基于AIS的船舶进出港轨迹数据压缩研究

Research on Ship Trajectory Compression Based on Dynamic Programming Algorithm

船载自动识别系统(Automatic Identification System,AIS)数据中蕴含着丰富的船舶行为特征信息,大量的海上交通研究围绕其展开。随着AIS的完善和广泛应用,日益增长的海量数据和数据冗余问题,已经带来了存储和使用上的压力。为精简并提高AIS数据的可用性,结合船舶进出港轨迹数据特征,提出一种基于动态规划算法的轨迹压缩方法。以天津港大港港区船舶轨迹数据为例开展实验,将动态规划算法与自顶向下时间比算法、Douglas Peucker算法和Sliding Window算法进行对比测试,探讨了在不同压缩率下动态规划算法的压缩性能。实验结果表明,经动态规划算法压缩后的轨迹与原始轨迹高度吻合,能更好地保留原始轨迹的时空特征。文中提出的方法适用于船舶进出港轨迹的压缩,可为基于AIS数据的进出港船舶交通研究提供理论和技术支持。

Automatic Identification System(AIS)data contains a wealth of data on ship behavioral characteristics,and many marine traffic studies have been conducted around it.With the improvement and wide application of AIS,the increasing amount of data and data redundancy problems have brought pressure on storage and use.In order to improve the effectiveness of AIS data,this paper proposes a trajectory compression method based on the dynamic programming algorithm for the relevant problems in the trajectory data of ships entering and leaving the port.Combined with the ship trajectory data in Dagang port area of Tianjin Port,the dynamic programming algorithm is tested and compared with top-down time-ratio algorithm,Douglas Peucker algorithm and Sliding Window algorithm to explore the compression performance of the dynamic programming algorithm under different compression rates.The experimental results show that the trajectory compressed by the dynamic programming algorithm is highly compatible with the original trajectory and can better retain the spatial and temporal characteristics of the original trajectory.This indicates that the algorithm is suitable for the compression study of ship inbound and outbound trajectories,which provides support for the study of inbound and outbound ship traffic flow.