VESSEL TRAFFIC DENSITY MAPS BASED ON VESSEL DETECTION IN SATELLITE IMAGERY

Nowadays, the volume and variety of vessel tracking data are rapidly increasing. The Automatic Identification System (AIS) is the main source of vessel tracking data as most commercial vessels need to bear an AIS transponder and transmit messages every few seconds to minutes, depending on the vessel type and navigational status. Although calculating the density of vessel traffic based on AIS provides the most valuable insights, other sources of data could also be added in order to obtain a more complete picture of the maritime domain, as there are areas with limited AIS coverage and areas where vessels tend to switch-off their transponders. In the work described in this paper, we highlight those areas by performing vessel detection in Copernicus Sentinel-1 and Sentinel-2 imagery and producing "dark vessel" density maps, i.e., maps showing the density of vessels not transmitting AIS messages. The experimental evaluation of our approach shows that our framework achieves an accuracy greater than 95%.