基于改进TRACLUS算法的船舶轨迹聚类研究

doi:10.12305/j.issn.1001-506X.2025.04.18

系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (4): 1214-1221.doi: 10.12305/j.issn.1001-506X.2025.04.18

基于改进TRACLUS算法的船舶轨迹聚类研究

祁文娟¹, 刘志恒¹^,²^,*, 周绥平¹, 江澄³, 节永师³, 石磊¹

1. 西安电子科技大学空间科学与技术学院, 陕西西安 710126
2. 自然资源部矿山地质灾害成灾机理与防控重点实验室, 陕西西安 710054
3. 北京空间机电研究所先进光学遥感技术北京市重点实验室, 北京 100094

收稿日期:2024-01-30 出版日期:2025-04-25 发布日期:2025-05-28
通讯作者: 刘志恒
作者简介:祁文娟 (1999—), 女, 硕士研究生, 主要研究方向为时序数据预测
刘志恒 (1990—), 男, 讲师, 博士, 主要研究方向为遥感科学与技术
周绥平 (1968—), 男, 教授, 博士, 主要研究方向为分布式虚拟环境、人工智能与空间科学大数据分析
江澄 (1985—), 男, 研究员, 博士, 主要研究方向为遥感数据处理及应用
节永师 (1992—), 男, 高级工程师, 博士, 主要研究方向为遥感图像处理与信息提取
石磊 (1981—), 男, 教授, 博士, 主要研究方向为空间测控通信、空间目标探测识别
基金资助:
自然资源部国土卫星遥感应用重点实验室开放基金(KLSMNR-G202303);先进光学遥感技术北京市重点实验室开放基金(AORS20238);陕西省土地整治重点实验室(300102353502);陕西省自然科学基础研究计划(2023-JC-QN-0299);国家自然科学基金(62371375);陕西省创新能力支撑计划(2022TD-37)

Research on ship trajectory clustering based on improved TRACLUS algorithm

Wenjuan QI¹, Zhiheng LIU¹^,²^,*, Suiping ZHOU¹, Cheng JIANG³, Yongshi JIE³, Lei SHI¹

1. School of Aerospace Science & Technology, Xidian University, Xi'an 710126, China
2. Key Laboratory of Mine Geological Hazards Mechanism and Control, Ministry of Natural Resources, Xi'an 710054, China
3. Beijing Key Laboratory of Advanced Optical Remote Sensing Technology, Beijing Institute of Space Mechanics & Electricity, Beijing 100094, China

Received:2024-01-30 Online:2025-04-25 Published:2025-05-28
Contact: Zhiheng LIU

摘要/Abstract

摘要：

随着船舶自动识别系统(automatic identification system, AIS)的发展, 利用船舶轨迹数据进行聚类分析已成为海洋交通管理和船舶行为分析的关键环节。然而, 现有基于轨迹点的聚类方法未能充分考虑轨迹时序性, 而以整条轨迹为聚类对象则易导致计算效率低和忽视局部信息。针对上述问题, 提出一种基于改进TRACLUS算法的船舶行为分析框架, 使用Hausdorff距离计算轨迹相似性度。所提框架分为3个部分: 基于特征点的轨迹划分, 将整条轨迹进行分段，以考虑轨迹公共子轨迹; 轨迹段聚类, 采用基于密度的聚类算法对轨迹段进行聚类, 形成轨迹簇; 代表性轨迹提取, 使用扫描线方法在轨迹簇中识别出具有相似行为模式的路径。利用港口数据作为数据集, 结果表明改进的聚类算法相比原轨迹聚类(trajectory clustering, TRACLUS)算法在效果和运行效率上均有提升, 能有效提取研究区域内的船舶整体运动趋势和局部相似航行行为。

关键词: 轨迹聚类, 船舶行为, 自动识别系统

Abstract:

