A spatio-temporal data representation framework with applications to anomaly detection in the maritime domain

Maritime security and disaster response are critical for many nations to address the vulnerability of their sea lanes, ports, and harbours to a variety of illegal activities as well as to prevent, minimize, and respond to environmental and human disasters. With increasing volume of spatio-temporal data available from systems like the Automatic Identification System, satellite, marine radar, and other sources it is increasingly problematic to analyze this enormous volume of data. This work builds on the state-of-the art in spatio-temporal anomaly detection by proposing a representation framework for spatio-temporal data, providing a software implementation as an API, and evaluating it. The aim of the framework is to represent spatio-temporal data using abstract concepts to describe motion over time in order to concisely represent high level abstract motion behaviours. The framework is generic and can be applied to any type of spatio-temporal data, but the focus is on the maritime domain.