Mining of missing ship trajectory pattern in automatic identification system

This paper describes a prototype tracker that incorporates artificial intelligence (AI) procedures to improve tracking performance. The specific application area is the vessel traffic services (VTS) systems. VTS systems are operated by experienced marine traffic regulators (MTRs) who must use a variety of information to resolve automatic tracker errors. It is shown that proper cueing by an expert system enables the tracker to manage situations that can lead to problems for trackers without AI. The detail of the architecture of the AI tracker is presented. The paper concludes by presenting some results on real-life data from an operational VTS radar.

The Taiwan Strait, to the west of Taiwan, is rich in wind energy resources and has the greatest offshore wind power potential in the world. Therefore, Taiwan has been actively expanding its offshore wind power industry in this area in recent years and expects to achieve the total installed capacity to 15.6 GW by 2035. Due to the large vessel traffic flow in Western Taiwan’s sea area, wind farms will inevitably reduce the navigable space and shadow some existing marine aids to navigation, thus worsening navigation safety. An approach using a fault tree analysis was used to carry out analysis of collision risk between ship-to-ship and ship-to-turbine. The vessel density distribution and traffic flow within the open sea of offshore wind farms would further increase to curtail the available navigable space. The shadowing effects along navigation channels would thereafter be worsened to raise the probability of collision risks in the sea. The results of the fault tree analysis revealed that if the ship is out of control, the time allowed to provide assistance is rather short, leading to the increase of collision risk extent between ships and wind turbines. Moreover, the study also found that unfit functions of the Vessel Traffic Service System and navigation aids and frequently and arbitrarily crossing the navigation channel of fishery vessels are the main causes of ship collisions. In order to effectively improve the navigation safety, competitive strategies for navigation safety are investigated and evaluated in this study. These strategies include making a complete plan for utilizing the whole sea, integrating the offshore vessel traffic service and management system, providing remote pilotage services, and building salvage vessels. The above promising strategies would enhance the navigation safety within the open sea. Collision risk might occur once marine accident occurs and no salvage vessel is available.

선박교통류 평가는 대상해역 해상교통특성 파악을 통하여 정량화된 체계화된 교통관리를 수행함으로써 해양사고를 예방하는데 중요하다. 해상교통류의 특성은 선박자동식별장치(AIS, Automatic Identification System)가 선박에 설치됨에 따라 이 장치에서 수신된 정보를 토대로 평가할 수 있다. 본 연구에서는 해상교통관제센터(VTS, Vessel Traffic Services)에서 선박으로부터 수집된 위치, 속력, 침로, 시간 정보로부터 항로상에 해상교통류를 평가하기 위한 시뮬레이터를 구현하였다. 그 결과 해상교통관제센터에서 수집된 데이터로부터 선박 통항량, 통항분포, 선박속력분포, 기하학적 충돌빈도가 계산되어 표시된다. 이러한 해상교통류평가 평가는 해상교통관제사가 해상교통관리의 관점에서 해상안전을 위한 서비스를 제공하는데 유효하게 활용될 수 있을 것으로 사료된다. Maritime traffic assessment is important to understand the characteristics of maritime traffic and to prevent maritime accidents. The maritime traffic assessment can be calculated from the ship trajectory data observed by using AIS(Automatic Identification System). This paper developes a maritime traffic assessment tool using ship's position and speed, course, time data from ships navigating waterways. The results are represented in terms of the number of traffic quantity and traffic distribution, speed distribution, geometric collision candidates. The developed tool will contributes to advance maritime traffic safety by VTS(Vessel Traffic Services).

