Marine Target Research Articles

Localization correction method for underwater sensors network drift with single float-anchor node

Distributed localization method based on wireless sensor networks (WSNs) have been widely used in marine target locating. Main aim of underwater localization is to overcome the influence on acoustic channel and underwater environment to provide a higher accuracy for target exploration and navigation. Unfortunately, affected by the ocean current, sub-anchor nodes in WSNs will drift away from the initial position and led an obvious positioning error for the target. To overcome this difficulty, the paper proposes a novel and efficient method based on one extra float-anchor node (which the precise location is known) to optimize the positioning results. The proposed method consists of three stages: (a) to estimate the location of float-anchor node with sub-anchor nodes; (b) to compare the estimation result and real location of the float-anchor node to calculate the compensation function; (c) to locate the target with sub-anchor nodes and correct the result with compensation function. Simulation experiments clearly show that the proposed method have a significant improvement in the localization accuracy. The paper achieves correction localization method with existed sub-anchor nodes and only one extra float-anchor and obviously improve the positioning accuracy.

Design and Implementation of Marine Automatic Target Recognition System Based on Visible Remote Sensing Images

Gao, X.B., 2020. Design and implementation of marine automatic target recognition system based on visible remote sensing images. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 277-279. Coconut Creek (Florida), ISSN 0749-0208.In the process of visible light remote sensing imaging, different sea surface wave conditions have different reflection ability to illumination, which makes the brightness, contrast and other information of visible light remote sensing images have great changes. Marine ship target recognition is an important application of image processing in remote sensing field. Based on pixel-level fusion of visible and infrared bispectral images, this paper extracts features from fusion results, and recognizes targets in images according to the matching of target image features and template image features. Comprehensive utilization of image preprocessing, image smoothing and anti-cloud interference algorithms can quickly and accurately realize ship target detection under the complex background of land and sea. The experimental results show that the algorithm is effective both in physical mechanism and in actual image effect.

Sea Clutter Suppression for Radar PPI Images Based on SCS-GAN

The problem of strong sea clutter, e.g., sea spikes, may bring in low signal-to-clutter ratio (SCR) and cause great interference to radar marine target detection. However, the sea clutter suppression ability of current algorithms is limited with poor generalization under complex marine environment. In this letter, a novel sea clutter suppression generative adversarial network (SCS-GAN) is designed and employed for marine radar plan-position indicator (PPI) images detection. The SCS-GAN is based on residual networks and attention module, which includes residual attention generator (RAG) and sea clutter discriminator (SCD). In order to expand the data sets and improve generalization ability, clutter-free data set A, simulated sea clutter data set B (containing five types of sea clutter distributions), and actual sea clutter data set C are constructed by means of simulation and acquisition of real radar returns. At last, the parameter, i.e., clutter suppression ratio (CSR) is designed for evaluating the sea clutter suppression performances of the proposed method and other denoising and clutter suppression methods including CBM3D, denoising convolutional neural network (DnCNN), FFDNet, and Pix2pix. After testing with actual data, it is proved that the SCS-GAN has faster clutter removal speed, stronger generalization ability, and at the same time marine targets in images are remained completely.

NMTLAT: A New robust mobile Multi-Target Localization and Tracking Scheme in marine search and rescue wireless sensor networks under Byzantine attack

After a shipwreck (ship collision, explosion, disappearance, etc.), people rely on the marine search and rescue wireless sensor networks (MSR-WSNs) as one key weapon to locate and track drowning targets to save lives and assets. However, due to the complex and dynamic ocean environment, marine sensors could be captured by malicious attackers and then become Byzantine sensors. Byzantine sensors may tamper with the actual sensor data at a fixed or time-varying probability and transmit it to the data fusion center (DFC), which renders the normal localization and tracking function of the search and rescue system downgrade or even fail. To address this issue, we develop a New robust marine mobile Multi-Target LocAlization and Tracking scheme called NMTLAT by eliminating abnormal measurement data from the initial measurement data. NMTLAT works in several steps. By analyzing and mining sensors data and behavior, we firstly employ the information entropy of the system composed of a single sensor and their neighbor sensors to develop an efficient dynamic threshold based Byzantine node identification method. After migrating Byzantine sensors, the DFC utilizes sensor-aware and preprocessed marine data of the beacon or honest sensors to complete target localization and trajectory tracking. Specifically, NMTLAT consists of a novel distributed and cooperative multi-target localization and tracking algorithm using both received signal strength indication (RSSI) and priori information of sensors location. NMTLAT employs the importance sampling method to approximate the posterior probability distribution of the sensors and targets location. Furthermore, when the marine target is outside MSR-WSNs coverage, a piecewise function is utilized to characterize the likelihood of finding a drowning target in the search and rescue sea area. Finally, the Lyapunov’s second stability theorem is adopted to measure the stability of the NMTLAT. Our extensive simulation experiments validate that the NMTLAT performance is superior to existing solutions in various marine search and rescue scenarios.

