutional neural networks, which was never used before, as far as authors are concerned, for diminishing speckle in noisy SAR images. Multiple skip connections from the ResNet model are also employed in authors' proposed architecture. In order to maintain uniformity, a formula to be followed while applying skip connections is also derived. A hybrid loss function is developed to train the network more consistently to achieve the desired output. Experiments on simulated SAR images using the NWPU-RESISC benchmark are conducted and tested on real TerraSAR-X images and compared with the state-of-the-art techniques. Results show that the proposed method achieved considerable improvements compared to state-of-the-art methods with PSNRs 27.02, 24.60, and 22.01 for looks 10, 4, and 1, respectively.

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.

An Efficient Segmentation Method for Mariculture Areas on Airborne SAR Images

AbstractIn this paper, the problems of mariculture area segmentation and corresponding area value estimations are investigated on the basis of airborne synthetic aperture radar (SAR) images. In order to deal with a limited amount of noisy airborne SAR image data in an efficient way, an effective coarse-to-fine approach is proposed, consisting of three major components, including (1) an adaptive segmentation method for each local patch to remove noise from the ocean background, (2) a dynamic coarse-to-fine clustering method for grouping pixels to achieve image segments, and (3) a polygon-fitting-based algorithm to obtain regular borders for each region and corresponding area value. Some feasible experiments are operated based on the restricted airborne SAR images, and the effectiveness of the proposed algorithm is validated in terms of the provided pixel level evaluation annotations.

Ground Target Classification in Noisy SAR Images Using Convolutional Neural Networks

Speckle noise is an inherent but annoying property in the synthetic aperture radar (SAR) imaging. In this paper we investigate the influence of speckle on the classical convolutional neural network (CNN) for SAR target classification. Then a dual stage coupled CNN architecture, named despeckling and classification coupled CNNs (DCC-CNNs), is proposed to distinguish multiple categories of ground targets in SAR images with strong and varying speckle. It first applies the despeckling sub-network for noise reduction. After that, residual speckle features as well as target information would be learned by the classification sub-network in order to solve the noise robustness problem of CNN. Besides, a new quantitative measure is developed for the quality assessment of SAR target images. It takes into account structural properties of the speckled SAR image of the target of interest and consistency with visual perception. Finally, a series of comparative experiments and discussions are carried out to validate the proposed assessment criterion and DCC-CNNs. Using synthetic SAR images based on the public MSTAR datasets, results show that the overall classification accuracy for ten ground target classes could be higher than 82% at a variety of speckle noise levels.

Oil Spill Segmentation via Adversarial $f$ -Divergence Learning

We develop an automatic oil spill segmentation method in terms of $f$ -divergence minimization. We exploit $f$ -divergence for measuring the disagreement between the distributions of ground-truth and generated oil spill segmentations. To render tractable optimization, we minimize the tight lower bound of the $f$ -divergence by adversarial training a regressor and a generator, which are structured in different forms of deep neural networks separately. The generator aims at producing accurate oil spill segmentation, while the regressor characterizes discriminative distributions with respect to true and generated oil spill segmentations. It is the coplay between the generator net and the regressor net against each other that achieves a minimal of the maximum lower bound for the $f$ -divergence. The adversarial strategy enhances the representational powers of both the generator and the regressor and avoids requesting large amounts of labeled data for training the deep network parameters. In addition, the trained generator net enables automatic oil spill detection that does not require manual initialization. Benefiting from the comprehensiveness of $f$ -divergence for characterizing diversified distributions, our framework can accurately segment variously shaped oil spills in noisy synthetic aperture radar images. Experimental results validate the effectiveness of the proposed oil spill segmentation framework.

SAR image denoising based on patch ordering in nonsubsample shearlet domain

Synthetic aperture radar (SAR) has been extensively adopted in a variety of fields, e.g., agriculture and marine fields. In this regard, the improvement of SAR image quality has aroused a wide concern worldwide. In recent years, image processing based on local patches has been very popular and proven feasible. In this paper, a novel SAR image denoising algorithm is proposed in the NSST domain on the basis of patch ordering. First, the shearlet transform is applied to logarithmic transformation of the noisy SAR image. Second, the coefficients of the shearlet are denoised respectively by combining patch ordering and 1D filtering. Finally, the denoised SAR image can be obtained by exponential transformation after applying the inverse shearlet to denoised coefficients. The experimental results show that the proposed method not only effectively suppresses the speckle noise and improves the PSNR and ENL of denoising the SAR images but also obviously improves the visual effects of the SAR images, especially in maintaining the image edge and texture information.

Learning a Dilated Residual Network for SAR Image Despeckling

In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose a novel deep learning approach by learning a non-linear end-to-end mapping between the noisy and clean SAR images with a dilated residual network (SAR-DRN). SAR-DRN is based on dilated convolutions, which can both enlarge the receptive field and maintain the filter size and layer depth with a lightweight structure. In addition, skip connections and a residual learning strategy are added to the despeckling model to maintain the image details and reduce the vanishing gradient problem. Compared with the traditional despeckling methods, the proposed method shows a superior performance over the state-of-the-art methods in both quantitative and visual assessments, especially for strong speckle noise.

Speckle suppression in synthetic aperture radar ocean internal solitary wave images with curvelet transform

This paper proposes a speckle-suppression method for ocean internal solitary wave (ISW) synthetic aperture radar (SAR) images by using the curvelet transform. The band-shaped signatures of ocean ISWs in SAR images show obvious scale and directional characteristics. The curvelet transform possesses a very high scale and directional sensitivity. Therefore, the curvelet transform is very efficient in analyzing wave signals in SAR images. A noisy ocean ISW SAR image can be decomposed at different scales, directions, and positions using the curvelet transform. The information of the ISWs is centralized in the curvelet coefficients of certain directions under certain scales, whereas the speckle noise is distributed in every scale and direction. By manipulating the curvelet coefficients, the signals of the ISWs can be extracted from the noisy SAR image. Finally, the speckle noise is suppressed and the ISW feature is enhanced by adding the signals of the ISWs back to the original SAR image. Experiments demonstrate the effectiveness of this method.

Supervised Constrained Optimization of Bayesian Nonlocal Means Filter With Sigma Preselection for Despeckling SAR Images

Speckle reduction is an important problem in synthetic aperture radar (SAR) image analysis. Recent years have seen how Bayesian filters emerge as the natural extension of the nonlocal means filters, providing a general framework to deal with multiplicative (speckle) noise. In this paper, we present an easy-to-use software tool applying an evolutionary algorithm to optimize a Bayesian nonlocal means filter with sigma preselection for denoising SAR images. The desired result is a filtered image having a significative reduction in its variance but preserving the original mean value of the noisy image. A mixed-integer constrained optimization problem is stated and solved with the human intervention, where the user assists the evolutionary algorithm to reduce the noisy image variance under the restriction of keeping the mean value of the noisy SAR image within a predetermined interval of acceptance. We apply the methodology to a set of synthetic and real SAR speckle corrupted images. The results through the evaluation of objective global and local quality criteria show the excellent potential of the proposal.