Space-based Automatic Identification System Research Articles

Ship Classification in Synthetic Aperture Radar Images Based on Multiple Classifiers Ensemble Learning and Automatic Identification System Data Transfer Learning

With the continuous development of earth observation technology, space-based synthetic aperture radar (SAR) has become an important source of information for maritime surveillance, and ship classification in SAR images has also become a hot research direction in the field of maritime ship monitoring. In recent years, the remote sensing community has proposed several solutions to the problem of ship object classification in SAR images. However, it is difficult to obtain an adequate amount of labeled SAR samples for training classifiers, which limits the application of machine learning, particularly deep learning methods, in SAR image ship object classification. In contrast, as a real-time automatic tracking system for monitoring ships at sea, a ship automatic identification system (AIS) can provide a large amount of relatively easy-to-obtain labeled ship samples. Therefore, to solve the problem of SAR image ship classification and improve the classification performance of learning models with limited samples, we proposed a SAR image ship classification method based on multiple classifiers ensemble learning (MCEL) and AIS data transfer learning. The core idea of our method is to transfer the MCEL model trained on AIS data to SAR image ship classification, which mainly includes three steps: first, we use the acquired global space-based AIS data to build a dataset for ship object classification models training; then, the ensemble learning model is constructed by combining multiple base classifiers; and finally, the trained classification model is transferred to SAR images for ship type prediction. Experiments show that the proposed method achieves a classification accuracy of 85.00% for the SAR ship classification, which is better than the performance of each base classifier. This proves that AIS data transfer learning can effectively solve the problem of SAR ship classification with limited samples, and has important application value in maritime surveillance.

A Multi-Feature Ensemble Learning Classification Method for Ship Classification with Space-Based AIS Data

AIS (Automatic Identification System) is an effective navigation aid system aimed to realize ship monitoring and collision avoidance. Space-based AIS data, which are received by satellites, have become a popular and promising approach for providing ship information around the world. To recognize the types of ships from the massive space-based AIS data, we propose a multi-feature ensemble learning classification model (MFELCM). The method consists of three steps. Firstly, the static and dynamic information of the original data is preprocessed and features are then extracted in order to obtain static feature samples, dynamic feature distribution samples, time-series samples, and time-series feature samples. Secondly, four base classifiers, namely Random Forest, 1D-CNN (one-dimensional convolutional neural network), Bi-GRU (bidirectional gated recurrent unit), and XGBoost (extreme gradient boosting), are trained by the above four types of samples, respectively. Finally, the base classifiers are integrated by another Random Forest, and the final ship classification is outputted. In this paper, we use the global space-based AIS data of passenger ships, cargo ships, fishing boats, and tankers. The model gets a total accuracy of 0.9010 and an F1 score of 0.9019. The experiments prove that MFELCM is better than the base classifiers. In addition, MFELCM can achieve near real-time online classification, which has important applications in ship behavior anomaly detection and maritime supervision.

Improved Doppler Shift Estimation Algorithm for Down-Link Signals of Space-Based AIS

As an enhanced system for marine monitoring and autonomous navigation, the space-based automatic identification system (AIS) has attracted extensive attention and become a hot topic for research. However, it encounters the problem of Doppler shift stemmed from the relative motion between satellites and ships, which leads to performance degradation. To circumvent this issue, in this correspondence, we propose an improved Doppler shift estimation algorithm for down-link signals of space-based AIS, utilizing the calculation of the autocorrelation and ratio on the Rice factor. Specifically, the addressed method is robust to the non-Gaussian noise. Further, the suggested approach has low complexity compared with the existing algorithm. Finally, numerical simulations, such as the standard deviation of the estimated Doppler shift versus signal-to-noise ratio, Rice factor and non-Gaussian noise, and the complexity comparisons, are carried out to validate the theoretical analysis, and demonstrate the superior performance of the proposed estimation approach.

Design and Implementation of Blind Source Separation Based on BP Neural Network in Space-Based AIS

In space-based AIS (Automatic Identification System), due to the high orbit and wide coverage of the satellite, there are many self-organizing communities within the observation range of the satellite, and the signals will inevitably conflict, which reduces the probability of ship detection. In this paper, to improve system processing power and security, according to the characteristics of neural network that can efficiently find the optimal solution of a problem, proposes a method that combines the problem of blind source separation with BP neural network, using the generated suitable data set to train the neural network, thereby automatically generating a traditional blind signal separation algorithm with a more stable separation effect. At last, through the simulation results of combining the blind source separation problem with BP neural network, the performance and stability of the space-based AIS can be effectively improved.

