海船异常行为检测综述

doi:10.3969/j.issn.1674-0696.2019.09.18

摘要/Abstract

摘要： 海船异常行为检测对于海上航行安全、海域的智能监管及港口的发展规划都具有非常重要的意义。整理并总结了现阶段海船异常行为检测领域的相关方法，主要包括聚类分析、统计建模、神经网络以及基于预测等异常检测方法，在船舶位置异常、状态异常和潜在的行为异常检测等方面取得了较为显著的进展。同时梳理了海船异常行为检测领域在数据的时变性、模型的复杂性以及异常行为的语义分析等方面存在的异常检测准确性低、语义分析不明确等问题。并对海船异常检测领域未来在数据的增量学习、实时在线检测、情景语义分析和异常行为可视化等方面所存在的突破点做了展望和介绍。

关键词: 交通工程, 海船异常行为检测, 轨迹挖掘, 智能监管, 数据挖掘

Abstract: As the abnormal behavior detection of marine vessels is of great significance to the safety of maritime navigation, intelligent supervision of sea areas and development plan of harbors, its present methods and achievements, challenges as well as future research direction were defined and summarized. It is urgent that a robust algorithm with high accuracy and high real-time performance be proposed to detect and study their abnormal behavior for the improvement of maritime navigation safety.

Key words: traffic engineering, abnormal behavior detection, trajectory mining, intelligent supervision, data mining

中图分类号:

U675.5+9

唐皇，尹勇，神和龙. 海船异常行为检测综述[J]. 重庆交通大学学报（自然科学版）, 2019, 38(09): 109-115.

TANG Huang, YIN Yong, SHEN Helong. Survey of Abnormal Behavior of Marine Vessels[J]. Journal of Chongqing Jiaotong University(Natural Science), 2019, 38(09): 109-115.

