The path inference filter: model-based low-latency map matching of probe vehicle data

09/09/2011
by   Timothy Hunter, et al.
0

We consider the problem of reconstructing vehicle trajectories from sparse sequences of GPS points, for which the sampling interval is between 10 seconds and 2 minutes. We introduce a new class of algorithms, called altogether path inference filter (PIF), that maps GPS data in real time, for a variety of trade-offs and scenarios, and with a high throughput. Numerous prior approaches in map-matching can be shown to be special cases of the path inference filter presented in this article. We present an efficient procedure for automatically training the filter on new data, with or without ground truth observations. The framework is evaluated on a large San Francisco taxi dataset and is shown to improve upon the current state of the art. This filter also provides insights about driving patterns of drivers. The path inference filter has been deployed at an industrial scale inside the Mobile Millennium traffic information system, and is used to map fleets of data in San Francisco, Sacramento, Stockholm and Porto.

READ FULL TEXT
research
09/25/2018

Map matching when the map is wrong: Efficient vehicle tracking on- and off-road for map learning

Map matching is a key part of many GIS applications, linking observed GP...
research
11/07/2017

A cross-vendor and cross-state analysis of the GPS-probe data latency

Crowdsourced GPS probe data has become a major source of real-time traff...
research
10/07/2019

Learning Navigation by Visual Localization and Trajectory Prediction

When driving, people make decisions based on current traffic as well as ...
research
01/18/2018

A methodology for calculating the latency of GPS-probe data

Crowdsourced GPS probe data has been gaining popularity in recent years ...
research
09/18/2022

A Map-matching Algorithm with Extraction of Multi-group Information for Low-frequency Data

The growing use of probe vehicles generates a huge number of GNSS data. ...
research
08/04/2022

Improving Fuzzy-Logic based Map-Matching Method with Trajectory Stay-Point Detection

The requirement to trace and process moving objects in the contemporary ...
research
03/16/2022

Extended vehicle energy dataset (eVED): an enhanced large-scale dataset for deep learning on vehicle trip energy consumption

This work presents an extended version of the Vehicle Energy Dataset (VE...

Please sign up or login with your details

Forgot password? Click here to reset