Abnormal behavior detection of ships in harbor waterways
In view of current efficiency of VTS and AIS manual analysis cannot meet the increasingly severe situation of water traffic supervision,a method for detecting abnormal behaviors of ships in the waters of harbor waterways was proposed by considering the navigation characteristics of ships entering and leaving ports.Firstly,considering influence factors such as ship type and navigation rules,a ship trajectory clustering method based on semantic trajectory multi-dimensional simi-larity was established to identify traffic patterns of ships ente-ring and leaving the port that comply with navigation rules.Secondly,a semantic transformation model was constructed to convert traffic pattern trajectory data into pattern trajectory text,while the text cosine similarity method was used to match the traffic pattern of the target ship.Furthermore,a ship a-nomaly behavior detection model was constructed by using kernel density estimation.Taking Tianjin Port as an example,40 kinds of inbound and outbound traffic patterns were extrac-ted from historical ship trajectory data to construct the ship abnormal behavior detection method,and validated by using simulated data from navigation simulator.Results show that the proposed method can effectively detect ship abnormal be-haviors,providing assistance in waterway supervision.
NETL
NSTL
万方数据