参考文献

［1］张树波，唐强荣.基于AIS数据的船舶异常行为检测方法［J］.人工智能与机器人研究，2015,4(4)：23-31.
ZHANG Shubo, TANG Qiangrong. Abnormal vessel behavior detection based on AIS data［J］. Artificial Intelligence and Robotics Research, 2015, 4(4): 23-31.
［2］ LEI P R. A framework for anomaly detection in maritime trajectory behavior［J］. Knowledge and Information Systems, 2016, 47(1):189-214.
［3］ MARTINEAU E, ROY J. Maritime Anomaly Detection: Domain Intro-duction and Review of Selected Literature［R］. Canada: Defense Research and Development Canada,
2011.
［4］曲琳，周凡，陈耀武.基于Hausdorff距离的视觉监控轨迹分类算法［J］.吉林大学学报(工学版)，2009，39(6)：1618-1624.
QU Lin, ZHOU Fan, CHEN Yaowu. Trajectory classification based on Hausdorff distance for visual surveillance system［J］. Journal of Jilin University(Engineering
and Technology Edition),2009,39(6):1618-1624.
［5］胡宏宇，王庆年，曲昭伟，等.运动目标空间模式辨识与异常交通行为检测［J］.吉林大学学报(工学版)，2011，41(6)：1598-1602.
HU Hongyu, WANG Qingnian, QU Zhaowei, et al. Spatial pattern recognition and abnormal traffic behavior detection of moving object［J］. Journal of Jilin
University(Engineering and Technology Edition), 2011,41(6):1598-1602.
［6］曹妍妍，崔志明，吴健，等.一种改进Hausdorff距离和谱聚类的车辆轨迹模式学习方法［J］.计算机应用与软件，2012，29(5)：38-40.
CAO Yanyan, CUI Zhiming, WU Jian, et al. An improved Hausdorff distance and spectral clustering vehicle trajectory pattern learning approach［J］. Computer
Applications and Software,2012,29(5):38-40.
［7］魏龙翔，何小海，滕奇志，等.结合Hausdorff距离和最长公共子序列的轨迹分类［J］.电子与信息学报，2013，35(4)：784-790.
WEI Longxiang, HE Xiaohai, TENG Qizhi, et al. Trajectory classification based on Hausdorff distance and longest common subsequence［J］. Journal of Electronics &
Information Technology, 2013,35(4):784-790.
［8］胡晶.基于AIS的船舶轨迹分析与应用系统的设计与实现［D］.武汉：华中师范大学，2015.
HU Jin.Design and Implementation of Vessel Trajectory Analysis and Application System Based on AIS［D］. Wuhan: Central China Normal University,2015.
［9］ AGRAWAL R, FALOUTSOS C, SWAMI A N. Efficient similarity search in sequence databases［C］//International Conference on Foundations of Data Organization and
Algorithms. Berlin: Springer-Verlag, 1993:69-84.
［10］ CHEN Lei, ZSU M T, ORIA V. Robust and fast similarity search for moving object trajectories［C］// Proceedings of the 2005 ACM SIGMOD International
Conference on Management of Data. New York: ACM, 2005:491-502.
［11］ LEE Seok-Lyong, CHUN Seok-Ju, KIM D H, et al. Similarity search for multidimensional data sequences［C］// Proceedings of IEEE 16th International Conference
on Data Engineering. San Diego: IEEE, 2000:599-608.
［12］ ELNEKAVE S, LAST M, MAIMON O. Incremental clustering of mobile objects［C］// IEEE International Conference on Data Engineering Workshop. Washington, D.
C.,: IEEE, 2007:585-592.
［13］ BASHIR F, KHOKHAR A, SCHONFELD D. Segmented trajectory based indexing and retrieval of video data［C］// International Conference on Image Processing 2003.
Barcelona, Spain: IEEE, 2003:623-626.
［14］ PORIKLI F, HAGA T. Event detection by eigenvector decomposition using object and frame features［C］// 2004 Conference on Computer Vision and Pattern
Recognition Workshop. Washington, D. C.,: IEEE, 2004.
［15］袁和金，张艳宁，周涛，等.基于归一化编辑距离和谱聚类的轨迹模式学习方法［J］.计算机辅助设计与图形学学报，2008，20(6)：753-758.
YUAN Hejin, ZHANG Yanning, ZHOU Tao, et al. A trajectory pattern learning approach based on the normalized edit distance and spectral clustering algorithm［J］.
Journal of Computer-Aided Design and Computer Graphics, 2008,20(6):753-758.
［16］毛嘉莉，金澈清，章志刚，等.轨迹大数据异常检测：研究进展及系统框架［J］.软件学报，2017，28(1)：17-34.
MAO Jiali, JIN Ceqing, ZHANG Zhigang, et al. Anomaly detection for trajectory big data: advancements and framework［J］. Journal of Software, 2017,28(1):17-34.
［17］ ZHANG Zhang, HUANG Kaiqi, TAN Tan. Comparison of similarity measures for trajectory clustering in outdoor surveillance scenes［C］// International
Conference on Pattern Recognition 2006. Washington, D. C.,: IEEE, 2006:1135-1138.
［18］ LEE Jae-Gil, HAN Jiawei, WHANG Kyu-Young. Trajectory clustering:a partition-and-group framework［C］// Proceedingsof the 2007 ACM SIGMOD International
Conference on Management of Data. New York: ACM, 2007:593-604.
［19］袁冠，夏士雄，张磊，等.基于结构相似度的轨迹聚类算法［J］.通信学报，2011，32(9)：103-110.
YUAN Guan, XIA Shixiong, ZHANG Lei, et al. Trajectory clustering algorithm based on structural similarity［J］. Journal of Communica-tions, 2011,32(9):103-110.
［20］王天真，郝瑞吉，汤天浩，等.一种基于数据挖掘的GIS及在航海中的应用［J］.中国航海，2003(3)：1-4.
WANG Tianzhen, HAO Ruijie, TANG Tianhao, et al. A data mining method for GIS in marine engineering［J］. Navigation of China, 2003(3):1-4.
［21］邱洪生.基于卡尔曼滤波的船舶航行轨迹异常行为预测算法研究［D］.天津：河北工业大学，2012.
HONG Qiusheng. Research on Forecasting Ship Sailed Track Behavioral Abnormalities Algorithm Based on Kalman Filter［D］. Tianjin: Hebei University of Technology,
2012.
［22］胡晶.基于AIS的船舶轨迹分析与应用系统的设计与实现［D］.武汉：华中师范大学，2015.
HU Jing. Design and Implementation of Vessel Trajectory Analysis and Application System Based on AIS［D］. Wuhan: Central China Normal University, 2015.
［23］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 Xiao. Study on Ships Trajectory Clustering Model Based on AIS Data［D］. Xiamen: Jimei University, 2015.
［24］魏照坤.基于AIS的船舶轨迹聚类与应用［D］.大连：大连海事大学，2015.
WEI Zhaokun. The Vessels Trajectory Clustering and Its Application Based on AIS［D］. Dalian: Dalian Maritime University, 2015.
