Potential fields in maritime anomaly detection
2013 (English)Conference paper (Refereed) PublishedAlternative title
Potentiella fält i sjöfarts abnormitet detektering (Swedish)
This paper presents a novel approach for pattern extraction and anomaly detection in mari- time vessel traffic, based on the theory of potential fields. Potential fields are used to rep- resent and model normal, i.e. correct, behaviour in maritime transportation, observed in historical vessel tracks. The recorded paths of each maritime vessel generate potentials based on metrics such as geographical location, course, velocity, and type of vessel, resulting in a potential-based model of maritime traffic patterns. A prototype system STRAND, developed for this study, computes and displays distinctive traffic patterns as potential fields on a geographic representation of the sea. The system builds a model of normal behaviour, by collating and smoothing historical vessel tracks. The resulting visual presentation exposes distinct patterns of normal behaviour inherent in the recorded maritime traffic data. Based on the created model of normality, the system can then perform anomaly detection on current real-world maritime traffic data. Anomalies are detected as conflicts between vessels potential in live data, and the local history-based potential field. The resulting detection performance is tested on AIS maritime tracking data from the Baltic region, and varies depending on the type of potential. The potential field based approach contributes to maritime situational awareness and enables automatic detection. The results show that anomalous behaviours in maritime traffic can be detected using this method, with varying performance, necessitating further study.
Place, publisher, year, edition, pages
Dresden: TUD Press , 2013.
Anomaly Detection, Maritime Traffic, Potential Fields
IdentifiersURN: urn:nbn:se:bth-6417Local ID: oai:bth.se:forskinfo1A9F575FF8EB6F16C1257D96003EF055ISBN: 978-3-944331-34-8OAI: oai:DiVA.org:bth-6417DiVA: diva2:833923
Proceedings of the 3rd International Conference on Models and Technologies for Intelligent Transport Systems