Synthetic Aperture Radar (SAR) images are crucial for maritime vessel detection; however, challenges such as blurred ship edges, strong land scattering interference, and angular regression mismatches across varying target sizes hinder accurate rotational localization. In this paper, an oriented decoupling target detection method (R-MCLST) is proposed to address these issues. The method integrates three key modules: a multi-channel positioning module (MC-PM) that employs distributed average pooling and additional coordinate channels to enhance orientation awareness; a soft threshold-based multilayer perceptron (ST-MLP) that effectively mitigates background interference while robustly extracting complex features; and a Gaussian distribution-based prediction box (GD-BPB) that transforms rotated bounding box encoding into a two-dimensional Gaussian distribution using KL divergence for adaptive parameter adjustment. Experimental evaluations on the R-SSDD and MR-HRSID datasets demonstrate that R-MCLST achieves superior performance, with the R-SSDD dataset yielding AP50 of 87.48%, AP75 of 34.96%, AP of 41.15%, and AR of 46.52%, and the MR-HRSID dataset yielding AP50 of 61.59%, AP75 of 4.96%, AP of 19.13%, and AR of 22.24%. Comparative analyses confirm that the proposed method outperforms current state-of-the-art networks in accurately localizing rotating targets under challenging SAR imaging conditions.

Rapid and accurate prediction of the sea clutter amplitude distribution is essential to improve target detection capability in synthetic aperture radar (SAR) imagery. In this letter, we propose a sea clutter amplitude network (SCA-Net) based on multitask learning for sea clutter amplitude distribution prediction (SCADP) of SAR images. To reduce the number of model parameters, we design a shallow residual network structure with four residual blocks and replace the normal convolution with depthwise separable convolution in the residual blocks. The efficient channel attention (ECA) module is incorporated into each residual block to strengthen the model’s feature extraction capability. To validate the performance of the model, we construct a SCADP dataset using GaoFen-3 wave mode data. The experimental results on the SCADP dataset indicate that the proposed method achieves the highest prediction accuracy, which proves that the method can effectively achieve integrated prediction of amplitude distribution types and parameters of sea clutter.

Ship detection in remote sensing images has been attracting a lot of attention due to its great application value in both military and civilian fields. However, ships in high-resolution remote sensing images are characterized by the remarkable features of multiscale, arbitrary orientation, and dense arrangement, which is a great challenge for fast and accurate target detection. In order to solve problems, we propose a YOLOV5-based oriented ship detection method of remote sensing images with contextual global attention mechanism and lightweight task-specific context decoupling (CGTC-RYOLO) in this article. First, a cross-stage partial context transformer (CSP-COT) module is introduced to capture global contextual spatial relations using multihead self-attention (MHSA) to verify their implications in implicit dependencies. Second, we propose an angle classification prediction branch in the YOLOV5 head network for detecting targets in any direction and design probability and distribution loss function (PrfoIoU) to optimize the regression effect. Third, the lightweight task-specific context decoupling (LTSCODE) for target detection is employed to replace the original head in the YOLOV5 model, which is used to solve the accuracy problem caused by YOLOV5’s hybridization of classification and localization. Ablation experiments demonstrate the importance and effectiveness of each module. Compared with the benchmark model, the CGTC-RYOLO has the 5.9%, 3.7%, and 4.3% mAP improvements on the DOTA-ship dataset, the HRSC2016 dataset, and the UCAS-AOD dataset, respectively. Moreover, the model’s generalization is also validated. Compared with state-of-the-artmethods, the CGTC-RYOLO can achieve better accuracy and fewer parameters.