Tracking Capability and Detection Probability Assessment of Space-Based Automatic Identification System (AIS) From Equatorial and Polar Orbiting Satellites Constellation

Performance of LAPAN-A2 and LAPAN-A3 space-based Automatic Identification System (AIS) have been successfully assessed as the satellites operated at individual and two-satellites constellation modes. Since LAPAN-A2 and LAPAN-A3 respectively orbiting at 6° and 97° of inclination, they form a unique constellation; hence, assessment on AIS performance from this equatorial-polar constellation is unprecedented. The assessment is intended to measure both the system and receiver performance of space-based AIS. The measurement of system performance calculates the capability of a space-based AIS system in re-detecting a ship as it moves globally. This performance is used to analyze whether the satellite and its AIS payload are systematically well-configured, including its orbital properties, antenna placement, and receiver’s ability. The measurement of receiver performance is aimed to analyze the receiver capability in detecting all existing ships transmitting the AIS messages. This performance is represented as the ratio between the number of ships detected by the space-based AIS receiver and an ideal AIS receiver. In our case, massive AIS messages collected by an integrated space-terrestrial AIS receiver network has been used as the benchmark. By using 31 days of the collected AIS dataset, operating the satellites as a constellation increases the system and receiver performance by a factor of 7.56% and 7.93%, respectively. The further result shows that the constellated AIS receiver performs excellently in the deep-sea regions, with the value of system performance ranging from 95% to 100%. Moreover, the receivers of constellation satellites overperformed the benchmark receiver on up to 61.84% of their full coverage. The main contribution of this research is to provide information related to the advantages of operating equatorial-polar AIS constellation regarding its in-orbit performance. The results could become a reference in developing a space-based maritime surveillance tool with excellent performance and frequent accesses in those regions.

The Impact of Space-Based AIS Antenna Orientation on In-Orbit AIS Detection Performance

In this paper, a study on the impact of changing the space-based Automatic Identification System (AIS) monopole antenna orientation on its message reception performance in orbit has been conducted. The study has been carried out by maneuvering the attitude of LAPAN-A2, an equatorial orbiting microsatellite with AIS antenna fixedly mounted on the satellite’s body, into the desired orientation. Based on the analysis of the datasets collected during the maneuver, the orientation of AIS monopole antenna 45° toward its flight direction increases the overall detection performance of the AIS message, including class A ship to 208.80% and also class B ships to 175.93%. This orientation also increases the detection of AIS messages in ocean areas having low detection probability due to AIS signal collision. The result of this research could become a reference in order to specify AIS antenna position and orientation in a small satellite carrying a space-based AIS system for maritime surveillance & monitoring purposes.

Ship tracking results from state-of-the-art space-based AIS receiver systems for maritime surveillance

Norway currently operates four satellites with Automatic Identification System (AIS) receivers. The first-generation satellites, AISSat-1 and AISSat-2, are equipped with a two-channel, single-antenna AIS receiver, while NorSat-1 and NorSat-2 are equipped with an improved AIS receiver capable of decoding on all four AIS channels and using the two antennas installed on the NorSat satellites. This paper aims to investigate the ship tracking performance enhancement realised by the technology improvements of antenna diversification, frequency diversification, and advanced algorithms. The ship tracking capability of the NorSat satellites is presented and shown to yield a significant improvement, up to a 20% point increase, over the first AISSat generation ship tracking capability. A further 20% point increase is achieved in select areas using frequency diversity introduced in the AIS system since the development of the AISSat satellites. In addition, NorSat-1 detected 34% more vessels than AISSat-2 over the same timeframe. The contribution to the performance improvement from the incremental improvements in decoding algorithms, antenna diversity, and frequency diversity is indicated in the results. The results indicate that, in the short term, upgrading to the latest algorithms, low noise electronics, and taking advantage of antenna diversity is the greatest performance enhancer. In the medium and long term, the frequency diversity likely yields the greatest performance enhancement.

