Vessel Motion Pattern Recognition Based on One-Way Distance and Spectral Clustering Algorithm

摘要

Identification of vessel motion pattern from large amount of maritime data can help to high level contextual information and improve the effectiveness of surveillance technologies. Vessel routes belonged to certain motion pattern can provide useful information on daily patterns and transit duration. Therefore an approach to identify motion pattern is presented. In paper, the distance similarity matrix of the trajectory dataset was constructed by using the measurement method in trajectory with one-way distance. The regular motion patterns of vessels were extracted from the trajectories spatial distribution learnt by the spectral clustering algorithm. Finally motion patterns of vessel traveling in Qiongzhou strait was extracted using the proposed method. The results showed that the method has high precision on clustering the vessel trajectories and is applicable to identify movement patterns of vessels in maritime areas such as coastal ports, narrow waterway and traffic complex area.