Synthetic aperture radar (SAR) and optical images possess complementary strengths, offering rich spatial and spectral information. The intelligent classification of features through image fusion of SAR and optical presents both opportunities and challenges. However, fusion and intelligent classification encounter hurdles. Different physical properties and imaging principles between SAR and optical images often lead to sensor property mismatches, causing information loss. Moreover, optical images are susceptible to weather conditions, while SAR images suffer from scattering noise interference. In addition, the nonuniform distribution of feature categories results in sample imbalance. To address these problems, this article proposed a new fusion network structure dual-encoder net (DEN). First, without increasing the model complexity, considering the differences in the performance of features under different sensors, this network was keyed to a composition of two encoders that were able to utilize their respective features to encode and reduce the impact of modal differences. Second, a detail attention module (DAM) was constructed to capture the detailed information that was obscured by the optical image and acquired by the SAR image. Finally, a new loss function, comprising weighted information loss, pixel loss, and noise loss, was introduced to mitigate sample imbalance, retain key information, and reduce noise effects. The experimental results showed that the proposed method outperforms the current popular image fusion methods, and the model complexity was improved by 15.3% while the overall accuracy (OA) was improved by 2.6%, and the entropy, peak signal-to-noise ratio (PSNR), and mean square error (MSE) were improved by 29%, 27%, and 7%, respectively.

Ship classification in synthetic aperture radar (SAR) images is a challenge in the field of ocean monitoring. On the one hand, there are few labeled samples in SAR remote sensing ship datasets, and a commonly used single classification criterion cannot effectively represent the distribution of categories. On the other hand, the small size of the SAR ship and the inconspicuous appearance characteristics lead to the fact that the SAR ship samples are with less discriminative information; therefore, the rich feature space of a ship cannot be effectively obtained, which increases the difficulty of target distinguishability. A multibranch embedding network with bi-classifier (MBEN-BC) model was proposed to address these problems and for few-shot SAR ship classification. First, the MBEN module was utilized to extract the multiscale feature map spatial information of the input image at multiple levels and establish cross-channel information interaction so as to obtain discriminative features at the local and global levels, which effectively enriched the feature space. Then, the BC module was constructed to represent the image features from the image level and descriptor level, respectively, and the two classification criteria were presented to promote a more compact distribution of similar samples in the feature space in order to effectively represent the distribution of categories with a small number of labeled samples. Experimental validation was carried out using the FUSAR-Ship, Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and OPENSAR-Ship dataset, and the MBEN-BC method achieved superior performance and good generalization ability compared to the current popular and state-of-the-art few-shot methods.

Convolutional Neural Networks (CNNs) have achieved remarkable breakthroughs on remote sensing tasks in recent years. However, deploying CNNs for real-time remote sensing on-board processing still remains a challenge due to power consumption, real-time and other limitations. Therefore, in this article, a satellite-based real-time remote sensing accelerator is proposed, where algorithm and hardware approaches are proposed to jointly optimize CNNs’ deployment on edge-side aerospace devices. Firstly, a collaborative-trainable sparse-quantization (CTSQ) method is proposed to reduce the model’s storage overhead. In the CTSQ method, analysis of the errors is performed for the sparsity-quantization composition. Besides, the inter-channel correlations among parameters are leveraged, where the structured sparsity and quantization are performed with fine-grained units. Secondly, a modular-system co-optimized (MoSyC) architecture is proposed. A hardware-mapped sparse access (HMSA) strategy is proposed to effectively filter out zero elements in sparse parameters. Moreover, a high-throughput architecture is designed for parallel and pipelined data flow control. Finally, extensive experiments are conducted on both scene classification and object detection tasks with ResNet and YOLOv5 models. The results show that the proposed CTSQ method achieves the compression ratio of more than 13.81 times, and the proposed MoSyC architecture achieves the throughput of more than 1815 GOPS, demonstrating the effectiveness of the proposed accelerator.

Target detection is of vital importance to maritime security and maritime resource protection. However, the detection of small or high state targets is difficult based on traditional methods, for targets are easy to be submerged in sea clutter. In this paper, by using the Polarimetric differences of targets and sea clutter, a new polarized detector, multi-feature fusion Geometrical Perturbation–Polarimetric Notch Filter (GP-PNF) is proposed. To make the use of polarization features, a feature dimension reduction method is introduced to reduce the redundancy and the computational complexity, so as to extract new polarization features for the design of the new detector. Radarsat-2 full-Polarimetric SAR data are used to verify the effectiveness of the proposed method. The performances of full-, compact- and dual-Polarimetric SAR detectors are evaluated. The results demonstrated that the proposed method perform better than K-CFAR, G0-CFAR methods.

