DGNet: Distribution Guided Efficient Learning for Oil Spill Image Segmentation

Effective oil spill segmentation in synthetic aperture radar (SAR) images is critical for marine oil pollution cleanup, and proper image representation contributes to effective learning for accurate oil spill segmentation. In this article, we propose an effective oil spill segmentation network named SRCNet, which is constructed by leveraging seminal SAR image representation to empower the learning capability of the proposed segmentation network for accurate oil spill segmentation. Specifically, the image representation utilized in our proposed SRCNet originates from SAR imagery, modeling with the internal characteristics of oil spill SAR image data, which therefore promotes effective learning for accurate oil spill segmentation in the training process. Besides, to conduct enhanced oil spill segmentation, we construct the proposed SRCNet with a pair of deep neural nets that work in a competition manner, where one neural net strives to produce accurate oil spill segmentation maps by drawing samples from the collaborated seminal image representation, while the other tries its best to distinguish between the produced and the true segmentations. It is the competition and the image representation collaborated that drives the proposed SRCNet to operate accurate oil spill segmentation efficiently with small amount of training data. This establishes an economical and efficient way for oil spill segmentation. Additionally, to further improve the segmentation performance of the proposed SRCNet, a regularization term that penalizes the segmentation loss is devised, which encourages the produced segmentation to approach the ground-truth segmentation, promoting the segmentation capability of the proposed SRCNet for accurate oil spill segmentation. Experimental evaluations from different metrics validate the effectiveness of the proposed SRCNet for oil spill segmentation.

We address the application of model-supported exploitation techniques to synthetic aperture radar (SAR) imagery. The emphasis is on monitoring SAR imagery using wide area 2D and/or 3D site models along with contextual information. We consider here the following tasks useful in monitoring: (a) site model construction using segmentation and labeling techniques, (b) target detection, (c) target classification and indexing, and (d) SAR image-site model registration. The 2-D wide area site models used here for SAR image exploitation differ from typical site models developed for RADIUS applications, in that they do not model specific facilities, but constitute wide area site models of cultural features such as urban clutter areas, roads, clearings, fields, etc. These models may be derived directly from existing site models, possibly constructed from electro-optical (EO) observations. When such models are not available, a set of segmentation and labeling techniques described here can be used for the construction of 2D site models. The use of models can potentially yield critical information which can disambiguate target signatures in SAR images. We address registration of SAR and EO images to a common site model. Specific derivations are given for the case of registration within the RCDE platform. We suggest a constant false alarm rate (CFAR) detection scheme and a topographic primal sketch (TPS) based classification scheme for monitoring target occurrences in SAR images. The TPS of an observed target is matched against candidate targets TPSs synthesized for the preferred target orientation, inferred from context (e.g. road or parking lot targets). Experimental results on real and synthetic SAR images are provided.

Ocean oil spill detection from SAR images based on multi-channel deep learning semantic segmentation

In general, synthetic aperture radar (SAR) imaging and image processing are two sequential steps in SAR image processing. Due to the large size of SAR images, most image processing algorithms require image segmentation before processing. However, the existence of speckle noise in SAR images, as well as poor contrast and the uneven distribution of gray values in the same target, make SAR images difficult to segment. In order to facilitate the subsequent processing of SAR images, this paper proposes a new method that combines the back-projection algorithm (BPA) and a first-order gradient operator to enhance the edges of SAR images to overcome image segmentation problems. For complex-valued signals, the gradient operator was applied directly to the imaging process. The experimental results of simulated images and real images validate our proposed method. For the simulated scene, the supervised image segmentation evaluation indexes of our method have more than 1.18%, 11.2% and 11.72% improvement on probabilistic Rand index (PRI), variability index (VI), and global consistency error (GCE). The proposed imaging method will make SAR image segmentation and related applications easier.

