A ship trajectory clustering algorithm based on segmentation direction

Abstract

Listen

Translate article

With the increase of ship AIS data. Through AIS data mining algorithm, it is possible to extract guidelines for the best path of a specific water area by using trajectory segment clustering. The defects of the current trajectory segment clustering algorithm are mainly reflected in: the lack of direction of the path after clustering; For trajectory segment clustering, the whole trajectory is considered rather than a single trajectory segment. In this paper, the trajectory direction and density are used as a measure of similarity between trajectories, and the trajectory segment clustering algorithm is used to analyze the compressed ship trajectory segment data. The first step is to eliminate clusters that contain too few trajectories, and clusters that have too small a distance value between trajectories. For two nearby clusters in opposite directions, the Hausdorff distance is determined. When the distance is less than the threshold, the trajectory is considered to be a two-way route. Finally, the trajectory clusters after clustering are fused to form a view of the overall traffic flow frame of ships in the water area. The framework can describe the main driving direction of the ship in the water and provide decision-making suggestions for the driver's path planning.