Wave breaking significantly influences the scattering mechanism at the sea surface. Therefore, investigating wave breaking is crucial for understanding the microwave scattering mechanism at the sea surface. This paper presents a study on wave breaking contribution under small incidence angles, building upon the analyzed characteristics of wave breaking contribution. We propose a backscattering model that combines wave breaking at small incidence angles with small slope approximation. Additionally, we execute a spectrum cutoff, leveraging the dominant relationship between incidence wave and their corresponding sea surface roughness detection capabilities. This method not only further constrains the spectrum cutoff range but also substantially decreases the computational complexity, all while maintaining the core computational content.

Polarimetric SAR has been widely used in ship detection. In this paper, the Doppler information between polarization channels is extracted based on the covariance matrix elements, and the joint description of polarization characteristics and Doppler characteristics for targets is realized. On this basis, two new ship detectors considering Doppler information are designed. The experimental results show that the proposed method can maintain a good ship detection effect, and to a certain extent inhibit the false alarms generated by the land, thus improving the ship detection performance.

Sea clutter is an important factor for the detection of sea surface targets in radar images. However, only limited time and local sea clutter samples can be obtained currently, which cannot cover the ever-changing marine environment. The generation of sea clutter data from unknown sea areas based on complex marine environments has important theoretical significance and application value. Therefore, a sea clutter data generation method based on Pix2Pix is proposed for SAR images. The nonlinear mapping relationship between wave spectrum and SAR image spectrum is learned by 2912 pairs of SAR images and ERA-5 wave spectrum data. Thus, the network can generate matched sea clutter images by inputting real marine environment information (wave spectrum) after training. Finally, the image similarity index and histogram model fitting are used to verify the effectiveness of the proposed method.

Ocean wave is of great significance in marine environment prediction, maritime navigation, and global climate change. Synthetic aperture radar (SAR) is widely used in ocean wave spectra retrieval due to its 2-D high resolution, all-weather, and all-time advantages. Nevertheless, the nonlinear mapping between SAR and ocean waves, caused by velocity bunching, hinders the advancement of wave spectra inversion techniques, resulting in low-quality and incomplete wave spectra. To overcome the problem, a novel deep learning model SAR2WV for ocean wave spectra retrieval based on Pix2pix is proposed by constructing the nonlinear mapping relationship of SAR cross spectra and ocean wave spectra. A total of 106 844 Sentinel-1 wave mode dataset along with the corresponding European Centre for Medium-Range Weather Forecasts (ECMWF) ERA 5 wave data is processed and used for training the SAR2WV model. Experiments demonstrate that the proposed SAR2WV model can significantly improve the accuracy of the retrieved wave spectra and wave parameters, with the spectra similarity improved by 60.3%, root-mean-square error (RMSE) of significant wave height (SWH) decreased from 0.966 to 0.386 m, RMSE of mean wave period (MWP) decreased from 1.208 s to 0.811 s, and correlation coefficient of peak wave direction increased from 0.65 to 0.72, which achieves better performance than ocean swell wave spectra (OSW) algorithm and other methods.