FUSAR-Ship: building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition

Gaofen-3 (GF-3) is Chinas first civil C-band fully polarimetric spaceborne synthetic aperture radar (SAR) primarily missioned for ocean remote sensing and marine monitoring. This paper proposes an automatic sea segmentation, ship detection, and SAR-AIS matchup procedure and an extensible marine target taxonomy of 15 primary ship categories, 98 sub-categories, and many non-ship targets. The FUSAR-Ship high-resolution GF-3 SAR dataset is constructed by running the procedure on a total of 126 GF-3 scenes covering a large variety of sea, land, coast, river and island scenarios. It includes more than 5000 ship chips with AIS messages as well as samples of strong scatterer, bridge, coastal land, islands, sea and land clutter. FUSAR-Ship is intended as an open benchmark dataset for ship and marine target detection and recognition. A preliminary 8-type ship classification experiment based on convolutional neural networks demonstrated that an average of 79% test accuracy can be achieved.

A CNN-LSTM Network for Augmenting Target Detection in Real Maritime Wide Area Surveillance Radar Data

Typical radar detectors exploit only a small proportion of the valuable information contained in radar reflections, i.e. magnitude and Doppler. A neural network-based approach for augmenting traditional radar detector structures using machine learning (ML) is proposed in this paper. Specifically, the network is designed to augment target detection in the field of maritime wide area surveillance for non-coherent data. A combination network consisting of a convolutional neural network (CNN) to extract spatial features and a long short-term memory (LSTM) for extracting temporal patterns in the spatial features is proposed. The network augments the detector structure by blanking out regions of the frame which are classified as not containing a target, thus reducing false alarms. The network is tested on data containing four marine targets collected by a ground-based radar. The data set was chosen because it contains strong sea clutter returns. When ML is used, the receiver operating characteristic (ROC) curves are shifted to lower probability of false alarm (PFA). A Kalman filter tracker was applied to the ML-augmented and baseline detections, and it was shown that ML-augmented detections produced similar tracks at lower PFA. The feature discovering capability of the network is analyzed through a series of tests, and the argument is made that the CNN-LSTM network presented in this work demonstrates the ability to improve the detection performance by exploiting spatial and temporal information in the data.

Processing of Raw GNSS Reflectometry Data From TDS-1 in a Backscattering Configuration

Global navigation satellite system reflectometry (GNSS-R) has found many applications in the field of Earth observation including ocean wind-speed detection, ice altimetry, soil moisture monitoring, and more. The main focus of GNSS-R research to date has been on forward-scattered reflections, but theoretical work has proposed a backscattering regime and associated new application opportunities, including marine target detection. This article discusses the methods and results of processing the U.K. TechDemoSat-1 raw data collections in a backscattering regime for the first time, with initial results from sea ice datasets presented. The research has also identified a key problem with the backscatter method-for certain geometries the power from the specular point (forward scattered) may contaminate the data. The theory behind this and a method for predicting such occurrences is also discussed.