With the advancement of ship automatic identification system (AIS), clustering analysis through ship trajectory data has become a critical component in marine traffic management and ship behavior analysis. However, the existing clustering methods based on trajectory points do not adequately consider the temporal aspect of trajectories, and clustering the entire trajectory leads to low computational efficiency and overlook of local information. To address these issues, this paper proposes a ship behavior analysis framework based on an improved trajectory clustering (TRACLUS) algorithm, utilizing Hausdorff distance to assess trajectory similarity. The proposed framework comprises three parts: Trajectory segmentation based on feature points, which segments the entire trajectory to account for common sub-trajectories; Trajectory segment clustering, using the density-based spatial clustering of application with noise (DBSCAN) algorithm to form trajectory clusters; Representative trajectory extraction, employing a scanning line method to identify paths with similar behavior patterns within the clusters. Utilizing data from the ports as a dataset, the results demonstrate that the improved clustering algorithm surpasses the original TRACLUS algorithm in both effectiveness and efficiency, effectively extracting the ship overall movement trends and local similar navigation behaviors within the study area.

Key words: trajectory clustering, ship behavior, automatic identification system (AIS)

中图分类号:

TP751

祁文娟, 刘志恒, 周绥平, 江澄, 节永师, 石磊. 基于改进TRACLUS算法的船舶轨迹聚类研究[J]. 系统工程与电子技术, 2025, 47(4): 1214-1221.

Wenjuan QI, Zhiheng LIU, Suiping ZHOU, Cheng JIANG, Yongshi JIE, Lei SHI. Research on ship trajectory clustering based on improved TRACLUS algorithm[J]. Systems Engineering and Electronics, 2025, 47(4): 1214-1221.