Sea surface temperature (SST) is one of the most important parameters in the global ocean-atmosphere system. Predicting SST can help to analyze and identify extreme weather and protect marine environment in advance. Traditional numerical and machine learning methods tend to ignore spatial features. The single model in existing deep learning methods suffers from weakening spatial features and reducing ability of discriminating time-series information. At the same time, rare consideration about the influence of ocean physical phenomena has been given. These will lead to inaccurate prediction results. Based on the spatial-temporal characteristics and physical laws of the SST field, this paper proposes a hybrid multi-scale spatial-temporal model combining error correction map (ECM-HMSTM) to predict the SST. First, the ECM-HMSTM can comprehensively extract the spatial-temporal features of the SST field at different scales and thus the SST prediction map can be obtained. Second, by a new error correction approach based on the activity of tropical instability waves (TIWs), the ECM-HMSTM can effectively predict the variation characteristics of TIWs signals, which results in producing the error correction maps. Third, by fusing the two above maps, the SST field in the tropical eastern Pacific Ocean after five days is predicted. Experiment results show that the accuracy of the ECM-HMSTM was improved by 10.3% compared with the current state-of-the-art deep convolution model. Moreover, the SST predicted by the ECM-HMSTM performs well on characterizing the intensity of TIWs. Therefore, this paper provides a strategy for effective short-term prediction of SST fields, which is of guidance for prediction and analysis of ocean phenomena and climate.

This paper introduces an innovative approach in Synthetic Aperture Radar (SAR) polarimetry and proposes a novel descriptor called polarimetric autocorrelation matrix. Different from polarimetric covariance and coherency matrices, the polarimetric autocorrelation matrix can capture hidden Doppler information in the frequency domain and encode it in the phase using higher-order statistical methods. This matrix facilitates the joint extraction and analysis of polarization and Doppler information from fully Polarimetric SAR (PolSAR) data through matrix analysis. The paper explains that the polarimetric autocorrelation matrix can be decomposed into a Doppler-related matrix and a covariance-related matrix. The magnitudes and phases of these matrices provide insight into Doppler shifts between different polarizations and the variance of the backscattering coefficient. Our research demonstrates how the Doppler shift is influenced not only by the target’s radial velocity but also by radar polarization. Four quad-polarimetric RADARSAT-2 images are used for testing in this study, and a set of characterization features and parameters are derived from the polarimetric autocorrelation matrix. The novel descriptor, together with the new parameters, can detect man-made target and sea ice, mitigate ambiguity caused by moving targets, and indicate the motion status of ship targets and sea currents. Specifically for marine scenes, our data found Doppler differences in HH polarization and VV polarization induced by sea surface motion can be up to 100 Hz.

Altimeters, spectrometers, scatterometers, and synthetic aperture radars (SARs) are widely used for detecting marine dynamic elements. The development of multimode integrated microwave remote sensors has become a trending research topic in the field of microwave remote sensing; a single load on a satellite presents relatively few functions, and multiple loads on a satellite create large volume and mass and high operational risks. The system parameters of a multimode integrated microwave remote sensor are designed, and then the minimum energy of the transmitted signal is taken as the optimization objective function. The constraints are defined in many aspects, and a time sequence optimization model of the signal for the multimode integrated microwave remote sensor is established. The genetic algorithm is used to solve the established optimization model. The simulation results show that the proposed optimization method can design a signal timing that meets a variety of constraints and requires minimal energy.

Coast-transmit ship-receive (CTSR) bistatic high-frequency surface wave radar (HFSWR) can fully exploit the flexibility of moving platforms and the anti-interference advantages of bistatic radar. However, the platform motion can cause the spread of target echo in the frequency spectrum and reduction of amplitude, which is not conducive to detection. In this letter, a motion compensation method using a direct wave signal is proposed for CTSR bistatic HFSWR. First, the frequency shift characteristics of direct wave signal and target echo are analyzed by simulation. The simulation results show that the platform motion has a similar modulation form on both target echo and direct wave signal, and their difference is mainly caused by different azimuths. In addition, the direct wave signal is only affected by the platform motion, so it can be used to obtain the platform motion effect. Then, the proposed method uses a direct wave signal as the reference information to estimate and eliminate the phase modulation caused by the platform motion. At last, the effectiveness of the method is verified by the experiment based on simulated and measured attitude data.