The usage of a hypersonic platform for remote sensing application has promising prospects, especially for hypersonic platform-borne synthetic aperture radar (SAR) imaging. However, the high-speed of hypersonic platform will lead to extreme friction between the platform and air, which will cause the ionization of air. The ionized gas forms the plasma sheath wrapped around the hypersonic platform. The plasma sheath will severely affect the propagation of SAR signal and further affect the SAR imaging. Therefore, hypersonic platform-borne SAR imaging should be studied from a physical perspective. In this paper, hypersonic platform-borne SAR imaging under plasma sheath is analyzed. The SAR signal propagation in plasma sheath is computed using scatter matrix method. The proposed SAR signal model is verified by using a ground experiment system. Moreover, the effect of attenuation caused by plasma sheath on SAR imaging is studied under different SAR parameters and plasma sheath. The result shows that attenuation caused by plasma sheath will degrade the SAR imaging quality and even cause the point and area targets to be submerged into the noise. The real SAR images under plasma sheath also illustrate this phenomenon. Furthermore, by studying imaging results under different SAR and plasma parameters, it can be concluded that the severe degradation of SAR imaging quality appears at condition of high plasma sheath electron density and low SAR carrier frequency. The work in this paper will be beneficial for the study of hypersonic platform-borne SAR imaging and design of hypersonic SAR imaging systems in the future.

A probabilistic method has been developed that distinguishes oil spills from other similar sea surface features in synthetic aperture radar (SAR) images. It considers both the radiometric and the geometric characteristics of the areas being tested. In order to minimize the operator intervention, it adopts automatic selection criteria to extract the potentially polluted areas from the images. The method has an a priori percentage of correct classification higher than 90% on the training dataset; the performance is confirmed on a different dataset of verified slicks. Some analyses have been conducted using images with different radiometric and geometric resolutions to test its suitability with SAR images different from European Remote Sensing (ERS) satellite ones. The system and its ability to detect and classify oil and non‐oil surface features are described. Starting from a set of verified oil spills detected offshore and over the coastline, the ability of SAR to reveal oil spills is tested by analysing wind intensity, deduced from the image itself, and the distance from the coast.

In single band and single polarized synthetic aperture radar (SAR) images, the information is limited to intensity and texture only and it is very difficult to interpret such SAR images without any a priori information. For unsupervised classification of SAR images, M-band wavelet decomposition is performed on the SAR image and sub-band selection on the basis of energy levels is applied to improve the classification results since sparse representation of sub-bands degrades the performance of classification. Then, textural features are obtained from selected sub-bands and integrated with intensity features. An adaptive neuro-fuzzy algorithm is used to improve computational efficiency by extracting significant features. K-means classification is performed on the extracted features and land features are labeled. This classification algorithm involves user defined parameters. To remove the user dependency and to obtain maximum achievable classification accuracy, an algorithm is developed in this paper for classification accuracy in terms of the parameters involved in the segmentation process. This is very helpful to develop the automated land-cover monitoring system with SAR, where optimized parameters are to be identified only once and these parameters can be applied to SAR imagery of the same scene obtained year after year. A single band, single polarized SAR image is classified into water, urban and vegetation areas using this method and overall classification accuracy is obtained in the range of 85.92%–93.70% by comparing with ground truth data.

Finding ships in water using high-resolution radar images is goal of synthetic aperture radar (SAR) ship detection, which works in any lighting or weather scenario. By taking advantage of ships' distinct scattering characteristics against water's surface, it is an essential tool for border security, maritime surveillance, and monitoring illicit fishing or trafficking. To accurately recognize ships in synthetic aperture radar (SAR) images in real-time, this study presents AMTNet, a new attention-enhanced multiscale transformer network. Despite abundance of structural information in SAR images, object detection remains a tough task due to speckle noise and diverse backdrops. suggested AMTNet integrates a ResNet-based multiscale convolutional backbone, a spatial attention module (SAM), a channel attention module (CAM), and transformer-based contextual modeling to solve these problems. In addition, a feature exchange system is implemented to address issue of domain gaps that might be generated by differences in environment and sensors in bi-temporal SAR images. To improve accuracy of change detection and localization, this Siamese design allows cooperative exploitation of spatial, temporal, and contextual signals. Compared to top models like MSDFF-Net, GLDet, and LEAD-YOLO, AMTNet outperforms them all on SSDD dataset, with metrics like detection speed (138.5 FPS), accuracy (94.60 percent), recall (95.15 percent), and F1-score (74.87%). Attention processes and feature exchange have been proven to play a key role in ablation research. Another proof of model's practicality is its resilience in face of occlusion and noise. With its excellent performance in a variety of SAR imaging settings and its high interpretability, AMTNet is a computationally economical and effective option for marine surveillance.

