The Automatic Identification System (AIS) of ships provides massive data for maritime transportation management and related researches. Trajectory clustering has been widely used in recent years as a fundamental method of maritime traffic analysis to provide insightful knowledge for traffic management and operation optimization, etc. This paper proposes a ship AIS trajectory clustering method based on Hausdorff distance and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), which can adaptively cluster ship trajectories with their shape characteristics and has good clustering scalability. On this basis, a re-clustering method is proposed and comprehensive clustering performance metrics are introduced to optimize the clustering results. The AIS data of the estuary waters of the Yangtze River in China has been utilized to conduct a case study and compare the results with three popular clustering methods. Experimental results prove that this method has good clustering results on ship trajectories in complex waters.

With the enormous amount of information provided by the ship Automatic Identification System (AIS), AIS is now playing a significant role in maritime transport system-related research and development. Many kinds of research and industrial applications are based on the ship trajectory extracted from raw AIS data. However, due to the issues of equipment, the transmission environment, and human factors, the raw AIS data inevitably contain abnormal messages, which have hindered the utilization of such information in practice. Thus, in this paper, an anomaly detection method that focuses on AIS trajectory is proposed, making comprehensive use of the kinematic information of the ship in the AIS data. The method employs three steps to obtain non-error AIS trajectories: (1) data preprocessing, (2) kinematic estimation, and (3) error clustering. It should be noted that steps (2) and (3) are involved in an iterative process to determine all of the abnormal data. A case study is then conducted to test the proposed method on real-world AIS data, followed by a comparison between the proposed method and the rule-based anomaly detection method. As the processed trajectories show fewer abnormal features, the results indicate that the method improves performance and can accurately detect as much abnormal data as possible.