［25］谢斌，陈莉明.密度聚类方法在船舶航迹图谱挖掘中的应用研究［J］.舰船科学技术，2016，38(7A)：100-102.
XIE Bin, CHEN Liming. Research on the density clustering method in ship track patternmining［J］. Ship Science and Technology, 2016, 38(7A):100-102.
［26］张洛蒙.出租车异常轨迹挖掘系统设计与实现［J］.福建电脑，2018(1)：134-135.
ZHANG Luomeng. Design and implementation of taxi abnormal trajectory mining system［J］. Fujian Computer, 2018(1): 134-135.
［27］赵梁滨.船舶轨迹的数据挖掘框架及应用［D］.大连：大连海事大学，2016.
ZHAO Liangbin. Research and Application of the Mining Framework of Trajectory Data for Vessels［D］. Dalian: Dalian Maritime University, 2016.
［28］王建军.基于出租车轨迹挖掘的寻客路线推荐［D］.湘潭：湖南科技大学，2016.
WANG Jianjun. Mining Taxis Trajectories for Cruising Routes Recommendation［D］. Xiangtan: Hunan University of Science and Technology, 2016.
［29］周宇鹏，牛保宁.密度聚类划分时间段的动态热度路网构建［J］.计算机工程与设计，2017，38(11)：3023-3028.
ZHOU Yupeng, NIU Baoning. Constructing dynamic hot road networks using time points density clustering［J］. Computer Engineering and Design, 2017, 38(11):3023-
3028.
［30］ DAHLBOM A, NIKLASSON L. Trajectory clustering for coastal surveillance［C］// 2017 10th International Conference on Information Fusion. Washington, D. C.,:
IEEE, 2007:1-8.
［31］ PALLOTTA G, VESPE M, BRYAN K. Vessel pattern knowledge discovery from AIS data: aframework for anomaly detection and route prediction［J］. Entropy, 2013,
15(6):2218-2245.
［32］ NG A Y, JORDAN M I, WEISS Y. On spectral clustering: analysis and an algorithm［C］// Proceedings of 14th International Conference on Neural Information
Processing Systems: Natural and Synthetic. MA, U.S.A.: MIT Press, 2002:849-856.
［33］ RIVEIRO M, JOHANSSON F, ZIEMKE T, et al. Supporting maritime situation awareness using self organizing maps and gaussian mixture models［C］// Proceedings
of the 2008 conference on Tenth Scandinavian Conference on Artificial Intelligence: SCAI 2008. Amsterdam, the Netherlands: IOS Press, 2008:84-91.
［34］ LAXHAMMAR R. Anomaly detection for sea surveillance［C］// 2008 11th International Conference on Information Fusion. Washington, D. C.,: IEEE, 2008:1-8.
［35］ RISTIC B, SCALA B L, MORELANDE M, et al. Statistical analysis of motion patterns in AIS data: anomaly detection and motion prediction［J］.International
Conference on Information Fusion, 2008, 29(1):1-7.
［36］熊勇，瞿小豪，郭俊维，等.基于AIS数据的渡轮异常运动模式监测［J］.中国安全科学学报，2016，26(1)：100-103.
XIONG Yong, QU Xiaohao, GUO Junwei, et al. Monitoring of abnormal movement patterns of ferry based on AIS data［J］. China Safety Science Journal, 2016, 26(1):100
-103.
［37］ BOMBERGER N A, RHODES B J, SEIBERT M, et al. Associative learning of vessel motion patterns for maritime situation awareness［C］// 2006 9th International
Conference on Information Fusion. Washington, D. C.,: IEEE, 2007:1-8.
［38］ RHODES B J, BOMBERGER N A, SEIBERT M, et al. Maritime situation monitoring and awareness using learning mechanisms［C］// 2005 IEEE Military Communications
Conference. Washington, D. C.,: IEEE, 2005:646-652.
［39］ RHODES B J, BOMBERGER N A, ZANDIPOUR M. Probabilistic associative learning of vessel motion patterns at multiple spatial scales for maritime situation
awareness［C］// International Conference on Information Fusion. Washington, D. C.,: IEEE, 2007:1-8.
［40］ LAXHAMMAR R, FALKMAN G. Sequential conformal anomaly detection in trajectories based on Hausdorff distance［C］// Proceedings of the International
Conference on Information Fusion. Washington, D. C.: IEEE, 2011:1-8.
［41］ LAXHAMMAR R, FALKMAN G. Conformal prediction for distribution-independent anomaly detection in streaming vessel data［C］// Proceedings of the First
International Workshop on Novel Data Stream Pattern Mining Techniques. New York: ACM, 2011:47-55.
［42］ LAXHAMMAR R, FALKMAN G. Online detection of anomalous sub-trajectories: asliding window approach based on conformal anomaly detection and local outlier
factor［M］// Artificial Intelligence Applications and Innovations. Berlin: Springer-Verlag, 2012:192-202.
［43］ LAXHAMMAR R. Anomaly Detection in Trajectory Data for Surveillance Applications［D］. Orebro, Sweden: Orebro University, 2011.
［44］甄荣，金永兴，胡勤友，等.基于AIS信息和BP神经网络的船舶航行行为预测［J］.中国航海，2017，40(2)：6-10.
ZHEN Rong, JIN Yongxing, HU Qingyou, et al. Vessel behavior predection based on AIS data and BP neural network［J］. Navigation of China, 2017, 40(2):6-10.
［45］杨龙海，徐洪，张春.基于GPS数据的高速公路车辆异常行为检测［J］.重庆交通大学学报(自然科学版)，2018，37(5)：97-103.
YANG Longhai, XU Hong, ZHANG Chun. Vehicle abnormal behavior detection on freeway based on global positioning system data［J］. Journal of Chongqing Jiaotong
University(Natural Science), 2018,37(5):97-103.
［46］马文耀，吴兆麟，杨家轩，等.基于单向距离的谱聚类船舶运动模式识别［J］.重庆交通大学学报(自然科学版)，2015，34(5)：130-134.
MA Wenyao,WU Zhaolin, YANG Jiaxuan, et al. Vessel motion pattern recognition based on one-way distance spectral clustering algorithm［J］. Journal of Chongqing
Jiaotong University(Natural Science), 2015,34(5):130-134.
［47］李永攀，刘正江，郑中义.基于时空密度的船载AIS数据聚类分析方法研究［J］.重庆交通大学学报(自然科学版)，2018，37(10)：117-122.
LI Yongpan, LIU Zhengjiang, ZHENG Zhongyi. Clustering analysis method of shipborne AIS data based on spatio-temporal density［J］. Journal of Chongqing Jiaotong
University(Natural Science), 2018,37(10):117-122.