The AIS (Automatic Identification System) became a standard under the International Convention for the Safety of Life at Sea (SOLAS) in December 2001. Using the AIS transponder, the vessel will report its position, identity heading and other information to other ship traffic in the same area. The AIS is a significant contribution to the control and safety of shipping. Transport Canada (TC) is a pioneer internationally in using the AIS (R4A airborne AIS transponder) integrated with the remote sensing system (MSS 6000 from Swedish Space Corporation) on board their aircraft, in order to add the information on ship identity and voyage to the information from other sensors. The AIS integration provides a quantum leap in the effectiveness of the surveillance mission. In the Canadian system integration, detailed vessel information obtained through the AIS system is displayed and correlated with information received from other sensors. All information is also presented together with a high-resolution digital map including nautical chart data. The AIS provides the operators with vessel voyage and identity information. It is very useful for vectoring the aircraft to areas where ships have been reported. The advent of AIS simplifies surveillance procedures and makes each hour of surveillance more productive. During last year TC reported that over 9700 vessels were over flown. It is anticipated that over 20,000 AIS targets will be acquired using AIS in 2007–2008. The experience from Canada also indicates an outstanding VHF range. During missions, vessels have been identified as far away as 200 nautical miles (n.m.) from the aircraft. The AIS information together with other sensor images gives a comprehensive image that will dramatically improve the chance to tie a ship to a detected illegal oil spill. Receiving ship identity information will enable aircrews to conduct covert operations and contact the suspect ship from far standoff distances. This will also act as a deterrent to potential polluters. Integrating AIS within the operational requirements of surveillance programs, dedicated to minimizing the adverse effects of shipping on the marine environment, will make a significant contribution towards improving the effectiveness of surveillance missions.

This study developed a decision‐making support system (DMSS) for automatically determining the route priority of vessels entering/exiting the waters surrounding the port monitored by vessel traffic services (VTS). The developed DMSS was combined with marine geographic information systems (GIS), automatic identification systems (AIS), and fuzzy logic theory. The simulations of case studies for the ports of Keelung and Singapore were shown to illustrate the fitness of the developed DMSS. Based on the vessel information received/transmitted by AIS within the waters monitored by VTS, the developed DMSS can compute and output the route priority values for the captains on board and the operators in VTS stations as a point of reference. In other words, each ship in the waters surrounding the port can know the route priority for entering/exiting the port. The simulation results of case studies showed that the developed DMSS seems promising. The developed DMSS could be a useful tool in improving a port's navigation safety.

Navigation safety has become one of the important issues to the entire world community. Automatic Identification System (AIS) firstly has been used to comply with safety and security regulations, functioning as collision avoidance, vessel traffic services, maritime security, aids to navigation, search and rescue and accident investigation. This paper presents marine navigation collision preventing system between ships and ships using AIS. In the system, the raw data from AIS is crossed with database based MMSI number to find detail information then, location of each ship was plotted on to Google Map. The safety distance is assessed based actual and stopping distance. The system was tested in the Batam and Singapore Channel.

Ship traffic monitoring may be performed using satellite SAR data. The advantage with the SAR sensor is the all weather and day/night imaging capability. However, the SAR backscatter contrast between a vessel and the surrounding sea state may be small in high wind conditions and at small incidence angles. The present and future SAR satellites will have the capability of imaging the earth surface with several incidence angles, and with dual-polarimetry (HH/HV, VV/VH or HH/VV). The SAR ship/clutter contrast may threrefore be increased by applying different polarisation combinations, or using higher incidence angles. We have shown that geocoded ENVISAT ASAR images in the coastal region of Norway can be used to gain experience in the combined use of satellite SAR and an automatic identification system (AIS) for ship traffic monitoring. There are plans for placing AIS systems onboard satellites. It will then be possible to fuse the information from satellite SAR with those from satellite (or ground-based coastal) AIS and thereby identify all the detected ships within a SAR image. This data fusion will enable us to develop further knowledge about SAR backscatter properties from vessel types that may not be detected so well using the SAR data only. On the other side, it will be possible to pin-point those ship candidates that do not carry an AIS system, and thereby take appropriate security or rescue actions.

This paper presents an intellectual decision making system for the vessel traffic service (VTS). Its aim is to increase the safety and efficiency of the traffic and the effectiveness of VTS. In general, the navigational decision making process in a traffic control system is based on radar and navigation information although other systems, such as automatic identification systems, GPS can be used with good effect. The application of an intellectual component during a decision making process increases safety and economic effects of the shipping as well as reduces the operator's workload.

