Obtaining Dense Road Speed Estimates from Sparse GPS Measurements

Phan, Andrew; Ferrie, Frank P.

doi:10.1109/itsc.2008.4732598

Cited by 4 publications

(2 citation statements)

References 18 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have diversified over the years with the arrival of new acquisition technologies. Bluetooth scanners, automated number plate recognition [5], and video footage from cameras [6] are a few of the numerous ways to estimate traffic conditions. In recent years, GPS data from probe vehicles or smartphones have taken the lead.…”

Section: Literature Reviewmentioning

confidence: 99%

From Massive Trajectory Data to Traffic Modeling for Better Behavior Prediction in a Usage-Based Insurance Context

Blais

Badard

Duchesne

et al. 2020

IJGI

View full text Add to dashboard Cite

Usage-Based Insurance (UBI) is an insurance framework that has made its appearance in the last few years. It allows direct measurement of the traveling of policyholders, hence the growing interest of the industry to better understand driving behaviors. UBI generates large data volumes, from which events can be extracted, like harsh brakes or accelerations. Still, these events are measured without contextual information, which limits their explanatory power. Traffic is one of these types of contextual information that may have great potential, but access to such data remains an issue. Solutions exist, like traffic data from external providers, but for insurance companies that conduct business over large areas, this could result in very large costs. This paper demonstrates that data from insurance companies acquired via UBI can be used to model traffic. A method based on link travel time is proposed and tested on four Canadian cities. Then, routes created with the model are compared with those created using Google Maps. The results show that for 38 routes with an average length of around 5 km, the difference between the travel time of the routes of the proposed model and Google Maps is as small as one second on average.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

From Massive Trajectory Data to Traffic Modeling for Better Behavior Prediction in a Usage-Based Insurance Context

Blais

Badard

Duchesne

et al. 2020

IJGI

View full text Add to dashboard Cite

show abstract

“…In Dailey et al (2000) and Pattara-atikom et al (2006), the mean travel speed of road segment was obtained, which is statistical average speed without considering road's space characteristics. Paper (Poomrittigul et al, 2008;Phan and Ferrie, 2008;Wei et al, 2007) used probe vehicles, GPS-based personal cars (Poomrittigul et al, 2008) or GPS-based roving ambulances (Phan and Ferrie, 2008) to obtain mean travel speed. This average speed contains road's space characteristics where these vehicles were driving.…”

Section: Based On Gpsmentioning

confidence: 99%

A measurement of real travel speed for road segment with magnetic sensors

Zhang

Kuang

2013

COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to introduce a weighted average method to process speed measurements from multiple magnetic sensors, which are installed on road segments. Speeds are weighted-averaged in a fix duration time (5 minutes) for each sensor across location index of the sensor where it was installed. The proposed method is evaluated with numeric and simulation results. Design/methodology/approach -Unlike traditional vehicle average speed measurements, the authors propose a weighted-average speed measurement method of road segment, using wireless magnetic sensor nodes, which are installed on the measured road segment. Magnetic sensors offer a non-contact vehicle detection method, and small sensors with relatively low power consumption. Using magnetic sensors, the local changes in the Earth's magnetic field caused by the presence of a moving vehicle can be measured and the vehicle's speed obtained. Next, using adaptive weighted average algorithm and space weighted algorithm in a fixed period, the weighted average travel speed of road segment can be obtained. Findings -In current literature, there are many methods to measure vehicles' speed on road, such as image-based, radar-based, GPS-based, double-loop-based or magnetic sensor-based, but most of them only provide individual vehicle speed. Using probe vehicles, mean travel speed of road segment can be obtained, but it is costly on hardware and measurement, because many probe-vehicles need to be used on roads and many measurements need to be done everyday. GPS data can be used to provide valuable travel speed data for Intelligent Transportation System (ITS). However, not every vehicle is equipped with GPS and to access ID numbers for personal cars would entail privacy problems. Mean travel speed of road segment is obtained based on statistical average speed. Generally, statistical average speed is used, which is based upon Gaussian distribution is not true in traffic systems. Originality/value -By using wireless magnetic sensor nodes, vehicle instantaneous speeds are obtained in a fixed time when vehicles are passing over sensor nodes and then the adaptive weighted average speed on each sensor node location is computed based on the monitoring data from each sensor node in the fixed time. Considering different weights of each lane and road space (in the middle of the road segment or near the intersection), the proposed scheme can obtain the weighted-average speed of the road segment.

show abstract

Interpolating Sparse GPS Measurements Via Relaxation Labeling and Belief Propagation for the Redeployment of Ambulances

Phan

Ferrie

2011

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Obtaining Dense Road Speed Estimates from Sparse GPS Measurements

Cited by 4 publications

References 18 publications

From Massive Trajectory Data to Traffic Modeling for Better Behavior Prediction in a Usage-Based Insurance Context

From Massive Trajectory Data to Traffic Modeling for Better Behavior Prediction in a Usage-Based Insurance Context

A measurement of real travel speed for road segment with magnetic sensors

Interpolating Sparse GPS Measurements Via Relaxation Labeling and Belief Propagation for the Redeployment of Ambulances

Contact Info

Product

Resources

About