The freeboard height of the ship is a critical parameter that mirrors the ship’s load capacity and safety performance. However, research on the height of the ship is less explored. This letter derives imaging differences between the top and bottom of the ship’s freeboard based on SAR imaging geometry and then establishes a ship-sea coupling scattering path model. Relying on the proposed model and the polarimetric synthetic aperture radar’s (PolSAR) capability to differentiate various scattering mechanisms, a method for retrieving the freeboard height of ships is proposed. This method primarily utilizes the total backscattering power SPAN and double-bounce scattering component (DBL) features of single-pass PolSAR data acquired with a single antenna. Finally, the proposed method is verified by the in situ data and tested on different types of ships, such as cargo ships and bulk carriers, and the absolute relative error (ARE) of the retrieval results is less than 6.1%.

Thanks to the powerful feature extraction and expression ability of convolutional neural networks (CNNs), exceptional success has been achieved in the field of ship automatic target recognition (ATR) of synthetic aperture radar (SAR). However, the CNNs cannot work effectively with sparse labelled samples and imbalanced categories.This study proposes a new Attention-Dense-CycleGAN (ADCG) method that is suitable for the ship transfer learning task from optical to SAR (OPT2SAR). The key improvement of the ADCG lies in the construction of a Dense Connection Module (DCM) and a lightweight Convolutional Block Attention Module (CBAM). The DCM is able to overcome the problems of generator feature redundancy, large network model parameters, and severe training time in the original CycleGAN network. The lightweight CBAM can solve the problem of not being able to locate the main features of ships with a minimal increase in network parameters. Compared with the performance of other popular generative adversarial networks, the superior performance of the ADCG in the OPT2SAR transfer learning is demonstrated with the Fréchet Inception Distance (FID) minimum of 76.04 and the Kernel Inception Distance (KID) minimum of 0.0403. Finally, the ability of pseudo-SAR domain images were tested to improve the recognition accuracy of popular ship classification networks, this achieved an average improvement of 6% in recognition accuracy. Therefore the results of this study verifies the rationality, validity, and application value of pseudo-SAR domain in solving the problems of sparse marker samples and class imbalance in ship ATR network model.

With the development of deep learning (DL), research on ship classification in synthetic aperture radar (SAR) images has made remarkable progress. However, such research has primarily focused on classifying large ships with distinct features, such as cargo ships, containers, and tankers. The classification of SAR fishing vessels is extremely challenging because of two main reasons: 1) the small size and minor interclass differences of fishing vessels make learning fine-grained features difficult, and 2) determining fishing vessel types is difficult, resulting in a lack of labeled data. Hence, after designing a process framework for vessel tagging, we construct a high-resolution fine-grained fishing vessel classification dataset (FishingVesselSAR), which contains 116 gillnetters, 72 seiners, and 181 trawlers. We then propose a novel DL model (FishNet) that aims to strengthen feature extraction and utilization. In FishNet, we introduce four innovative modules to ensure superior performance in SAR fishing vessel classification: a multipath feature extraction (MUL) module, a feature fusion (FF) module, a multilevel feature aggregation (MFA) module and a parallel channel and spatial attention (PCSA) module. Furthermore, we design an adaptive loss function to achieve better classification performance by mitigating the effects of class imbalance. In this paper, we report extensive ablation studies conducted to confirm the efficacy of the five improvements listed above. Sufficient comparisons with 33 advanced methods from the DL and SAR target classification communities demonstrate that FishNet achieves a SAR fishing vessel classification accuracy of 89.79%, which is 6.77% higher than that of the second-best method.

In this paper, sea ice classification on a remote sensing image given just a small number of labeled pixels is investigated. Effective sea ice classification is rendered from two aspects. First, a feature extraction method is developed. It extracts the context feature from a classification map. Second, an iterative learning paradigm is established. The labeled pixels are divided into two training subsets. At each iteration, the context feature for one subset is extracted from the classification map which is obtained subject to the other subset. Therefore, the two subsets mutually guide each other for updating the context feature in an iterative manner, which finally renders effective sea ice classification. The above paradigm is referred to as mutually guided contexts. The advantages of the new paradigm are two-fold. First, the context feature enriches the sea ice image representation in a general manner regardless of the types of raw image data. Second, the two training subsets keep providing different refined classification maps for each other such that the comprehensiveness of the context feature is recursively enhanced. Therefore, the paradigm of mutually guided contexts comprehensively characterizes the sea ice image representation for training and classification even when only small training data are available. Experiments validate the effectiveness of the mutually guided contexts for sea ice classification.

