The Automatic Identification System (AIS) has proven itself to be a valuable source for ship traffic information. Its introduction has reversed the previous situation with scarcity of precise data from ship traffic and has instead posed the reverse challenge of coping with an overabundance of data. The number of time-series available for ship traffic and manoeuvring analysis has increased from tens, or hundreds, to several thousands. Sifting through these data manually, either to find the salient features of traffic, or to provide statistical distributions of decision variables is an extremely time consuming procedure. In this paper we present the results of applying computer vision techniques to this problem and show how it is possible to automatically separate AIS data in order to obtain traffic statistics and prevailing features down to the scale of individual manoeuvres and how this procedure enables the production of a simplified ship traffic model.
