基于网格化压缩挖掘船舶航道位置信息
|
摘要
由于海上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,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。
Since the anomalies of the maritime 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,The 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.
Since the anomalies of the maritime 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,The 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.
引文
[1]Tang Cun-bao,Shao Zhe-ping,Wu Jian-sheng,et al.Based on the research of AIS information density distribution algorithm and implementation[J].Journal of Guangzhou Maritime College,2012,20(3):7-10.
[2]宁建强,黄涛,刁博宇,等.一种基于海量船舶轨迹数据的细粒度网格海上交通密度计算方法[J].计算机工程与科学,2015,37(12):2242-2249.
[3]Pallotta G,Vespe M,Bryan K.Vessel Pattern Knowledge Discovery from AIS Data:A Framework for Anomaly Detection and Route Prediction[J].Entropy,2013,15(6):2218-2245.
[4]Guillarme N L,Lerouvreur X.Unsupervised extraction of knowledge from S-AIS data for maritime situational awareness[A].International Conference on Information Fusion[C].IEEE,2013:2025-2032.
[5]Osekowska E,Carlsson B.Learning Maritime Traffic Rules Using Potential Fields[A].International Conference on Computational Logistics[C].Springer,Cham,2015:298-312.
[6]Osekowska E,Axelsson S,Carlsson B.Potential Fields in Modeling Transport over Water[J].Operations Research/Computer Science Interfaces,2015,58(2):259-280.
[7]Osekowska E,Johnson H,Carlsson B.Grid Size Optimization for Potential Field based Maritime Anomaly Detection[J].Transportation Research Procedia,2014,3(2):720-729.
[8]高曙,刘甜甜,初秀民,等.船舶异常行为研究进展及发展趋势[J].中国航海,2017,40(2):38-43.
[2]宁建强,黄涛,刁博宇,等.一种基于海量船舶轨迹数据的细粒度网格海上交通密度计算方法[J].计算机工程与科学,2015,37(12):2242-2249.
[3]Pallotta G,Vespe M,Bryan K.Vessel Pattern Knowledge Discovery from AIS Data:A Framework for Anomaly Detection and Route Prediction[J].Entropy,2013,15(6):2218-2245.
[4]Guillarme N L,Lerouvreur X.Unsupervised extraction of knowledge from S-AIS data for maritime situational awareness[A].International Conference on Information Fusion[C].IEEE,2013:2025-2032.
[5]Osekowska E,Carlsson B.Learning Maritime Traffic Rules Using Potential Fields[A].International Conference on Computational Logistics[C].Springer,Cham,2015:298-312.
[6]Osekowska E,Axelsson S,Carlsson B.Potential Fields in Modeling Transport over Water[J].Operations Research/Computer Science Interfaces,2015,58(2):259-280.
[7]Osekowska E,Johnson H,Carlsson B.Grid Size Optimization for Potential Field based Maritime Anomaly Detection[J].Transportation Research Procedia,2014,3(2):720-729.
[8]高曙,刘甜甜,初秀民,等.船舶异常行为研究进展及发展趋势[J].中国航海,2017,40(2):38-43.