基于改进TRACLUS算法的船舶轨迹聚类研究

打开文本图片集

中图分类号：TP751 文献标志码：A DOI：10.12305/j.issn.1001-506X.2025.04.18

Abstract：With the advancement of ship automatic identification system（AIS），clustering analysis through shiptrajectory data has become a critical component in marine trafc management and ship behavior analysis. However，the existing clustering methods based on trajectory points do not adequately consider the temporal aspect of trajectories，and clustering the entire trajectory leads to low computational efficiency and overlook of local information. To address these issues，this paper proposes a ship behavior analysis framework based on an improved trajectory clustering（TRACLUS）algorithm，utilizing Hausdorff distance to assess trajectory similarity. The proposed framework comprises three parts：Trajectory segmentation based on feature points， which segments the entire trajectory to account for common sub-trajectories；Trajectory segment clustering， using the density-based spatial clustering of application with noise（DBSCAN）algorithm to form trajectory clusters；Representative trajectory extraction，employing a scanning line method to identify paths with similar behavior patterns within the clusters.Utilizing data from the ports as a dataset，the results demonstrate that the improved clustering algorithm surpasses the original TRACLUS algorithm in both effectiveness and efficiency，effectively extracting the ship overall movement trends and local similar navigation behaviors within the study area.

Keywords：trajectory clustering；ship behavior；automatic identification system（AIS）

0 引言

随着海上贸易的发展，海洋安全管理的重要性日益凸显。（剩余14693字）