Sparse Fractional Energy Distribution and its Application to Radar Detection of Marine Targets With Micro-Motion

The fractional Fourier transform (FRFT), a time-frequency analysis tool, is an effective tool for non-stationary signal processing. Some non-stationary signals, especially chirp signals, appear sparse in fractional Fourier domain (FRFD). To leverage this inherent sparsity, by combining adaptive atomic decomposition in FRFD with sparse representation technique, a novel energy density function, called sparse fractional energy distribution, is proposed for signals that are sparsely represented in FRFD. The relationships between the proposed distribution and other time-frequency distributions are depicted. The performance of the proposed distribution in chirp signal processing is analyzed. Both the theoretical analysis and simulations demonstrate that the proposed distribution achieves multicomponent resolution and robustness against noise. Furthermore, the application to detection and extraction for marine target with micro-motion of the proposed distribution is presented. Experiments are conducted to validate that the proposed distribution can yield promising detection results.

A Method for Active Marine Target Detection Based on Complex Interferometric Dissimilarity in Dual-Channel ATI-SAR Systems

Synthetic aperture radar (SAR) operating in an along-track interferometric (ATI) mode has the advantage of minimum detectable velocity (MDV) in active marine target detection. However, most of the conventional ATI detectors fail to identify the marine targets cruising with blind speeds, in which case the interferometric phases of these targets are closely distributed around those of the sea background due to phase wrapping and aliasing through ATI processing. To address this issue, we propose a method to detect the active marine targets based on complex interferometric dissimilarity for dual-channel ATI-SAR systems. First, an interferometric bilateral filter is designed to smooth the random noises and locally adapt to the spatial structure of the interferogram for measuring the interferometric magnitude and phase. Then, the target detection metric is constructed based on the complex interferometric dissimilarity between the marine targets and the sea background. By adaptively regressing into a magnitude-based test toward the blind-speed targets, the target detection metric can mitigate the blind-speed detection problem and thus yield a satisfactory detection result. Furthermore, this metric is of a constant false-alarm rate (CFAR), and its probability density function (pdf) is derived to facilitate the detection threshold computation. Finally, both the simulated and real-data processing results are given to validate the superiorities of the proposed method.

An Optimal Imaging Time Interval Selection Technique for Marine Targets ISAR Imaging Based on Sea Dynamic Prior Information

Marine targets are usually involved in remarkably strong maneuvering motion due to sea wave disturbance, which will cause continual change of inverse synthetic aperture radar image projection plane (ISAR IPP). As a result, optimal imaging time interval (OITI) selection is indispensable to obtain well-focused ISAR images. Conventional OITI selection algorithms are entirely driven by echo signal, so strong noise has been always challenging the conventional methods in parameter estimation, and the algorithm accuracy is insufficient. Moreover, the analyses for echo signal in traditional methods cost a considerable number of computational loads, leading to low algorithm efficiency. In this paper, a novel OITI selection algorithm for marine targets is proposed via sea dynamic prior information (SDPI) (such as sea state, ship navigation speed, and wave direction angle) instead of echo signal. In the proposed technique, the coupling mechanism between time-varying 3D rotational motion of marine targets (roll, pitch, and yaw) and SDPI can be inferred integrating with hydrodynamics. Based on this, the effective rotational vectors (ERVs) of marine targets relative to radar line of sight (RLOS) can be deduced from the combination of rotational motion and translational motion. It is worth noting that the ERV is an accurate result with the accommodation of complex SDPI rather than an approximate value obtained from the echo signal. By means of the ERV and maximum contrast criterion, the optimal imaging instant (OII) and optimal imaging duration (OID) can be accurately determined, respectively. Without huge computational complexity, the proposed algorithm provides good robustness and high accuracy. Extensive experiments based on electromagnetic simulated data are provided to demonstrate the effectiveness of the proposed algorithm.

A Global Deal For Nature: Guiding principles, milestones, and targets.

The Global Deal for Nature (GDN) is a time-bound, science-driven plan to save the diversity and abundance of life on Earth. Pairing the GDN and the Paris Climate Agreement would avoid catastrophic climate change, conserve species, and secure essential ecosystem services. New findings give urgency to this union: Less than half of the terrestrial realm is intact, yet conserving all native ecosystems-coupled with energy transition measures-will be required to remain below a 1.5°C rise in average global temperature. The GDN targets 30% of Earth to be formally protected and an additional 20% designated as climate stabilization areas, by 2030, to stay below 1.5°C. We highlight the 67% of terrestrial ecoregions that can meet 30% protection, thereby reducing extinction threats and carbon emissions from natural reservoirs. Freshwater and marine targets included here extend the GDN to all realms and provide a pathway to ensuring a more livable biosphere.

