Distributed Anomaly Detection Algorithm for Spatio-Temporal Trajectories of Vehicles
Liping Lu, Hao Cheng, Shengwu Xiong, Pengfei Phil Duan, Yuan Xiao · 2017
With extensive use of Internet of Vehicle (IoV) technologies in vehicle traffic management, real-time analysis of vehicle behavior trajectories is of great significance to the assessment of traffic conditions and the avoidance of abnormal conditions. This paper presents a solution which can efficiently deal with real-time streaming data of trajectory and excavate temporal and spatial abnormal information. In order to represent the local feature information of the trajectory and solve the problem of large loss of information in the feature point extraction algorithm, a trajectory partitioning strategy based on multi- motion feature and a similarity measure method based on trajectory structure are proposed. And based on the proposed strategy and method, a distributed clustering algorithm is designed for streaming trajectories to improve the efficiency of clustering algorithm. In order to solve the problem of massive calculation of distance and neighborhood density in trajectory anomaly detection algorithm, the data set is pruned by track clustering results, and the efficiency of the algorithm increases the real-time performance of abnormal trajectory detection.