图/表 9

图1

图2

表1

图3

图4

图5

图6

图7

图8

参考文献 31

1	DEVELOPMENT U N . Review of maritime transport 2021[M]. Geneva: United Nations Publications, 2021.
2	肖潇. 基于AIS信息的船舶轨迹聚类模型研究[D]. 厦门: 集美大学, 2015.
	XIAO X. Study on ship's trajectory clustering model based on AIS data[D]. Xiamen: Jimei University, 2015.
3	刘敦伟. 基于AIS数据的船舶航线挖掘[D]. 大连: 大连海事大学, 2017.
	LIU D W. The vessels route mining based on AIS data[D]. Dalian: Dalian Maritime University, 2017.
4	ZHOU Y , DAAMEN W , VELLINGA T , et al. Ship classification based on ship behavior clustering from AIS data[J]. Ocean Engineering, 2019, 175, 176- 187. doi: 10.1016/j.oceaneng.2019.02.005
5	LIU C , LIU J X , ZHOU X , et al. AIS data-driven approach to estimate navigable capacity of busy waterways focusing on ships entering and leaving port[J]. Ocean Engineering, 2020, 218, 108215. doi: 10.1016/j.oceaneng.2020.108215
6	孙明悦, 马胤垚. 基于Spark并行化的改进K-Means轨迹聚类的方法[J]. 数字技术与应用, 2023, 41 (10): 112- 114.
	SUN M Y , MA Y Y . Method of trajectory clustering based on improved K-Means algorithm with Spark parallelization[J]. Digital Technology & Application, 2023, 41 (10): 112- 114.
7	张喜梅, 解滨, 徐童童, 等. 基于反向K近邻和密度峰值初始化的加权K-Means聚类入侵检测算法[J]. 南京理工大学学报, 2023, 47 (1): 56- 65.
	ZHANG X M , XIE B , XU T T , et al. Intrusion detection algorithm based on weighted K-Means clustering with reverse K-Nearest neighbor and density peak initialization[J]. Journal of Nanjing University of Science and Technology, 2023, 47 (1): 56- 65.
8	ZHEN R , YONGXING J , HU Q , et al. Maritime anomaly detection within coastal waters based on vessel trajectory clustering and naive Bayes classifier[J]. Journal of Navigation, 2017, 70 (3): 648- 670. doi: 10.1017/S0373463316000850
9	邱文轩, 许志远, 翟泽宇, 等. 基于改进DBSCAN算法的船舶轨迹聚类与可视化应用[J]. 中国水运, 2023, 8, 59- 61.
	QIU W X , XU Z Y , ZHAI Z Y , et al. Application of vessel trajectory clustering and visualization based on improved DBSCAN algorithm[J]. China Water Transport, 2023, 8, 59- 61.
10	刘钰, 彭鹏菲. 基于改进DBSCAN的船舶轨迹聚类方法研究[J]. 舰船电子工程, 2022, 42 (12): 57- 63.
	LIU Y , PENG P F . Research on clustering method of vessel trajectory based on improved DBSCAN[J]. Ship Electronic Engineering, 2022, 42 (12): 57- 63.
11	韩田宇. 基于HDBSCAN的船舶轨迹聚类方法[J]. 科学技术创新, 2022, 19, 164- 167.
	HAN T Y . Ship trajectory clustering method based on HDBSCAN[J]. Scientific and Technological Innovation, 2022, 19, 164- 167.
12	宋鹏. 基于C-OPTICS算法的船舶轨迹聚类与应用[D]. 大连: 大连海事大学, 2017.
	SONG P. In partial fulfillment of the requirement for the degree of master of engineering[D]. Dalian: Dalian Maritime University, 2017.
13	PALLOTTA G, VESPE M, BRYAN K. Traffic route extraction and anomaly detection from AIS data[C]//Proc. of the Cost Move Workshop on Moving Objects at Sea, 2013.
14	江玉玲, 熊振南, 唐基宏. 基于轨迹段DBSCAN的船舶轨迹聚类算法[J]. 中国航海, 2019, 42 (3): 1- 5.
	JIANG Y L , XIONG Z N , TANG J H . Ship trajectory clustering algorithm based on DBSCAN[J]. Navigation of China, 2019, 42 (3): 1- 5.
15	苏俊杰, 兰培真. 考虑多维特征的船舶轨迹分层聚类算法[J]. 上海海事大学学报, 2022, 43 (4): 30- 36.
	SU J J , LAN P Z . Hierarchical clustering algorithm for ship trajectories considering multi-dimensional features[J]. Journal of Shanghai Maritime University, 2022, 43 (4): 30- 36.
16	陈星佑. 基于分层聚类及LSTM模型的共享单车流量预测研究[D]. 上海: 上海财经大学, 2020.
	CHEN X Y. Research on bike sharing traffic forecasting based on hierarchical clustering and LSTM model[D]. Shanghai: Shanghai University of Finance and Economics, 2020.
17	孙宗元, 方守恩. 高速公路出入口运动车辆轨迹分层聚类算法[J]. 吉林大学学报(工学版), 2017, 47 (6): 1696- 1702.