Taking advantage of AIS data to mine the dynamic characteristics of fishery resource exploitation helps to carry out scientific management of fishery and realize the sustainable development of marine resources. The paper selected 210 million records of AIS data of approximately 115,000 fishing vessels in the six Chinese fishing grounds. After processing the AIS dataset for fishing activities and fishing vessel types identification, we conducted a thorough mining and analysis of the characteristics of fishing vessel activities in winter and spring of 2019. The results showed that the number of fishing vessels was gradually increasing as the latitude decreased in winter, and that were quite different between winter and spring in the northern fishing grounds. Gillnetters were the most numerous fishing vessel type operating in the inshore fishing grounds with increased in spring, while seiners had an absolute advantage in the Xisha-Zhongsha fishing ground.

The azimuth cutoff wavelength of SAR is an important parameter for retrieval of sea surface wind and wave. Earlier studies have fully demonstrated the substantial dependence of azimuth cutoff wavelength on polarization, but the present studies only focus on H-V linear polarization bases (HH, HV/VH, and VV) without considering the effects of other polarization bases (e.g., linear rotated, circular, and elliptical polarization). Benefiting from the quad-polarization advantage of GaoFen-3 SAR wave mode data and the support of polarization basis transformation theory, this study used 4,648 SAR data to study the correlation between cutoff wavelength and wind and wave parameters (e.g., significant wave height, and wind speed) under different polarization bases, and analyzed the variation of correlation coefficient caused by polarization basis change. Finally, the results were applied to evaluating the performance of wind and wave parameters retrieval. The results of the study show that the azimuth cutoff is strongly dependent on the polarization state of electromagnetic wave. The azimuth cutoff wavelength under the elliptical polarization bases has higher correlation with wind and wave than that under H-V linear, circular, and linear rotated polarization bases. Using the azimuth cutoff wavelength of the elliptical polarization bases can significantly improve the retrieval accuracy of wind and wave parameters. This study shall enhance the capabilities of polarized SAR systems to precisely derive more ocean surface properties. The result implies that polarization basis is an important factor that must be considered in future ocean SAR studies.

Ship classification using Synthetic Aperture Radar induces effective marine applications but suffers from imbalanced datasets. Common ship types (majority classes) contain many more instances than rare ship types (minority classes), resulting in performance loss since minority instances tend to be ignored. Meanwhile, it is difficult and time-consuming to produce reliable instances for rare ships. The synthetic minority oversampling techniques have shown great potential to balance the distribution of classes by synthesizing minority instances. However, the newly synthesized instances may overlap with the majority instances, reducing the separability among classes, or being far away from the classification boundary, which is meaningless. This paper proposes a clustering-based size-adaptive safer oversampling technique to address the imbalanced classification problem. Proven schemes, including cluster minority instances, adaptively allocate oversampling sizes, and assign weights are adopted for selecting minority instances. Then, new instances are synthesized according to the safe metric of selected instances, instead of randomly inserted. Furthermore, multiple handcrafted features are tested to provide a clearer classification boundary. The proposed comprehensively considers the usefulness and safety of synthesizing instances. Experiments on the OpenSARShip and the FUSAR-Ship datasets demonstrate that the proposed technique achieves significantly better results.

Regarding the imaging of circular scan inverse synthetic aperture radar (ISAR), the rapid circular scan of the antenna expands the beam coverage area. However, how to determine the rotation speed of the antenna is still a difficult problem. This paper proposes an antenna speed optimization model to quantify the antenna rotation speed. Under the constraints of the beam coverage area per second and the accumulated signal-to-noise ratio (SNR), the value of azimuth resolution is minimized. In addition, to improve the resolution of the image, the split Bregman algorithm is also introduced. This algorithm solves the problem that the azimuth resolution is still lower than the traditional ISAR after the antenna rotation speed is optimized. By optimizing the antenna rotation speed and processing data by the split Bregman algorithm, a super-resolution ISAR image is obtained. The simulation results verify the effectiveness of the method.