Cumulative Impact Index for the Adriatic Sea: Accounting for interactions among climate and anthropogenic pressures

Assessing and managing cumulative impacts produced by interactive anthropogenic and natural drivers is a major challenge to achieve the sustainable use of marine spaces in line with the objectives of relevant EU acquis. However, the complexity of the marine environment and the uncertainty linked to future climate and socio-economic scenarios, represent major obstacles for understanding the multiplicity of impacts on the marine ecosystems and to identify appropriate management strategies to be implemented. Going beyond the traditional additive approach for cumulative impact appraisal, the Cumulative Impact Index (CI-Index) proposed in this paper applies advanced Multi-Criteria Decision Analysis techniques to spatially model relationships between interactive climate and anthropogenic pressures, the environmental exposure and vulnerability patterns and the potential cumulative impacts for the marine ecosystems at risk. The assessment was performed based on spatial data characterizing location and vulnerability of 5 relevant marine targets (e.g. seagrasses and coral beds), and the distribution of 17 human activities (e.g. trawling, maritime traffic) during a reference scenario 2000–2015. Moreover, projections for selected physical and biogeochemical parameters (temperature and chlorophyll ‘a’) for the 2035–2050 timeframe under RCP8.5 scenario, were integrated in the assessment to evaluate index variations due to changing climate conditions. The application of the CI-Index in the Adriatic Sea, showed higher cumulative impacts in the Northern part of the basin and along the Italian continental shelf, where the high concentration of human activities, the seawater temperature conditions and the presence of vulnerable benthic habitats, contribute to increase the overall impact estimate. Moreover, the CI-Index allowed understanding which are the phenomena contributing to synergic pressures creating potential pathways of environmental disturbance for marine ecosystems. Finally, the application in the Adriatic case showed how the output of the CI-Index can provide support to evaluate multi-risk scenarios and to drive sustainable maritime spatial planning and management.

Satellite group autonomous operation mechanism and planning algorithm for marine target surveillance

In terms of fast response problem of unanticipated marine target, it is necessary to design the satellite-ground-combined operation mechanism and planning algorithm for autonomous task planning. Firstly, based on the autonomous operation and task planning of remote sensing satellite group, it is divided into two parts: ground planning and satellite autonomous planning. Secondly, the satellite-ground-combined operation mechanism and operation flow for task planning are proposed after fully considering the resource characteristics and task demand characteristics of the ground and satellite. The satellite autonomous task planning algorithm based on extended contract net is designed. Through the simulation operation of the self-developed distributed simulation demonstration software, it shows that the operation mechanism can coordinate and cooperate effectively between the satellite autonomous task planning and ground planning. It can give full play to the advantages of the ground computing resources, reflect the control intention, make full use of the real-time feature and flexibility of the satellite calculation, and respond fast to the unanticipated task. Besides, it has solved problems of the untimely response of ground control on unanticipated observation task, the limitation of satellite computing resources and satellite-ground planning and coordination, which can effectively improve the responsiveness of remote sensing satellite to the observation task of maritime unanticipated target.

Unsupervised Classification of Hydrophone Signals With an Improved Mel-Frequency Cepstral Coefficient Based on Measured Data Analysis

Recently, passive detection technology has developed the ability to detect surface ships based on the noise emissions recorded by hydrophones, making it possible in some cases to classify surface ships. One of the most concerning issues with ships and underwater targets is the current lack of reliable features for unsupervised classification. To solve this problem, this paper proposes an improved Mel-frequency cepstral coefficients (IMFCC) feature for unsupervised clustering of marine targets. As the feature extraction of hydrophone signals rely on preprocessing, the IMFCC adds cyclic modulation spectrum (CMS) and cross-correlation bispectrum (CCB) in the preprocessing module before traditional the Mel-frequency cepstral coefficient process, and the principal component analysis (PCA) is added as the backend processing module. There are four contributions as follows: First, for IMFCC extraction, it combines the advantages of the CMS, CCB, MFCC, and PCA. Second, the two common unsupervised clusters, Gaussian mixture model (GMM) and fuzzy C-means are used to evaluate the CMS, CCB, and several MFCCs—MFCC-vector quantization (MFCC-VQ), MFCC-Gaussian mixture model (MFCC-GMM), TEO-MFCC (Teager Energy Operator based MFCC), and IMFCC. Third, the performances of traditional MFCC, Teager-energy operator (TEO)-MFCC, IMFCC, MFCC-VQ, and MFCC-GMM are discussed under different dimensions, signal-to-noise ratios, distances, and depths. Finally, the experimental results prove that the IMFCC method has a strong anti-interference ability and is robust and has a high-success rate for clustering multitarget or different depth targets, which enables the IMFCC to be a reliable feature for unsupervised classification.