Doppler Shift Estimation for Space-Based AIS Signals Over Satellite-to-Ship Links

As a communication system for maritime monitoring and navigation, automatic identification system (AIS) has been employed for many years, but its service range is limited in 40 nautical miles. Fortunately, an updated service navigation system named as space-based AIS has been presented in recent years, which can provide global coverage service. However, it encounters the frequency offset issue caused by the relative satellites/ships motion. To cope with it, in this paper, a novel Doppler shift estimation algorithm is proposed for space-based AIS signals over satellite-to-ship wireless fading channels and non-Gaussian noise. In the estimation stage, the signals including the Doppler shift information are first separated from the received ones, but they are also disturbed by the noise. Then, Doppler shift is extracted from the above-detached signals via the higher moments which cancel some excrescent parameters by using several flexible algebra operations, and its estimated expression is presented. Finally, the numerical simulations are carried out to verify the performance of the proposed method, and simulation results demonstrate the benefits of the suggested scheme.

Statistical Analysis of the Detection Probability of the TianTuo-3 Space-based AIS

The Micro-Nano satellite TianTuo-3 (TT-3) developed by the National University of Defense Technology (NUDT) was successfully launched on 20 September 2015. The space-based Automatic Identification System (AIS) on board TT-3 works well and stably receives AIS signals from global vessels. In this work, we perform statistical analysis on the detection probability of the vessels in the concerned areas by using the TT-3 AIS data. The results suggest that the detection probability of vessels decreases as the distribution density increases, especially in the offshore areas of dense traffic and the TT3-AIS vessel detection probability in the oceans can be higher than 40%, indicating that the TT-3 AIS has achieved a high probability of coverage of vessels for a single receiving antenna. The analysis results will present helpful references both in evaluating the potential application of satellite-based AIS and for designing the next generation space-based AIS which might greatly improve the detection probability of ocean-going vessels.

Data Reception Analysis of the AIS on board the TianTuo-3 Satellite

The Automatic Identification System (AIS) receiver on board the main satellite of the TianTuo-3 constellation, LvLiang-1, is a new generation of AIS receiver. Having partly solved the signal conflict problems and with larger coverage over the ground, the AIS receiver on board TianTuo-3 greatly improves the signal detection ability. The data received by the AIS receiver during the TianTuo-3 debugging stage is employed for detailed analysis in this paper. Results include: TianTuo-3 implements four-frequency detection at the same time, and a time-flag is inserted into the received AIS data, a small portion of Class A vessels (at least 1480) have been equipped with AIS sending the long range AIS broadcast message with two new frequency channels and the hourly averaged count of the message received by TianTuo-3’s AIS is between 1500 ~ 2500. This AIS receiver is capable of real-time tracking a single vessel. In conclusion, the TianTuo-3 space-based AIS receiver is capable of continuously receiving AIS messages sent by global maritime vessels.

Simulating Surveillance Options for the Canadian North

As part of the overarching research goal to assess current and potential maritime information sources for use in maritime defence and security in the Canadian north, we examine whether wide-area surveillance data, as represented by Space-based Automatic Identification System (S-AIS) data, offers sufficient information for surveillance requirements in the Canadian north. If S-AIS data are not sufficient, we address how the additional information provided by Long-Range Identification and Tracking (LRIT) can be used to meet the surveillance requirements. A Systems Tool Kit (STK) simulation scenario is constructed that includes five exactEarth satellites collecting AIS data. Simulated AIS transmitters are positioned at 20 northern Canada ground locations. The results indicate that for each location, two thirds of the eight-day simulation is spent without a satellite within range, when using the five satellites. As the number of satellites decreases, intervals in the range of 80 to 105 minutes, during which there are no AIS messages received, increase in frequency. If the end-user requires vessel location information more often than S-AIS consistently provides, augmenting the S-AIS information with LRIT polling should achieve the desired vessel traffic awareness.

