An advanced deep learning approach to real-time estimation of lane-based queue lengths at a signalized junction

Lee, S; Xie, K; Ngoduy, D; Keyvan-Ekbatani, M

An advanced deep learning approach to real-time estimation of lane-based queue lengths at a signalized junction

Lee, S

Xie, K Ngoduy, D

Keyvan-Ekbatani, M

Permalink

Publication Type:: Journal Article
Citation:: Transportation Research Part C: Emerging Technologies, 2019, 109 pp. 117 - 136
Issue Date:: 2019-12-01

Closed Access

	Filename	Description	Size
	09.An advanced deep learning approach to real-time estimation.pdf	Published Version	6.78 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lee, S https://orcid.org/0000-0003-2356-3677	en_US
dc.contributor.author	Xie, K	en_US
dc.contributor.author	Ngoduy, D https://orcid.org/0000-0003-2356-3677	en_US
dc.contributor.author	Keyvan-Ekbatani, M	en_US
dc.date.issued	2019-12-01	en_US
dc.identifier.citation	Transportation Research Part C: Emerging Technologies, 2019, 109 pp. 117 - 136	en_US
dc.identifier.issn	0968-090X	en_US
dc.identifier.uri	http://hdl.handle.net/10453/136713
dc.description.abstract	© 2019 Elsevier Ltd In this study, we develop a real-time and novel estimation method of lane-based queue lengths using two deep learning processes, which include of a Convolutional Neural Network (CNN) into a Long Short-Term Memory (LSTM). This approach not only outperforms the recently developed real-time estimation of lane-based queue lengths but also captures the spatiotemporal attributes of traffic. There are three primary challenges to design a deep learning based queue estimation model. First, the CNN and the LSTM are integrated to estimate lane-based queue lengths minimizing accumulative counting errors. Furthermore, short-term arrival patterns and long-term traffic demand trends are captured by the LSTM to improve the accuracy of estimates of cycle-based proportional lane-uses. In addition, imaged second-based occupancy rates and impulse memories are used to identify whether vehicular queues are remained at the end of each cycle by using the CNN. In numerical examples and case study, the integrated CNN – LSTM method shows excellent performance to estimate queue lengths in individual lanes in seconds compared to the other approaches applied in this paper. This work paves the way for the applicability of the deep learning to estimate traffic quantities in real-time for lane-based adaptive traffic control systems (ATCS). Furthermore, we will introduce offset in a signal plan and lane-based turning proportion on the proposed framework to explain vehicular spillbacks in an individual lane and a grid lock for pursuing coordinated traffic movements along arterials and in signalized urban networks.	en_US
dc.relation.ispartof	Transportation Research Part C: Emerging Technologies	en_US
dc.relation.isbasedon	10.1016/j.trc.2019.10.011	en_US
dc.subject.classification	Logistics & Transportation	en_US
dc.title	An advanced deep learning approach to real-time estimation of lane-based queue lengths at a signalized junction	en_US
dc.type	Journal Article
utslib.citation.volume	109	en_US
utslib.for	0102 Applied Mathematics	en_US
utslib.for	0802 Computation Theory and Mathematics	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
utslib.for	15 Commerce, Management, Tourism and Services	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	109	en_US

Abstract:

© 2019 Elsevier Ltd In this study, we develop a real-time and novel estimation method of lane-based queue lengths using two deep learning processes, which include of a Convolutional Neural Network (CNN) into a Long Short-Term Memory (LSTM). This approach not only outperforms the recently developed real-time estimation of lane-based queue lengths but also captures the spatiotemporal attributes of traffic. There are three primary challenges to design a deep learning based queue estimation model. First, the CNN and the LSTM are integrated to estimate lane-based queue lengths minimizing accumulative counting errors. Furthermore, short-term arrival patterns and long-term traffic demand trends are captured by the LSTM to improve the accuracy of estimates of cycle-based proportional lane-uses. In addition, imaged second-based occupancy rates and impulse memories are used to identify whether vehicular queues are remained at the end of each cycle by using the CNN. In numerical examples and case study, the integrated CNN – LSTM method shows excellent performance to estimate queue lengths in individual lanes in seconds compared to the other approaches applied in this paper. This work paves the way for the applicability of the deep learning to estimate traffic quantities in real-time for lane-based adaptive traffic control systems (ATCS). Furthermore, we will introduce offset in a signal plan and lane-based turning proportion on the proposed framework to explain vehicular spillbacks in an individual lane and a grid lock for pursuing coordinated traffic movements along arterials and in signalized urban networks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/136713