Maritime Traffic Network Extraction and Application Based on AIS Data

The paper presents a data-driven approach for maritime traffic network extraction based on Automatic Identification System (AIS) data. A maritime traffic network, consisting of nodes that represent waypoint areas and navigational legs, is constructed to represent the maritime traffic at a larger scale. The proposed maritime traffic network extraction approach consists of three phases: 1) extraction of maritime traffic motion patterns based on historical Automatic Identification System data; 2) enrich the ship trajectories with semantic information and each ship trajectory is abstracted as an “origin-waypoint-destination” itinerary object; 3) ship itinerary objects are further merged into nodes and edges of a directed maritime traffic network. Based on the maritime traffic network, a hierarchical reasoning approach is proposed to associate a partially observed ship trajectory to the derived compatible ship routes and ship abnormal behaviour can be detected. The presented method can assist maritime authorities to improve the efficiency of maritime traffic surveillance and to develop strategies to improve navigation safety.