The SEASAT satellite system, using an onboard 23-cm-wavelength synthetic aperture radar (SAR), collected approximately 25- to 40-m-resolution radar images of the ocean in 100-km-wide swaths ranging in length from about 300 to 3000 km. Here we report results from the 18 SEASAT SAR passes during the Joint Air-Sea Interaction (JASIN) experiment conducted off the west coast of Scotland in the summer of 1978. These many SAR images, when coupled with the intensive ship, buoy, and aircraft measurements of the JASIN experiment, provide a unique opportunity to assess the ability of satellite SAR to measure ocean surface phenomena, particularly surface wave fields. In this study we use only optically processed SAR images. Although gravity waves of length approximately 80 to 300 m are often seen in SAR imagery, they are not always seen. We find that SAR resolution and wave height are important criteria for determining wave visibility and suggest that wind velocity is also. Comparisons between SAR and buoy estimates of dominant wavelength and direction (including data from several other experiments) agree to within about ±14% and ± 10°, respectively. We use a focus sharpness algorithm to resolve the 180° directional ambiguity of SAR image directional estimates. Correlation of buoy measurements of significant wave height (H 1/3) with peak signal- to-noise ratio in Fourier transforms of SAR images (r = 0.7) suggests that H 1/3 can be estimated to an accuracy of about ± 1 m. However, a similar, but weaker, correlation exists between signal-to-noise and wave length, i.e., H 1/3 and wavelength are correlated in the JASIN data set. SAR image power spectra are in rough agreement with buoy measurements of omnidirectional ocean wave height spectra Ψ(K) and correspond less closely with ocean wave slope spectra Ψ(K) However, the dominant wavenumber (Kpeak.) in SAR spectra typically falls below the dominant wavenumber of corresponding buoy spectra. Further, the slope of SAR spectra for K K Peak is typically less steep than corresponding buoy spectra Ψ(K). These differences between SAR spectra and buoy measurements of form qualitative support for the imaging mechanisms developed by Alpers, Ross, and Rufenach. Analysis algorithms based on this theory, but including empirical modifications, should substantially improve estimates of Ψ (K,θ) using SAR images.

Thanks to the availability of large-scale data, deep Convolutional Neural Networks (CNNs) have witnessed success in various applications of computer vision. However, the performance of CNNs on Synthetic Aperture Radar (SAR) image classification is unsatisfactory due to the lack of well-labeled SAR data, as well as the differences in imaging mechanisms between SAR images and optical images. Therefore, this paper addresses the problem of SAR image classification by employing the Generative Adversarial Network (GAN) to produce more labeled SAR data. We propose special GANs for generating SAR images to be used in the training process. First, we incorporate the quadratic operation into the GAN, extending the convolution to make the discriminator better represent the SAR data; second, the statistical characteristics of SAR images are integrated into the GAN to make its value function more reasonable; finally, two types of parallel connected GANs are designed, one of which we call PWGAN, combining the Deep Convolutional GAN (DCGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP) together in the structure, and the other, which we call CNN-PGAN, applying a pre-trained CNN as a discriminator to the parallel GAN. Both PWGAN and CNN-PGAN consist of a number of discriminators and generators according to the number of target categories. Experimental results on the TerraSAR-X single polarization dataset demonstrate the effectiveness of the proposed method.

