The acquisition approach of Reference sequences of road traffic running characteristics

Abstract

The accurate acquisition of road traffic states is the most important basis in the Intelligent Transportation Systems. Though the technology for collectting road traffic states information has been developed greatly, the data problems such as data invalidation also exist and have not been effectively settled. So the acquisition method of reference sequences of road traffic running characteristics is put forward in this paper. Firstly, the road traffic states information template is designed. Then the regularity analysis of the road traffic states information is carried out based on the Singular Value Decomposition of the road traffic states information matrix and the effective classification of eigenflows of the road traffic states information. Then the road traffic modes are divided into several different sub-modes according to different classification identifications. Finally the regularity information of road traffic states under different modes is abstracted and Reference sequences of road traffic running characteristics are effectively designed based on this regularity information. Typical expressways in Beijing are adopted for the application of the reference sequences of road traffic running characteristics for data imputation. The results prove that the reference sequences of road traffic running characteristics can be a effective complement in the process of date collection.