|Publication type:||Conference other|
|Type of review:||Not specified|
|Title:||Travel time estimation for long freeway sections|
|Conference details:||Swiss Statistics Meeting, Lucerne, 14 -16 November 2007|
|Publisher / Ed. Institution:||Swiss Statistical Society (SSS)|
|Subjects:||Traffic; Global alignment|
|Abstract:||Using global alignment algorithm and image processing for travel time estimation We present a novel approach to estimate the travel times between subsequent detector stations in a freeway network with long distances between detector stations and various unobserved on- and off-ramps. The approach relies on two pattern matching methodologies: (i) an algorithm based on global sequence alignment and (ii) an algorithm based on image processing and pattern classification. The network under investigation was a two-lane freeway. The maximum distance between detector stations, for which travel times estimations were carried out was about 20 km and there were three on- and off-ramps in between with no measurements available. The algorithm was applied on real data with unknown travel times but known macroscopic traffic parameters and on simulated data with known travel times, allowing us to verify the estimated travel times. The estimated travel times show that for the investigated scenarios all relevant travel time characteristics were correctly identified. Moreover, a comparison of the estimates with the 'true' travel times has shown good performance and accuracy.|
|Fulltext version:||Published version|
|License (according to publishing contract):||Licence according to publishing contract|
|Departement:||School of Engineering|
|Organisational Unit:||Institute of Data Analysis and Process Design (IDP)|
|Appears in collections:||Publikationen School of Engineering|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.