Highlights A model for scaling mobility data to match a population of trips. A model that doesn’t require data other than mobility data for a region and vehicle passage counts for few locations on the road network. Visual tools which can be used to verify model predictions for this model and others.
Abstract This paper considers the problem of inferring statewide traffic patterns by scaling massive GPS trajectory data, which capture about 3% of the overall traffic in Utah. It proposes a least absolute deviations model with controlled overfitting to scale 2.3 million trajectories such that resulting data best fit vehicle counts measured by 296 traffic sensors across the state. The proposed model improves on an often-cited approach from the literature and achieves 45% lower error for locations not seen in model training, obtaining 18% median hourly error across all test locations.
Scaling GPS trajectories to match point traffic counts: A convex programming approach and Utah case study
2020-09-21
Article (Journal)
Electronic Resource
English
A Bayesian Approach to Update Traffic Flows from Traffic Counts
British Library Conference Proceedings | 1993
|Estimation of Traffic Counts Using Traffic Flow Patterns
NTIS | 1978
|Canton counts its traffic by postcard
Engineering Index Backfile | 1949