This paper proposes a novel method on Synthetic Aperture Radar (SAR) Image denoising, which is based on context modeling combined with multiscale orthogonal bandlet coefficients. For the main influence of SAR image is multiplicative speckle noise, the logarithm uniform transform is used to convert it to additive noise. In this paper, the multiscale orthogonal bandlet transform is applied to noisy SAR Image. The contextual model is used to compute contextual values of bandlet coefficients on each scale. Therefore, bandlet coefficients are reconstructed into some parts by contextual values. The spatially adaptive soft-threshold (T) is to denoise SAR image in each part. Experimental results demonstrate that this method outperforms the methods of Ehance-Lee (E-lee), contextual model based on wavelet domain (Wavelet-context), and Hidden Markov Tree model bases on wavelet domain (Wavelet-hmt) on there indexes: Floating index (FI), Standard deviation and Edge saving index of vertical direction, by using a real SAR image. However, the method can not only reduce the speckle noise but also preserve edges and high frequency information, and gets considerable visual effect on SAR Image denoising.

This paper proposes an Synthetic Aperture Radar (SAR) imaging and detection model of multiple targets at the maritime scene. The sea surface sample is generated according to the composite rough surface theory. The SAR imaging model is constructed based on a hybrid EM calculation approach with the fast ray tracing strategy and the modified facet Small Slope Approximation (SSA) solution. Numerical simulations calculate the EM scattering and the SAR imaging of the multiple cone targets above the sea surface, with the scattering mechanisms analyzed and discussed. The SAR imaging datasets are then set up by the SAR image simulations. A modified YOLOv7 neural network with the Spatial Pyramid Pooling Fast Connected Spatial Pyramid Convolution (SPPFCSPC) module, Convolutional Block Attention Module (CBAM), modified Feature Pyramid Network (FPN) structure and extra detection head is developed. In the training process on our constructed SAR datasets, the precision rate, recall rate, mAP@0.5 and mAP@0.5:0.95 are 97.46%, 90.08%, 92.91% and 91.98%, respectively, after 300 rounds of training. The detection results show that the modified YOLOv7 has a good performance in selecting the targets out of the complex sea surface and multipath interference background.

A novel three-step method to reduce speckle in Synthetic Aperture Radar (SAR) images is presented. First, an edge detector is used to detect the edge orientations in SAR images. Second, using a data processing method named empirical mode decomposition, the SAR image is smoothed along four directions: horizontal, vertical, left diagonal and right diagonal, respectively. Third, the SAR image is reconstructed such that if the edge direction is horizontal, the pixel smoothed along the horizontal direction is used to reconstruct the image, and so on; if an edge is not detected, the mean of the four directionally smoothed images is used to reconstruct the image. Application of this method to SAR images has shown that it is well balanced in the quality of visual appearance, mean preservation, edge preservation, and reduction of the standard deviation.

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.

Ship detection from synthetic aperture radar (SAR) images is a hot topic, but the difficulty in collecting labeled SAR images may hinder the development of deep-learning-based detection methods. Inspired by the idea of domain adaptation, in this article, we propose a hierarchical similarity alignment neural network (HSANet) for ship detection in SAR images, which is a domain adaptive (DA) approach with optical remote sensing images as training samples. The kernel target of HSANet is to mine and align both the global structure and the local instance information between SAR and optical images, where two modules, structural alignment module (SAM) and prototype alignment module (PAM), are designed to, respectively, conduct two hierarchies of alignment process. In general, SAM attempts to extract the global structure similarity which exists in image-level feature representation, while PAM tends to extract the local shape similarity which is instance-level representation. To be specific, SAM is developed by Fourier-based feature alignment, which tries to describe the similar structural relationship between optical and SAR images. Meanwhile, PAM is proposed based on the conjoint confidence analysis where the instance-level ship representations of the source and target domains is aligned. SAM and PAM work together to construct a hierarchical domain adaptation network for SAR ship detection. Experiments on several public datasets may indicate the effectiveness of the proposed method.