An Algorithm for Road Closure Detection from Vehicle Probe Data

We developed an algorithm for automatically detecting road closures by monitoring vehicle probe data. The algorithm applies to a large class of roads and in the implementation presented was optimized for lower-volume roads. It is suitable for batch as well as real-time applications, the latter class...

Full description

Saved in:
Bibliographic Details
Published in:ACM transactions on spatial algorithms and systems 2019-08, Vol.5 (2), p.1-13
Main Authors: Pietrobon, Davide, Lewis, Andrew P., Heverly-Coulson, Gavin S.
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We developed an algorithm for automatically detecting road closures by monitoring vehicle probe data. The algorithm applies to a large class of roads and in the implementation presented was optimized for lower-volume roads. It is suitable for batch as well as real-time applications, the latter class being the most valuable to guarantee a continuously up-to-date traffic product. The algorithm compares the likelihood that every road segment meeting certain requirements is closed or open, and it triggers an alert whenever the likelihood of the observed probe activity is too small given a historical model. We implemented the algorithm and tested it on 12 metro areas in Western Europe. After optimizing parameters for performance on lower-volume roads, we obtained a precision of 92% on those roads and of 80% overall.
ISSN:2374-0353
2374-0361
DOI:10.1145/3325912