Citation

Wang Z, Ye J, Tang J. Transp. Saf. Environ. 2023; 5(2): tdac049.

Copyright

(Copyright © 2023, Oxford University Press)

DOI

10.1093/tse/tdac049

PMID

unavailable

Abstract

In the complex urban road traffic network, a sudden accident leads to rapid congestion in the nearby traffic region, which even makes the local traffic network capacity quickly reduce. Therefore, an efficient monitoring system for abnormal conditions of the urban road network plays a crucial role in the tolerance of the urban road network. The traditional traffic monitoring system not only costs a lot in construction and maintenance, but also may not cover the road network comprehensively, which could not meet the basic needs of traffic management. Only a more comprehensive and intelligent monitoring method is able to identify traffic anomalies more effectively and quickly, so that it can provide more effective support for traffic management decisions. The extensive use of positioning equipment made us able to obtain accurate trajectory data. This paper presents a traffic anomaly monitoring and prediction method based on vehicle trajectory data. This model uses deep learning to detect abnormal trajectory on the traffic road network. The method effectively analyses the abnormal source and potential anomaly to judge the abnormal region, which provides an important reference for the traffic department to take effective traffic control measures. Finally, the paper uses Internet vehicle trajectory data from Chengdu (China) to test and obtains an accurate result.

Language: en