Speed profile estimation using license plate recognition data

•A systematic LPR data-mending method is proposed.•Propose a modified car-following model corresponding to LPR data characteristics.•The speed profile of vehicles on road segments is estimated using proposed model.•The proposed model is validated by a field experiment.•The model can fully capture th...

Full description

Saved in:
Bibliographic Details
Published in:Transportation research. Part C, Emerging technologies Vol. 82; pp. 358 - 378
Main Authors: Mo, Baichuan, Li, Ruimin, Zhan, Xianyuan
Format: Journal Article
Language:English
Published: Elsevier India Pvt Ltd 01.09.2017
Subjects:
Car-following model
Emission estimation
License plate number matching procedure
License plate recognition
Minimum cost bipartite matching
Speed profile estimation
MRE
Speed profile estimation
Car-following model
Minimum cost bipartite matching
RMSE
CMEM
LPR
MAE
NGSIM
FVD
GA
License plate number matching procedure
License plate recognition
Emission estimation
ISSN:0968-090X, 1879-2359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A systematic LPR data-mending method is proposed.•Propose a modified car-following model corresponding to LPR data characteristics.•The speed profile of vehicles on road segments is estimated using proposed model.•The proposed model is validated by a field experiment.•The model can fully capture the pattern of ground truth speed profile. Vehicle speed profile is a fundamental data support for calculating vehicular emission using the micro-emission model. However, achieving accuracy and breadth for the speed profile estimation is difficult. This study proposes a new vehicle speed profile estimation model using license plate recognition (LPR) data. This model allows speed profile estimation of every individual vehicle between two consecutive intersections. A systematic LPR data-mending method is developed to infer the information of unmatched vehicles. Using the complete arrival and departure information as boundary conditions, a customized car-following model combined with dummy-overtaking hypothesis and boundary constraints is then applied to estimate the speed profile of vehicles. The proposed model is validated using ground truth speed information from a field experiment conducted in Langfang City in China. Results show that the model can fully capture the pattern of ground truth speed profile. A complementary model validation using the Next Generation Simulation dataset and a model application for calculating emissions are also conducted. The numerical results indicate the effectiveness of the proposed model in estimating vehicle speed profile and emissions.
ISSN:0968-090X
1879-2359
DOI:10.1016/j.trc.2017.07.006