Extraction of Hottest Shipping Routes: From Positioning Data to Intelligent Surveillance

The automatic extraction of hottest shipping routes is naturally beneficial for ship monitoring, maritime surveillance, and traffic safety management in vessel traffic service (VTS) systems. The extraction results are highly dependent on the historical positioning data collected from the widely-used automatic identification system (AIS). It plays an important role in guaranteeing intelligent traffic management and collision avoidance services in maritime surveillance. In this work, we propose to develop a big data-driven multi-step computational framework for extracting hottest shipping routes. To be specific, we first generate the maritime traffic networks using trajectory simplification and density clustering algorithms. The kernel density estimation (KDE) method is then introduced to generate the visualization of shipping route heatmap, related to the frequency of traffic counts in specific areas. The hottest shipping routes can be finally extracted through a sliding windows algorithm performed on the shipping route heatmap. Experimental results on realistic AIS data have demonstrated the robustness and effectiveness of the proposed multi-step computational framework.