	SUN Z Y , FANG S E . Hierarchical clustering algorithm of moving vehicle trajectories in entrances and exits freeway[J]. Journal of Jilin University (Engineering and Technology Edition), 2017, 47 (6): 1696- 1702.
18	王浩成, 向隆刚, 关雪峰, 等. 基于出租车上下客数据流与分布式多阶段网格聚类的城市热点区域实时探测方法[J]. 地球信息科学学报, 2023, 25 (7): 1514- 1530.
	WANG H C , XIANG L G , GUAN X F , et al. Urban hotspot detection from the data stream of Taxi pick-up and drop-off based on distributed multistage grid clustering[J]. Journal of Geo-information Science, 2023, 25 (7): 1514- 1530.
19	孙子超. 基于位置的大数据网格聚类统计发布与隐私保护方法[D]. 兰州: 兰州理工大学, 2023.
	SUN Z C. Location-based big data grid clustering statistics publishing and privacy protection model[D]. Lanzhou: Lanzhou University of Technology, 2023.
20	唐春华. 基于轨迹聚类和KDE的船舶轨迹异常实时检测[D]. 上海: 上海海事大学, 2022.
	TANG C H. Real-time detection of abnormal ship trajectory based on trajectory clustering and KDE[D]. Shanghai: Shanghai Maritime University, 2022.
21	张韫博. 基于AIS数据的船舶轨迹异常检测[D]. 大连: 大连海事大学, 2021.
	ZHANG Y B. Vessel trajectory anomaly detection based on AIS data[D]. Dalian: Dalian Maritime University, 2021.
22	王森杰, 何正伟. 分层建模的船舶轨迹快速聚类算法[J]. 武汉理工大学学报(交通科学与工程版), 2021, 45 (3): 596- 601.
	WANG S J , HE Z W . Fast clustering algorithm of ship trajectory based on hierarchical modeling[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2021, 45 (3): 596- 601.
23	冷泳林, 鲁富宇. 一种基于时序的层次轨迹聚类算法[J]. 重庆理工大学学报(自然科学), 2017, 31 (3): 123-127, 157.
	LENG Y L , LU F Y . A hierarchical trajectory clustering algorithm based on time series[J]. Journal of Chongqing University of Technology (Natural Science), 2017, 31 (3): 123-127, 157.
24	ILANGO M R , MOHAN V . A survey of grid based clustering algorithms[J]. International Journal of Engineering Science and Technology, 2010, 2 (8): 3441- 3446.
25	姬强, 孙艳丰, 胡永利, 等. 深度聚类算法研究综述[J]. 北京工业大学学报, 2021, 47 (8): 912- 924.
	JI Q , SUN Y F , HU Y L , et al. Review of clustering with deep learning[J]. Journal of Beijing University of Technology, 2021, 47 (8): 912- 924.
26	MIN E , GUO X F , LIU Q , et al. A survey of clustering with deep learning: from the perspective of network architecture[J]. IEEE Access, 2018, 6, 39501- 39514.
27	LI X C, ZHAO K Q, CONG G, et al. Deep representation learning for trajectory similarity computation[C]//Proc. of the IEEE 34th International Conference on Data Engineering, 2018: 617-628.
28	FANG Z Q, DU Y T, CHEN L, et al. E2DTC: an end to end deep trajectory clustering framework via self-training[C]//Proc. of the IEEE 37th International Conference on Data Engineering, 2021: 696-707.
29	YAO D, ZHANG C, ZHU Z H, et al. Trajectory clustering via deep representation learning[C]//Proc. of the International Joint Conference on Neural Networks, 2017: 3880-3887.
30	LEE J G, HAN J, WHANG K Y. Trajectory clustering: a partition-and-group framework[C]//Proc. of the ACM SIGMOD International Conference on Management of Data, 2007.
31	王明涛. 移动对象轨道聚类算法的研究[D]. 南京: 南京航空航天大学, 2010.
	WANG M T. Research on trajectory clustering algorithms of moving objects[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2010.

聚簇数量K	运行时间/s	轮廓系数值
4	0.167	0.508
5	0.211	0.507
6	0.251	0.522
7	0.493	0.534

[1]	胡玉可, 夏维, 胡笑旋, 孙海权, 王云辉. 基于循环神经网络的船舶航迹预测[J]. 系统工程与电子技术, 2020, 42(4): 871-877.
[2]	刘根旺1,2, 刘永信1, 纪永刚2,3, 王超2. 基于模糊双门限的高频地波雷达与AIS目标航迹关联方法[J]. 系统工程与电子技术, 2016, 38(3): 557-562.
[3]	任文娟, 周志鑫, 吕守业, 师栋锋. 基于AIS信息的舰船位置标校方法[J]. 系统工程与电子技术, 2016, 38(10): 2381-2388.

基于改进TRACLUS算法的船舶轨迹聚类研究

Research on ship trajectory clustering based on improved TRACLUS algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 31

相关文章 3

编辑推荐

Metrics

本文评价