A distributed framework for extracting maritime traffic patterns

Abstract

All the modern surveillance systems take advantage of the Automatic Identification System (AIS), a compulsory tracking system for many types of vessels. Ships that carry AIS transponders on board transmit their position and status in order to alert nearby vessels and ground stations, but this information can well be used to identify events of interest and support decision making. The detection of anomalies (i.e. unexpected sailing behavior) in vessels' trajectories is such an event, which is of utmost importance. Approaches for detecting such anomalies vary from extracting normality models to searching for individual cases, such as AIS switch-off or collision avoidance maneuvers. The current research work follows the former method; it employs sparse historic AIS data and polynomial interpolation in order to extract shipping lanes. It modifies the DB-Scan clustering algorithm in order to achieve more coherent trajectory clusters, which are then composed to create the shipping lanes. The proposed approach implements distributed processing on Apache Spark in order to improve processing speed and scalability and is evaluated using real-world AIS data collected from terrestrial AIS receivers. The evaluation shows that the biggest part (i.e. more than 90%) of any future vessel trajectory falls within the extracted shipping lanes.

A Deep Learning Streaming Methodology for Trajectory Classification

“…The clustering of trajectories often constitutes an initial step when dealing with trajectory classification. Most of the well-established clustering algorithms require input parameters that are hard to determine (Optics [20], Traclus [21], DBSCAN [22]) and that eventually have a significant impact on the clustering results. As our method skips this step entirely, as stated above, we eliminated the need for arbitrary or empirical user-defined parameters, making our approach scalable and robust; • Due to these unparalleled quantities of trajectory data, which in turn can overwhelm human analysis approaches, several compression techniques were applied in order to minimize the size of the trajectory data, while at the same time minimizing the impact on the trajectory analysis methods.…”

Intelligent geospatial maritime risk analytics using the Discrete Global Grid System

“…Filipiak et al (2018) utilised Apache Spark to process 310 million vessel positions, calculating statistics and identifying anomalies, demonstrating both significant efficiencies and scalability over conventional methods. Other applications include extracting maritime traffic patterns for anomaly detection (Kontopoulos, Varlamis, & Tserpes, 2020), characterising vessel behaviour near critical infrastructure (Scully et al, 2019), mapping global shipping routes from 21 billion vessel positions (Wu et al, 2017) or presenting novel data models (Widhalm & Dragaschnig, 2020). Few studies have investigated the use of big data processing for use in maritime risk assessment.…”

A Comparison of Trajectory Compression Algorithms Over AIS Data

“…The exploitation of AIS data from the maritime authorities has shifted the focus of researchers' attention towards the development of trajectory mining techniques. Such tech-niques allow the authorities to further take advantage of the trajectories formed from the AIS messages either in real-time [1]- [3] or on historical data [4]- [6]. The main challenge to be tackled in the development of trajectory mining techniques is the data's huge volume generated globally and the associated high frequency.…”