The successful launch of the Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) provides a new and advanced tool for sea ice thickness (SIT) estimations in the Arctic. However, the performance of ICESat-2 for SIT estimations still remains unknown. In the present study, SIT estimates derived from ICESat-2 are examined using three retrieval methods, namely, two buoyancy methods with the merged snow depth and empirical snow depth (BMA and BME, respectively) and one empirical estimation method (EEM), and these estimates are compared to near-simultaneous airborne measurements from the IceBird mission in April 2019. Overall, the ICESat-2 total freeboard registers quite well with that from the near-concurrent IceBird mission with a mean bias of 2.5 cm, which demonstrates the high reliability of ICESat-2 data for SIT estimation. However, the much more evident difference between SIT estimations than total freeboard from ICESat-2 and IceBird indicates that other parameters (e.g., snow depth and snow/ice densities) may bring increased uncertainties to the SIT estimation. Overall, BMA is the best method for SIT estimation and has the closest thickness distribution to that of IceBird data with a mean bias of 0.11 m, followed by the BME and EEM methods. The dominate error sources for SIT estimation using the buoyancy method are ice density and snow depth that require further investigation in future studies.

This paper proposes a new scheme for detecting ship targets in high-resolution (HR) single-channel synthetic aperture radar (SAR) images. By using the proposed spatially enhanced pixel descriptor (SEPD) and the modified density-based spatial clustering of application with noise (M-DBSCAN), this scheme can overcome typical challenges of ship detection in HR SAR images. Specifically, the proposed SEPD maps the representation for a given pixel in an SAR image into a high-dimensional feature space by embedding spatial and intensity information of its neighborhood synchronously. It enables the spatial structure information of ship targets and textural information of the sea surface to be preserved by the SEPD feature vector, leading to a significant improvement in the separability between ship targets and sea clutter. A statistical study shows that, in SEPD feature space, a large amount of pixels belonging to sea clutter gather densely in the low-value region and are surrounded by a tiny proportion of ship targets that are distributed sparsely in the high-value region. This distribution characteristic motivates us to apply a density-based clustering approach to distinguish ship targets from the sea clutter. To overcome the weakness of original DBSCAN clustering algorithm and make it suitable for the requirements of ship detection in SAR images, we propose the method of M-DBSCAN, which introduces three critical improvements, including a new dimensionality independent distance metric, a one-class clustering strategy, and an entirely deterministic approach to border points. A novel ship detector is proposed by applying M-DBSCAN to cluster pixels that are represented by SEPD descriptor. Comprehensive experiments demonstrate that the proposed method outperforms other intensity-based clustering methods ($k$ -means and fuzzy c-means), and widely used intensity threshold-based method (constant false alarm rate detector) in most circumstances, and can effectively handle various challenging situations appearing in HR images, such as sidelobes, small/weak targets, moving targets, and so on.

Sea ice type is one of the most sensitive variables in Arctic ice monitoring and detailed information about it is essential for ice situation evaluation, vessel navigation, and climate prediction. Many machine-learning methods including deep learning can be employed for ice-type detection, and most classifiers tend to prefer different feature combinations. In order to find the optimal classifier-feature assembly (OCF) for sea ice classification, it is necessary to assess their performance differences. The objective of this letter is to make a recommendation for the OCF for sea ice classification using Cryosat-2 (CS-2) data. Six classifiers including convolutional neural network (CNN), Bayesian, K nearest-neighbor (KNN), support vector machine (SVM), random forest (RF), and back propagation neural network (BPNN) were studied. CS-2 altimeter data of November 2015 and May 2016 in the whole Arctic were used. The overall accuracy was estimated using multivalidation to evaluate the performances of individual classifiers with different feature combinations. Overall, RF achieved a mean accuracy of 89.15%, followed by Bayesian, SVM, and BPNN (~86%), outperforming the worst (CNN and KNN) by 7%. Trailing-edge width (TeW) and leading-edge width (LeW) were the most important features, and feature combination of TeW, LeW, Sigma0, maximum of the returned power waveform (MAX), and pulse peakiness (PP) was the best choice. RF with feature combination of TeW, LeW, Sigma0, MAX, and PP was finally selected as the OCF for sea ice classification and the results that demonstrated this method achieved a mean accuracy of 91.45%, which outperformed the other state-of-art methods by 9%.

