Ship AIS Trajectory Clustering: An HDBSCAN-Based Approach

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.

[1]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ickjai Lee,et al.  Hierarchical trajectory clustering for spatio-temporal periodic pattern mining , 2018, Expert Syst. Appl..

[3]  Miin-Shen Yang,et al.  Powered Gaussian kernel spectral clustering , 2017, Neural Computing and Applications.

[4]  M. I. Ortego,et al.  Characterizing the Evolution of the Container Traffic Share in the Mediterranean Sea Using Hierarchical Clustering , 2018, Journal of Marine Science and Engineering.

[5]  Jie Zhao,et al.  A review of moving object trajectory clustering algorithms , 2016, Artificial Intelligence Review.

[6]  Moshe Ben-Akiva,et al.  Hierarchical density-based clustering methods for tolling zone definition and their impact on distance-based toll optimization , 2020, Transportation Research Part C: Emerging Technologies.

[7]  Xin Wang,et al.  A Novel Framework of Real-Time Regional Collision Risk Prediction Based on the RNN Approach , 2020 .

[8]  H. Ligteringen,et al.  Study on collision avoidance in busy waterways by using AIS data , 2010 .

[9]  Miao Gao,et al.  Ship-handling behavior pattern recognition using AIS sub-trajectory clustering analysis based on the T-SNE and spectral clustering algorithms , 2020 .

[10]  Mahes Visvalingam,et al.  The Douglas‐Peucker Algorithm for Line Simplification: Re‐evaluation through Visualization , 1990, Comput. Graph. Forum.

[11]  I Ghamarian,et al.  Hierarchical density-based cluster analysis framework for atom probe tomography data. , 2019, Ultramicroscopy.

[13]  Pengfei Chen,et al.  Probabilistic risk analysis for ship-ship collision: State-of-the-art , 2019, Safety Science.

[14]  Kevin X. Li,et al.  How big data enriches maritime research – a critical review of Automatic Identification System (AIS) data applications , 2019, Transport Reviews.

[15]  Pieter van Gelder,et al.  Global path planning for autonomous ship: A hybrid approach of Fast Marching Square and velocity obstacles methods , 2020 .

[16]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[17]  Andrew T. Wilson,et al.  Exploratory Trajectory Clustering with Distance Geometry , 2016, HCI.

[18]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[19]  Xiaoyan Wang,et al.  The global Minmax k-means algorithm , 2016, SpringerPlus.

[20]  Liangbin Zhao,et al.  A trajectory clustering method based on Douglas-Peucker compression and density for marine traffic pattern recognition , 2019 .

[21]  Liangbin Zhao,et al.  Maritime Anomaly Detection using Density-based Clustering and Recurrent Neural Network , 2019, Journal of Navigation.