港口内运车辆作业轨迹异常检测  

ANOMALY DETECTION OF OPERATION TRAJECTORY OF VEHICLES IN PORT

作　　者：胡俊雅 李勇华[1,2] 唐晨[1,2] Hu Junya;Li Yonghua;Tang Chen(College of Computer Science and Technology,Wuhan University of Technology,Wuhan 430063,Hubei,China;Hubei Key Laboratory of Transportation Internet of Things,Wuhan University of Technology,Wuhan 430070,Hubei,China)

机构地区：[1]武汉理工大学计算机科学与技术学院,湖北武汉430063 [2]武汉理工大学交通物联网技术湖北省重点实验室,湖北武汉430070

出　　处：《计算机应用与软件》2022年第1期71-78,125,共9页Computer Applications and Software

基　　金：内河航运技术湖北省重点实验室基金项目(NHHY2017003);交通物联网技术湖北省重点实验室基金项目(2017III028-002)。

摘　　要：内运车是用于港口内部货物转运的车辆。如果在转运过程中缺乏监管,很容易造成偷货(将A货主的货转移至B货主堆位)、漏货(货物转运未经过计量设备)等行为,给港口带来严重的损失。为了有效杜绝这类情况的发生,提出轨迹真实状态序列提取方法并设计自适应有限状态机(Adaptive Finite State Machine,AFSM)对内运车作业是否产生异常意图进行判断。实验采用重庆市某港口内运车辆一个月(7547趟)的真实轨迹数据,结果表明轨迹真实状态序列提取方法能有效提取内运车作业轨迹的真实状态,使用AFSM进行轨迹异常检测的精度高达95%~96%。The port internal transporting vehicle is used to transfer cargo in the port.If there is no or less supervision in the transshipment process,it is easy to cause serious loss to the ports such as goods stolen(Transfer cargo of owner A to stall of owner B),leakage of cargos(Goods transshipped without passing through measuring equipment)et al.In order to effectively eliminate the occurrence of this situation,a method for extracting the true state sequence of the trajectory is proposed,and an adaptive finite state machine(AFSM)is designed to judge whether the operation of internal transport vehicle has an abnormal intention.The real trajectory data of a port in Chongqing for one month(7547 times)were used in this experiment.The experimental results show that the real-state sequence extraction method can effectively extract the real state of the port internal transport vehicle trajectory,and AFSM trajectory anomaly detection accuracy can reach 95%~96%.

关 键 词：轨迹 异常检测 路网匹配 有限状态机 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]