This paper describes the application method of bumper area defined in the ship domain theory and it is to identify risky sectors in VTS(Vessel Traffic Services) area. The final goal of this work is to develop early warning system providing the location information with high traffic risks in Mokpo VTS area and to prevent the human errors of VTS Officer(VTSO). The current goal of this paper is to find evaluation and detection method of risky sectors. The ratio between overlapped bumper area of each vessels and the summing area of a designated sector, Ratio to Evaluate Risk(RER) <TEX>${\gamma}$</TEX> is used as one of evaluation and detection parameter. The usability of overlapped bumper area is testified through three kinds of scenarios for various traffic situations. The marine traffic data used in the experiments is collected by AIS(Automatic Identification System) receiver and then compiled in the SQL(Structured Query Language) Server. Through the analysis of passing vessel's tracks within the boundary of Mokpo VTS area, the total of 11 sectors are identified as evaluation unit sector. As experiment results from risk evaluation for the 11 sectors, it is clearly known that the proposed method with RER <TEX>${\gamma}$</TEX> can provide the location information of high risky sectors which are need to keep traffic tracks of vessel movements and to maintain traffic monitoring by VTSO.

Development of a Gridded Maritime Traffic DB for e-Navigation

In response to the presence of noise and missing data in the records of ship trajectories from the Automatic Identification System (AIS), which affects the accuracy of ship traffic flow modeling and knowledge discovery, an adaptive reconstruction method for ship trajectories is proposed, taking into account the state of motion of the ship. This method comprehensively considers latitude, longitude, speed, course, and turn rate in the ship trajectory data and enables the identification and removal of position, speed, and course noise. In addition, the ship’s trajectory is divided into straight segments and turning segments based on the rate of change of the ship’s course. Various interpolation methods are adaptively applied to repair the trajectory. The validation with real ship trajectories shows that the proposed method has higher accuracy than other benchmark methods and provides a solid basis for evaluating ship trajectories.

Accurate ship trajectory plays an important role for maritime traffic control and management, and ship trajectory prediction with Automatic Identification System (AIS) data has attracted considerable research attentions in maritime traffic community. The raw AIS data may be contaminated by noises, which limits its usage in maritime traffic management applications in real world. To address the issue, we proposed an ensemble ship trajectory reconstruction framework combining data quality control procedure and prediction module. More specifically, the proposed framework implemented the data quality control procedure in three steps: trajectory separation, data denoising, and normalization. In greater detail, the data quality control procedure firstly identified outliers from the raw ship AIS data sample, which were further cleansed with the moving average model. Then, the denoised data were normalized into evenly distributed data series (in terms of time interval). After that, the proposed framework predicted ship trajectory with the artificial neural network. We verified the proposed model performance with two ship trajectories downloaded from public accessible AIS data base.

This is a combination of YOLO (you only look once) target recognition detection algorithm and AIS (Automatic Identification System) automatic ship identification system to assist vessels in inland navigation to carry out vessels and obstacle avoidance. This system proposes a ship-assisted collision avoidance system for ship collision accidents caused by a narrow inland waterway and complex navigation channel. The system can process the image and video information acquired by the high-definition camera mounted on the ship, and frame and mark the ships in the current sea area, and combine the AIS system to realize the visualization of the ship information and improve the global view. The experiment shows that the system can effectively identify and frame the ship and realize the visualization of AIS information, and the transformed image and video information can be used for decision-making by the ship's driver.

In large harbours and long channels where congested traffic and critical weather are present, VTS (vessel traffic service) systems are needed for traffic management and control. The requirements for these systems become more and more demanding because of the continuous increase of traffic and adverse meteorological conditions; reliable systems which can help the operators to avoid accidents which can jeopardise the security of people and goods have to be used to increase safety and efficiency. These systems employ mainly radar sensors, suitably placed in order to have a complete coverage of the area to be controlled, because a 24-hours operation in all weather conditions must be assured. In this paper a new methodology to process digitised radar images to extract object features (size, heading, etc.) is presented. Considering that ships arriving to, or departing from, harbours are big objects moving in narrow channels or waterways, information such as length and bow position are fundamental to control the ship movements, to evaluate the distance between two vessels, or between the vessel and fixed objects such as buoys or wharves. Results of extensive measurement campaign carried out in Naples, Leghorn and Genoa harbours are reported.

A maritime traffic route extraction method based on density-based spatial clustering of applications with noise for multi-dimensional data