We present a simplified map-matching algorithm that could be considered a robust tool to identify the correct path between consecutive GPS traces over a large number of scenarios avoiding ambiguous route assignment consistent with trajectory samples. Our formulation relies on a hidden Markov model (HMM) framework including multiple features such as the travelled distances between consecutive GPS traces, the signal quality and the direction of travel. The accuracy of the algorithm was evaluated using Floating Car Data (FCD) from a large fleet of privately owned cars and commercial vehicles equipped with devices capable of acquiring GPS positions with a sampling period of about 30 s. Experimental results showed an average accuracy of the model of about 85%. Results suggest our model is suitable not only to identify trajectories for specific origins and destinations, but also to extract traffic and travel time patterns.

A Simplified Map-Matching Algorithm for Floating Car Data

Karagulian F.;Messina G.;Valenti G.;Liberto C.;Carapellucci F.
2021-01-01

Abstract

We present a simplified map-matching algorithm that could be considered a robust tool to identify the correct path between consecutive GPS traces over a large number of scenarios avoiding ambiguous route assignment consistent with trajectory samples. Our formulation relies on a hidden Markov model (HMM) framework including multiple features such as the travelled distances between consecutive GPS traces, the signal quality and the direction of travel. The accuracy of the algorithm was evaluated using Floating Car Data (FCD) from a large fleet of privately owned cars and commercial vehicles equipped with devices capable of acquiring GPS positions with a sampling period of about 30 s. Experimental results showed an average accuracy of the model of about 85%. Results suggest our model is suitable not only to identify trajectories for specific origins and destinations, but also to extract traffic and travel time patterns.
2021
978-3-030-75077-0
978-3-030-75078-7
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12079/66109
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
social impact