Ship Classification and Detection Based on CNN Using GF-3 SAR Images

Ocean surveillance via high-resolution Synthetic Aperture Radar (SAR) imageries has been a hot issue because SAR is able to work in all-day and all-weather conditions. The launch of Chinese Gaofen-3 (GF-3) satellite has provided a large number of SAR imageries, making it possible to marine targets monitoring. However, it is difficult for traditional methods to extract effective features to classify and detect different types of marine targets in SAR images. This paper proposes a convolutional neutral network (CNN) model for marine target classification at patch level and an overall scheme for marine target detection in large-scale SAR images. First, eight types of marine targets in GF-3 SAR images are labelled based on feature analysis, building the datasets for further experiments. As for the classification task at patch level, a novel CNN model with six convolutional layers, three pooling layers, and two fully connected layers has been designed. With respect to the detection part, a Single Shot Multi-box Detector with a multi-resolution input (MR-SSD) is developed, which can extract more features at different resolution versions. In order to detect different targets in large-scale SAR images, a whole workflow including sea-land segmentation, cropping with overlapping, detection with MR-SSD model, coordinates mapping, and predicted boxes consolidation is developed. Experiments based on the GF-3 dataset demonstrate the merits of the proposed methods for marine target classification and detection.

Deep Learning-Based Automatic Clutter/Interference Detection for HFSWR

High-frequency surface wave radar (HFSWR) plays an important role in wide area monitoring of the marine target and the sea state. However, the detection ability of HFSWR is severely limited by the strong clutter and the interference, which are difficult to be detected due to many factors such as random occurrence and complex distribution characteristics. Hence the automatic detection of the clutter and interference is an important step towards extracting them. In this paper, an automatic clutter and interference detection method based on deep learning is proposed to improve the performance of HFSWR. Conventionally, the Range-Doppler (RD) spectrum image processing method requires the target feature extraction including feature design and preselection, which is not only complicated and time-consuming, but the quality of the designed features is bound up with the performance of the algorithm. By analyzing the features of the target, the clutter and the interference in RD spectrum images, a lightweight deep convolutional learning network is established based on a faster region-based convolutional neural networks (Faster R-CNN). By using effective feature extraction combined with a classifier, the clutter and the interference can be automatically detected. Due to the end-to-end architecture and the numerous convolutional features, the deep learning-based method can avoid the difficulty and absence of uniform standard inherent in handcrafted feature design and preselection. Field experimental results show that the Faster R-CNN based method can automatically detect the clutter and interference with decent performance and classify them with high accuracy.

Designing optimal scenarios of nutrient loading reduction in a WFD/MSFD perspective by using passive tracers in a biogeochemical-3D model of the English Channel/Bay of Biscay area

