Probabilistic prediction of vessel motion at multiple spatial scales for maritime situation awareness

An improved neurobiologically inspired algorithm for situation awareness in the maritime domain takes real-time tracking information and learns motion pattern models based on temporal associations between vessel events enabling conditional probabilities between events to be learned incrementally and locally. These learned weights are used for future vessel location prediction. Improvements in prediction performance are achieved by using multiple spatial scales to represent position, enabling the most relevant spatial scale to be used for local vessel behavior. Features and performance of these updates to the learning system using recorded data are described and compared to previous results.