Highway Travel Time Data Fusion

Abstract

The development of new traffic monitoring systems and the increasing interest of road operators and researchers in obtaining reliable travel time measurements has leaded to the development of multiple travel time data sources. This situation represents a perfect environment for the implementation of data fusion systems to obtain the maximum accuracy from the available data. This paper presents a new approach to calculate highway travel times fusing different data sources: inductive loop detectors and toll ticket data. Although the data fusion algorithm presented herein is applied to these types of data, it could easily be generalized to other equivalent sources. The data fusion algorithm is applied to different travel time estimations in order to obtain a fused value more reliable than any of the individual estimations. The proposed algorithm overcomes some of the limitations of other methods, improving the spatial and temporal coverage, and determining the flow state (congested or not). The results obtained in the application of the methodology to the AP-7 highway, near Barcelona in Spain, are found to be reasonable and accurate.