In most cases, eutrophication of a coastal zone is a multi-source phenomenon. The questions often raised by authorities about these different sources are: what are their marine area of influence and their respective role in the eutrophication process?A first answer to these questions is proposed for the bay of Biscay-English Channel French coasts, using a hydrodynamical model alone with a passive tracer for each of the main 45 French watersheds of the domain. The statistical marine receiving area of each river is then defined over a whole decade (2000–2010) by using different percentiles (respectively the 10th, 50th, 90th ones) of the distribution of tracer values in each mesh of the grid: this enables to map the dilution areas of each river plume respectively for low water regime, mean flow rate regime and flood regime. If one can impose: 1/the marine winter concentration not to be exceeded to keep a Good Ecological Status, 2/a proxy for the cost of the unitary abatement of the nutrient concentration in each river, this linear dilution model can be coupled to a global optimisation method, in order to compute the set of concentrations in the 45 rivers which allows to obtain at the lowest price the best Ecological Status everywhere in the maritime domain under consideration. Two global optimisation techniques (linear Simplex method and quadratic Beale's method) have been compared on various marine target areas: the marine WFD water masses considered separately or together, the 3 MSFD French sub-regions of the Channel-Biscay area, or the coastal strip laying between the seashore and the 50 m isobath. Computations have been made using two successive nitrate and phosphate thresholds at sea, which are associated respectively to the WFD eutrophication High Status and Good Status. This exercise has shown that focusing on a single small marine target area can sometimes prescribe a strong abatement of concentrations in the sole small neighbouring rivers, but that dealing with a large marine target area points always to the biggest tributaries as being the main nutrient sources to be diminished, whereas small tributaries can be neglected. As it contains the whole big river plumes, the MSFD target requires stronger abatement of nitrate in some watersheds than the WFD target, which is limited to a thin, 1 nautical mile wide strip along the coasts. Whereas very few rivers (e.g. the Seine river) require some abatement of their phosphate loadings, almost all the medium and large French rivers would require very strong abatements (between 50 and 80%) of their nitrate concentrations.To verify this quick linear approach restricted to winter nutrients, a full non-linear, coupled biogeochemical-hydrodynamical model has been used to compute the effect of these optimal nutrient reduction scenarios on the most characteristic descriptors of eutrophication: chlorophyll 90th percentile, dinoflagellate maximum and bottom oxygen concentration 10th percentile. The results show that nutrient loading reductions enabling a Good Ecological Status everywhere for winter marine nutrients would still leave some marine areas in a Bad Ecological Status in terms of chlorophyll content.

An efficient raw data simulation algorithm for large complex marine targets and extended sea clutter in spotlight SAR

AbstractAn efficient algorithm is proposed to simulate the backscattering field of a complex marine target and surrounding 3D sea surface as clutter. Sea surface backscattering is simulated based on the numerical solution of the Electric Field Integral Equation by an improved meshing algorithm. The complex target is modeled using the discrete scattering centers independently. Combining the target and sea surface backscattered fields is used to extract the SAR raw data. The effectiveness of the proposed algorithm is verified for 2 hypothetical cases.

Target monitoring using small-aperture compact high-frequency surface wave radar

High-frequency surface wave radar (HFSWR) can detect and continuously track vessels beyond the horizon in excess of 200 nautical miles from the array [1]–[3]. Moreover, multiple HFSWRs can be used, and their detection results can be fused to improve the detection performance of marine target [13]–[15]. Most current HFSWRs for ship surveillance are large phased-array systems. The antenna arrays of such systems are hundreds or even thousands of meters wide [4], [5], [15]. Some of those radar systems require large fixed seaside radar sites or large transmit power. For those reasons, large-array HFSWR has not been widely applied.

Theoretical Performance of Space-Time Adaptive Processing for Ship Detection by High-Frequency Surface Wave Radars

In this paper, we analyze the levels of performance of the (full or reduced versions of) space-time adaptive processing (STAP) algorithms applied to high-frequency surface wave radars (HFSWRs) for marine target detection to verify whether this family outperforms the usual moving target indication (MTI) algorithms. In fact, STAP algorithms have well-known drawbacks (e.g., large amount of secondary data). The propagation and backscattering of radar signals are included in the covariance matrix calculation. Since the propagation and backscattering have to be derived from physical features of the sea (e.g., sea Doppler) and the atmosphere, we also include the difference induced by the waveform (pulsed radar/chirp) in our study. Moreover, since the inverse covariance matrix is used in the target detection algorithms, matrix conditioning is also inspected for practical implementation reasons. We numerically detail the performance (signal noise clutter ratio and conditioning number of the STAP algorithms) with regards to the MTI performance for several configurations of radar and sea state. These results show that the improvements of signal noise clutter ratio are counterbalanced by a raise of the conditioning number, except in the case of eigencanceler approach. The sea-state parameters have few effects on the performance unlike to radar parameters.