Context-based multi-level information fusion for harbor surveillance

Abstract

Abstract:Harbor surveillance is a critical and challenging part of maritime security procedures. Building a surveil-lance picture to support decision makers in detection of potential threats requires the integration of data and information coming from heterogeneous sources. Context plays a key role in achieving this task by providing expectations, constraints and additional information for inference about the items of interest. This paper proposes a fusion system for context-based situation and threat assessment with application to harbor surveillance. The architecture of the system is organized in two levels. The lowest level uses an ontological model to formally represent input data and to classify harbor objects and basic situations by deductive reasoning according to the harbor regulations. The higher level applies Belief-based Argumen-tation to evaluate the threat posed by suspicious vessels. The functioning of the system is illustrated with several examples that reproduce common harbor scenarios. IntroductionMaritime security is an area of strategic importance for the international community. As stated in [1], ''a terrorist incident against a marine transportation system would have a disaster impact on global shipping, international trade, and the world economy in addition to the strategic military value of many ports and waterways''. For that reason, one of the principal goals of strengthening maritime security is to ''increase maritime domain awareness'' by building a ''surveillance picture as complete as possible to assess the threats and vulnerabilities in the maritime realm''. In particular, harbor surveillance is a critical part of maritime security procedures because of its multiple objectives: recognition of terrorist threats, prevention of maritime and ecological accidents, detection of illegal immigration, fishing and drug trafficking, and so forth. However, it is nowadays mostly developed by human operators [2], who have to evaluate an overwhelming amount of information. This makes it very difficult to keep track of the event stream with the required level of attention due to distraction, fatigue and oversight. In addition, their decisions may be strongly affected by sensor data imprecision and subjective judgment. make informed decisions. According to the JDL data fusion model, the latter task belongs to the domain of Situation Assessment, defined as the estimation of ''sets of relationships among entities and their implications for the states of the related entities '' [4]. In this domain, it requires understanding the intrinsic information provided by coastal sensors in the context determined by extrinsic factors, like harbor environment, operational regulations, traffic data and intelligence reports.Recently, the increasing interest in higher-level information fusion has led to several proposals for context management -see for example the special sessions on context-based information fusion celebrated in the International Conferences on Information Fusion since 2007. Detection and characteri...

Dynamic Context-Aware Event Recognition Based on Markov Logic Networks

“…To cope with uncertainty, an interval-based approach was presented through probabilistic event logic which jointly model events with respect to time intervals and their spatiotemporal relationships [31]. Markov logic networks, combining the expressivity of first order logic (FOL) and the uncertainty disposal of probabilistic graphical models, are recently applied to event recognition in maritime domain [32,33], activity recognition of daily living [34], etc. For example, Skarlatidis et al [35] proposed a method (MLN-EC) which combines a variant of the event calculus with the probabilistic framework of MLNs.…”

Oil and Gas Pipeline Monitoring using Artificial Neural Network

“…A context-based situation and threat assessment system for harbor surveillance was developed in [8]. The system uses a two-level architecture; a low level ontology-based model for reasoning, by deducing and classifying harbor situations and objects respectively and a high level belief-argumentation model for threat evaluation due to suspicious vessels.…”

Context-based Information Fusion: A survey and discussion

“…A proposal to dynamically represent context knowledge with ontologies and evaluate anomalous situations is presented by Gomez-Romero et al in [125]. In a harbor surveillance scenario, it arranges the architecture of the system in two processing levels.…”