In this paper, we address the problem of ship detection in PolSAR image. We firstly investigate the differences of scattering mechanism between ship targets and the sea surface based on the polarimetric similarity analysis. It is shown that, the sea surface scattering is dominated by the odd bounce (denoted as r1), while the scattering of ship targets are both dominated by the even bounce scattering (r2) which has been widely accepted, and the line bounce scattering (r4) which is a new find from the experiments. Based on those differences, a metric (r2+r4)/r1can be applied to distinguish ship targets from the sea surface. To further suppress the effects of sidelobes and imaging artifacts which have the same/similar scattering behaviors with ship targets, we introduce in the third eigenvalue λ3) of the coherency matrix and obtain the metric (r2+ r4)λ3/r1. The preliminary results show that a constant false alarm rate (CFAR) ship detector based on the proposed metric can obtain promising ship detection performance.

The TanDEM-X constellation is served by two X-band SAR satellites, which fly in close orbit formation acting as a large and flexible single-pass radar interferometer. This paper investigates the potentials for monitoring sea ice in the Bohai Sea with the unique constellation. Our results show that the coherence and interferometric phase of TanDEM-X data can be used to detect sea ice, and the radial velocity of sea ice can be measured with the along-track phase.

We address the problem of sea surface distribution modeling in a synthetic aperture radar (SAR) image by developing an innovative nonparametric method to tackle the main weakness of the traditional Parzen window kernel method, i.e., relatively low computation speed. We derive an explicit analytical solution of modeling sea surface distribution by a composite cubic Bézier curve and propose an adaptive segmentation strategy to improve the modeling precision. A comparative study validates that the average computation time of the proposed method is only 1/60 of the Parzen window kernel method and about 1/6 of the k-root and G0 methods. More importantly, in terms of modeling performance, the proposed method can achieve more adaptability and stability to different SAR sensors, resolutions, and sea scenes. The average goodness of fit tested on eight sea scenes of the proposed method, measured by |R̂̅2̅| (the smaller the better), is only 0.0006 and outperforms that of the Parzen window kernel method (0.0059), k-root (0.0390), and G0 (0.0678).

Selecting discriminate features and constructing an appropriate classifier are two essential factors for ship classification in a synthetic aperture radar (SAR) image. Unfortunately, these two factors are rarely considered together by existing studies. We propose a joint feature and classifier selection method by integrating the classifier selection strategy into a wrapper feature selection framework. The sequential forward floating searching algorithm is improved to conduct efficient searching for an optimal triplet of feature-scaling-classifier. Comprehensive experiments on two data sets demonstrate that the proposed method can select the optimal combination of a nonredundant complementary feature subset, appropriate scaling, and classifier to improve the performance of ship classification in a SAR image.

Probability density function (pdf) estimation of sea clutter in synthetic aperture radar (SAR) imagery has a fundamental role in constructing a constant false alarm rate (CFAR) based ship detector. This paper proposes a semi-parametric sea clutter modeling method for SAR amplitude imagery. The pdf of sea clutter is estimated point by point for each amplitude value, by selecting an optimal component from a given dictionary. For a specific point, the optimal component is selected by measuring the statistical consistency between pdfs of different components and the pdf of sample data within a local window in pdf domain. The statistical consistency is measured by Kullback-Leibler distance (KL-distance). The size of local window is determined based on smoothness criterion. Experimental results on several real SAR imageries demonstrate that the proposed method accurately models the sea clutter, and is flexible to combine with CFAR to construct a ship detector.