Karna Bryan

Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction

Understanding maritime traffic patterns is key to Maritime Situational Awareness applications, in particular, to classify and predict activities. Facilitated by the recent build-up of terrestrial networks and satellite constellations of Automatic Identification System (AIS) receivers, ship movement information is becoming increasingly available, both in coastal areas and open waters. The resulting amount of information is increasingly overwhelming to human operators, requiring the aid of automatic processing to synthesize the behaviors of interest in a clear and effective way. Although AIS data are only legally required for larger vessels, their use is growing, and they can be effectively used to infer different levels of contextual information, from the characterization of ports and off-shore platforms to spatial and temporal distributions of routes. An unsupervised and incremental learning approach to the extraction of maritime movement patterns is presented here to convert from raw data to information supporting decisions. This is a basis for automatically detecting anomalies and projecting current trajectories and patterns into the future. The proposed methodology, called TREAD (Traffic Route Extraction and Anomaly Detection) was developed for different levels of intermittency (i.e., sensor coverage and performance), persistence (i.e., time lag between subsequent observations) and data sources (i.e., ground-based and space-based receivers).

Fusing uncertain knowledge and evidence for maritime situational awareness via Markov Logic Networks

The concepts of event and anomaly are important building blocks for developing a situational picture of the observed environment. We here relate these concepts to the JDL fusion model and demonstrate the power of Markov Logic Networks (MLNs) for encoding uncertain knowledge and compute inferences according to observed evidence. MLNs combine the expressive power of first-order logic and the probabilistic uncertainty management of Markov networks. Within this framework, different types of knowledge (e.g. a priori, contextual) with associated uncertainty can be fused together for situation assessment by expressing unobservable complex events as a logical combination of simpler evidences. We also develop a mechanism to evaluate the level of completion of complex events and show how, along with event probability, it could provide additional useful information to the operator. Examples are demonstrated on two maritime scenarios of rules for event and anomaly detection.

Maritime surveillance with multiple over-the-horizon HFSW radars: An overview of recent experimentation

This paper briefly explores the high-frequency surface-wave (HFSW) radar technology in general, and Wellen radar (WERA) in more detail. Then it describes the multitarget tracking data fusion (MTTDF) network architecture developed at Science and Technology Organization (STO) Centre for Maritime Research and Experimentation (CMRE) and discusses its capabilities in two real study cases: the first in the Ligurian Sea, Mediterranean [11]-[13], and a second in the German Bight, North Sea [14], [15]. In both cases, the main task of the HFSW radars is to estimate sea surface currents. In the second study case, the data recorded by the single stations are sent directly to the Centres Data Base (DB) and then processed in real-time. The historical information about ship traffic can be exploited not only for assessing system performance, but also in the field of knowledge-based (KB) tracking, for improving system capabilities. In this sense, simulation results are presented and discussed. Finally, a tool developed at STO CMRE, the so-called maritime situational awareness (MSA) viewer, allows displaying from the operators point of view the maritime picture of the surveyed area.

A Bayesian approach to predicting an unknown number of targets based on sensor performance

Estimating remaining targets after some attempt has been made to detect an overall, unknown number of targets is critical to determining the potential threat associated with these remaining targets. This paper presents a Bayesian approach to calculate the distribution on the number of remaining targets given the sensor performance and the number of targets detected. For a single sensor, a closed form posterior distribution on remaining targets is derived. For multiple sensors, the corresponding posterior distribution is developed. A naive implementation of this calculation is shown to be computationally prohibitive, and an efficient means for performing the calculation is presented

Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction

We present a novel method for predicting long-term target states based on mean-reverting stochastic processes. We use the Ornstein-Uhlenbeck (OU) process, leading to a revised target state equation and to a time scaling law for the related uncertainty that in the long term is shown to be orders of magnitude lower than under the nearly constant velocity (NCV) assumption. In support of the proposed model, an analysis of a significant portion of real-world maritime traffic is provided.

Wide-area feature-aided tracking with intermittent multi-sensor data

This paper addresses multi-sensor surveillance where some sensors provide intermittent, feature-rich information. Effective exploitation of this information in a multi-hypothesis tracking context requires computationally-intractable processing with deep hypothesis trees. This report introduces two approaches to address this problem, and compares these to single-stage, track-while-fuse processing. The first is a track-before-fuse approach that provides computational efficiency at the cost of reduced track continuity; the second is a track-break-fuse approach that is computationally efficient without sacrificing track continuity. Simulation and sea trial results are provided.