Collision-interference cancellation for space-based AIS using beam synthesis technology with optimal sparse linear array

Summary A basic problem in the space-based automatic identification system (AIS) is the low probability of detecting messages because ships' messages arrive at the receiver in the same time slot. In this study, sparse linear array optimal beam synthesis (SLA–OBS) technology is proposed to improve the capture ability of AIS messages by forming a narrow beam pattern that points in the direction of the desired AIS messages. To capture the desired signal within the narrow beam pattern, the directions of arrival (DOA) and the number of sources from ships are first estimated. Then, the ideal narrow beam pattern and minimal number of array elements are achieved synchronously with the CPLEX optimal tool. The simulations show that the message detection probability with the proposed method is greater than 95%, even when the situations are very serious, whereas the number of sparse linear antennas is small (no more than six). Copyright © 2015 John Wiley & Sons, Ltd.

Signal environment mapping of the Automatic Identification System frequencies from space

This paper presents received signal strength data recorded by the NORAIS Receiver on the four VHF channels allocated to the use of the Automatic Identification System (AIS). The NORAIS Receiver operated on-board the Columbus module of the International Space Station from June 2010 to February 2015. The data shows that a space-based AIS receiver must handle transient strong signals from land-based interference and that the effectiveness of the two long range AIS channels recently allocated is severely reduced in select areas due to land based interference.

Quantifying the tracking capability of space-based AIS systems

The Norwegian Defence Research Establishment (FFI) has operated three Automatic Identification System (AIS) receivers in space. Two are on dedicated nano-satellites, AISSat-1 and AISSat-2. The third, the NORAIS Receiver, was installed on the International Space Station. A general method for calculating the upper bound on the tracking capability of a space-based AIS system has been developed and the results from the algorithm applied to AISSat-1 and the NORAIS Receiver individually. In addition, a constellation of AISSat-1 and AISSat-2 is presented. The tracking capability is defined as the probability of re-detecting ships as they move around the globe and is explained to represent and upper bound on a space-based AIS system performance. AISSat-1 and AISSat-2 operates on the nominal AIS1 and AIS2 channels, while the NORAIS Receiver data used are from operations on the dedicated space AIS channels, AIS3 and AIS4. The improved tracking capability of operations on the space AIS channels is presented.

A Beam Scanning Method based on the Helical Antenna for Space-based AIS

We investigate a strategy to address the problem of low ship detection probability of space-based Automatic Identification System (AIS). A directional AIS antenna and an innovative beam scanning method are proposed, which scan the antenna across a wide swath to provide complete coverage and maintain the advantage of a narrow footprint to reduce signal collision. Aiming at the mission requirement of global ship detection by the year 2016, the appropriate swath, the scanning range and the scanning rate were studied and designed in detail. Theoretical analysis and simulations showed that this scanning antenna can greatly improve ship detection probability and hold the detection probability at an average reporting interval from six to 15 seconds for most oceans when compared with the traditional fixed wide beam antenna. Furthermore, the detection capacity of this scanning antenna was little affected by the heights of different Low Earth Orbits. The results of this work show that the design of the helical antenna along with the beam scanning method can be considered as a building block of future space-based AIS.

Ship Surveillance by Integration of Space-borne SAR and AIS – Further Research

Many countries are making increased efforts to improve marine security and safety and develop ship surveillance techniques to satisfy the increasing demands. Space-borne Synthetic Aperture Radar (SAR) delivers high performance day/night all weather capabilities and a space-based Automatic Identification System (AIS) can give near real time and global coverage. Limited by the development of sensors and data processing techniques, the integration of space-borne SAR and AIS has much to offer ship surveillance. State-of-the-art data fusion methods have generally provided satisfactory performance. However, in high-density shipping or high sea-states, performance quality is less assured. This paper firstly investigates improved data association methods. The association methods based on the position feature are improved, and multi-feature-based association methods are proposed. Then, ship identification and tracking by the integration of space-borne SAR and AIS are researched further. Multi-source data fusion strategy is also investigated. Finally, the discussion is presented and the future works are emphasized in the conclusion.

Vessel Track Recovery With Incomplete AIS Data Using Tensor CANDECOM/PARAFAC Decomposition

Global analysis of vessel motion patterns has become possible using satellite-based Automatic Identification System (AIS). The concept of space-based AIS needs several satellites to provide complete coverage and high detection probability. However, in early development stages, often only one satellite is launched and due to its limitation of orbit and footprint, received AIS messages are discontinuous. In this paper, we have analysed real AIS data obtained by satellite to form a global maritime surveillance picture. Furthermore, we propose to take advantage of the tensor CANDECOMP/PARAFAC (CP) decomposition to analyse three mode characteristics of the data, which are location, vessel and time. For incomplete data, we exploit the link prediction technique based on tensor factorisation to recover vessel tracks in a specified area. A variant of temporal link prediction based on CP is presented. We illustrate the usefulness of exploiting the three-mode structure of AIS data by simulation, and demonstrate that the track recovery result has acceptable precision.

