Publications included in the licentiate thesis
E. Osekowska, S. Axelsson and B. Carlsson. Potential fields in maritime anomaly detection. In Proceedings of the 3rd International Conference on Models and Technologies for Intelligent Transport Systems, 2013.
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.
For ages now, sailing open waters has been aided by various naviga- tion tools. Yet, without an explicit road-like regulation, following the proper sailing routes and practices is still a challenge mostly addressed using seamens know-how and experience. This chapter focuses on the problem of modeling ship movements over water with the aim to extract and represent this kind of knowledge.
The purpose of the developed modeling method, inspired by the theory of potential fields, is to capture the process of navigation and piloting through the observation of ship behaviors in transport over water. The models of typical ship movements are then used to provide insights into traffic properties (maritime situational awareness), and to warn about potentially dangerous traffic behaviors (anomaly detection).
A traffic modeling and anomaly detection prototype system STRAND implements the potential field based method for a set of AIS data. Aside the demonstration of modeling and visualization capabilities, a case study is taken out. The study focuses on quantifying the detections for varying geographical resolution of the detection. As a result, the detection resolution can be fine-tuned for the specific conditions of transport, in this casea river area. The modeled potential fields also extract be- havior patterns, such as right-hand sailing rule and speed limits, without any prior assumptions or information. The displayed patterns of correct (normal) behavior aid the choice of optimal sailing paths.
The eventual AIS-based patterns are the result of all traffic-shaping factors, and as such they include not only the effects of itinerary planning and navigational skills, but also environmental factors, such as the transport of water and weather condi- tions. Therefore, the fusion of AIS with the hydrological and meteorological in- formation is considered for future work, possibly providing more comprehensive insight into the circumstances of traffic events, enhancing the pattern recognition and improving performance of the anomaly detection.
E. Osekowska, H.Johnson and B. Carlsson. Optimization of grid precision for potential field based maritime anomaly detection. Accepted for publication in Transportation Research Procedia. Elsevier, 2014.
This study focuses on improving the potential field based maritime data modeling method, developed to extract traffic patterns and detect anomalies, in a clear, understandable and informative way. The method's novelty lies in employing the concept of a potential field for AIS vessel tracking data abstraction and maritime traffic representation. Unlike the traditional maritime surveillance equipment, such as radar or GPS, the AIS system comprehensively represents the identity and properties of a vessel, as well as its behavior, thus preserving the effects of navigational decisions, based on the skills of experienced seamen.
In the developed data modeling process, every vessel generates potential charges, which value represent the vessels behavior, and drops the charges at locations it passes. Each AIS report is used to assign a potential charge at the reported vessel positions. The method derives three construction elements, which define, firstly, how charges are accumulated, secondly, how a charge decays over time, and thirdly, in what way the potential is distributed around the source charge.
The collection of potential fields represents a model of normal behavior, and vessels not conforming to it are marked as anomalous. In the anomaly detection prototype system STRAND, the sensitivity of anomaly detection can be modified by setting a geographical coordinate grid precision to more dense or coarse. The objective of this study is to identify the optimal grid size for two different conditions an open sea and a port area case.
A noticeable shift can be observed between the results for the open sea and the port area. The plotted detection rates converge towards an optimal ratio for smaller grid sizes in the port area (60-200 meters), than in the open sea case (300-1000 meters). The effective outcome of the potential filed based anomaly detection is filtering out all vessels behaving normally and presenting a set of anomalies, for a subsequent incident analysis using STRAND as an information visualization tool.
E. Osekowska and B. Carlsson. Visualizing anomalies and traffic rules in a maritime setting using potential fields. Submitted to the 6th International Conference on Information Visualization Theory and Applications (IVAPP). 2015.
Automatic Identification System (AIS) transponders are used to identify and locate traffic. By recording AIS data, in a marine setting, it is possible to observe precise ship movements. An AIS-based maritime data modeling method is developed using a potential fields based method for extracting traffic patterns and detecting anomalies. The three aspects of potential field theory: charge accumulation, potential dissipation and field decay, enable the modeling of vessel traffic. STRAND, the tool visualizing the potential fields, shows actual past and present traffic behaviors and may generate traffic rules spontaneously. This study demonstrates and compares the modeling and detection results from three different areas, depicting a group of traffic rules identified in course of the result analysis. Based on the visual display of past traffic patterns, future routes may be optimized, using potential fields as a way of planning the actual route to destination. When deployed, such a solution could benefit a wide audience, from ship navigators, through traffic management, to transportation regulatory institutions.