[1]	唐继强1, 2，钟鑫伟2，刘健1，李天瑞3. 基于时间序列季节分类模型的轨道交通客流短期预测[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 31-38.
[2]	戚春华，王笑男，朱守林，李航天. 基于驾驶员视觉兴趣区域的交通工程设施信息量阈值研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 53-60.
[3]	邓天民1，朱杰2，朱凯家1，屈治华3. 基于iForest+Biscting K-means的驾驶风格辨识方法研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 1-6.
[4]	许茂增,张莉. 基于双射软决策理论的路段拥堵影响力识别[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 7-11.
[5]	王涛1，谢思红1，黎文皓1,2，李文勇1. 基于FFOS-ELM和PF的短时交通流自适应预测模型[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 21-27.
[6]	张诚1，汪成银1，陈志伟2，张正向3，张子磊3. 基于空间流量度的城市路网关键节点挖掘方法[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 28-35.
[7]	王永岗，张衡，彭志鹏，周琬琦. 基于结构方程模型的出租车事故影响因素分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 36-42.
[8]	朱顺应，李维吉，林小媛，肖文彬，王红. 特色小镇游客车辆无复检管控点布设研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 52-58.
[9]	潘兵宏1,2，胡炜1，任卉1,单慧敏1. 基于TruckSim仿真下弯道货车侧滑速度模型研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 38-45.
[10]	吴文静，孙刃超，宗芳，贾洪飞. 居民低碳通勤出行的主观态度识别及影响分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 53-58.
[11]	李军，邓育新. 基于非负矩阵分解的出租车时空行为聚类分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 59-65.
[12]	成卫1，刘翔1，雷建明2. 基于RBF神经网络预测的交叉口信号周期时长优化[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 13-18.
[13]	史天亮，王文光. 信息观和粒子群算法在城市交通拥堵中的研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 19-25.
[14]	贺玉龙1,2，刘磊1,2，迟佳欣1,2. 高速公路车辆换道行为风险研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 26-33.
[15]	王露1，陈肖欣2，李华恩1. 大风雨雪气象条件下高速公路车辆稳定行驶的临界车速研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 34-40.