基于网格化压缩挖掘船舶航道位置信息

The position information of vessel track mining based on grid compression

摘要:

由于海上军事目标的异常多为位置异常,为了实现海上军事目标在位置上的异常检测,需要挖掘出海上正常船舶航道的位置信息。针对传统航道挖掘方法多基于单一目标的小样本进行,而无法实现海量数据挖掘航道的问题,本文提出了一种基于网格化压缩挖掘船舶航道位置信息的算法。该算法首先采用网格化压缩的方法提高了计算效率；之后采用九宫格矢量化方法重构了航迹方向属性；最后通过设置变阈值实现不同方向上的主航道位置信息的提取。实验结果表明网格化压缩方法有效压缩了原始数据,提高了计算效率；同时在适当的阈值下可以有效挖掘出航道的位置信息。

Abstract:

Since the anomalies of the maritime military targets are mostly positional anomalies, in order to achieve anomaly detection of the position of the maritime military targets, it is necessary to extract the position information of the normal vessel track at sea. Aiming at the problem that the traditional channel mining method, based on a small sample of a single target, can’t realize the massive vessel track data mining, this paper proposes an algorithm based on grid compression to mine the vessel track position information. Firstly, the algorithm improves the computational efficiency by using the grid compression method. Then, the trajectory direction property is reconstructed by the nine-grid vectorization method. Finally, the the main vessel track position information was extracted by using the variable threshold. The results show that the grid compression method effectively compresses the original data and improves the computational efficiency. Meanwhile, the position information of the vessel track can be effectively extract under appropriate thresholds.