Joint EMSA/ESA initiative for a European satellite AIS programme

Space-based Automatic Identification System (SAT-AIS) will provide AIS data via satellite, allowing for the detection and tracking of seafaring vessels on global scale and contribute therefore to maritime awareness. The provision of SAT-AIS data would bring additional added value to existing maritime information services. SAT-AIS will be able to assist European entities and institutions in law enforcement, fisheries control campaigns, maritime border control operations, maritime safety and security issues including marine pollution response, search and rescue, and anti-piracy.The possibility of establishing a European-based SAT-AIS capability is being considered by ESA in partnership with the European Maritime Safety Agency (EMSA). The ARTES 21 SAT-AIS element currently defines the design of a sustainable space-based system that will provide AIS data as a self-standing institutional system or as a hybrid solution in combination with commercial systems.EMSA and ESA are currently implementing a SAT-AIS Data Processing Centre (DPC) under a joint project team. Presently EMSA is developing an Integrated Maritime Data Environment (IMDatE) that will host EMSA′s new SAT-AIS data processing service. ESA has provided EMSA with complementary SAT-AIS data and performance evaluation to the Blue Belt pilot project whose aim was to explore new ways to promote and to facilitate short sea shipping in the European Union by reducing the administrative burden for intra-Community trade. The use of SAT-AIS data helped customs to benefit from an added degree of certainty with regard to ship′s voyage when ships were transiting outside the range of shore based AIS coverage.The current SAT-AIS initiative covers activities that are implemented through different ARTES (Advanced Research in Telecommunications Systems) programme elements, which will be discussed in detail in this paper:•ARTES 5—technology activities, currently underway as antenna miniaturization, receiver developments and performance Testbed.•ARTES 20—implementation and validation of the Data Processing Centre in close cooperation with EMSA for full data integration into SafeSeaNet services.•ARTES 21—covers the initial steps of the system design and implementation, including system design Phase B1 studies, comparative performance assessments, as well the exploration of possible Hybrid Solutions and Public Private Partnership (PPP) implementation schemes for the European SAT-AIS operational system.Consultation with users has taken place through workshops hosted jointly by ESA and EMSA. The 3rd EMSA/ESA information meeting took place on 26 January 2012, at ESOC, in Darmstadt. The outcome of the meeting together with the current achievements and updates of the joint European SAT-AIS programme, are summarized in the following paper.

S192034 小型実証衛星におけるシステムノイズ対策([S192-03]宇宙システムに関する実践的解決と知見の汎用化(3))

The Small Demonstration Satellite 4 (SDS-4) is the first zero momentum three-axis controlled 50kg class satellite from J AX A. It was launched on May 17, 2012 on H-IIA Launch Vehicle, and, SDS-4 has four main demonstration missions: (1) Space-based automatic identification system experiment for tracking ships(SPAISE), (2) Flat-plate heat pipe on-orbit experiment(FOX), (3) Quartz crystal Microbalance for contamination environment monitoring(QCM), and (4) In-flight experiment of space materials using THERME(IST). SDS-4 was required reduction of system noise by SPAISE mission requirement, and conducted several system EMC test in system test phase. This paper reports on the specific antinoise measures and summarized how adaptation to the small satellite in the future.

SDS-4 Attitude Control System: In-Flight Results of Three Axis Attitude Control for Small Satellites

The Small Demonstration Satellite (SDS) program is a JAXA technology demonstration program, targeting the in-orbit demonstration of advanced technologies using small satellites. Following the success of SDS-1, the SDS-4 spacecraft was successfully launched on 18 May 2012 and continues the in-flight demonstration of a space-based Automatic Identification System (AIS) as well as numerous flight experiments. This paper describes the in-flight results of the Attitude Control System (ACS) for 50kg class small satellites using 3-axis zero-momentum stabilization.