Traffic light status detection using movement patterns of vehicles

Joseph Campbell, Hani Ben Amor, Marcelo H. Ang, Georgios Fainekos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Vision-based methods for detecting the status of traffic lights used in autonomous vehicles may be unreliable due to occluded views, poor lighting conditions, or a dependence on unavailable high-precision meta-data, which is troublesome in such a safety-critical application. This paper proposes a complementary detection approach based on an entirely new source of information: The movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real and simulated data sets, resulting in up to 97% accuracy in each set.

Original languageEnglish (US)
Title of host publication2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages283-288
Number of pages6
ISBN (Electronic)9781509018895
DOIs
StatePublished - Dec 22 2016
Event19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016 - Rio de Janeiro, Brazil
Duration: Nov 1 2016Nov 4 2016

Other

Other19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016
CountryBrazil
CityRio de Janeiro
Period11/1/1611/4/16

Fingerprint

Telecommunication traffic
Metadata
Lighting

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Campbell, J., Ben Amor, H., Ang, M. H., & Fainekos, G. (2016). Traffic light status detection using movement patterns of vehicles. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016 (pp. 283-288). [7795568] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC.2016.7795568

Traffic light status detection using movement patterns of vehicles. / Campbell, Joseph; Ben Amor, Hani; Ang, Marcelo H.; Fainekos, Georgios.

2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 283-288 7795568.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Campbell, J, Ben Amor, H, Ang, MH & Fainekos, G 2016, Traffic light status detection using movement patterns of vehicles. in 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016., 7795568, Institute of Electrical and Electronics Engineers Inc., pp. 283-288, 19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016, Rio de Janeiro, Brazil, 11/1/16. https://doi.org/10.1109/ITSC.2016.7795568
Campbell J, Ben Amor H, Ang MH, Fainekos G. Traffic light status detection using movement patterns of vehicles. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 283-288. 7795568 https://doi.org/10.1109/ITSC.2016.7795568
Campbell, Joseph ; Ben Amor, Hani ; Ang, Marcelo H. ; Fainekos, Georgios. / Traffic light status detection using movement patterns of vehicles. 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 283-288
@inproceedings{690553247d3f4e6c95e9b074750e51ea,
title = "Traffic light status detection using movement patterns of vehicles",
abstract = "Vision-based methods for detecting the status of traffic lights used in autonomous vehicles may be unreliable due to occluded views, poor lighting conditions, or a dependence on unavailable high-precision meta-data, which is troublesome in such a safety-critical application. This paper proposes a complementary detection approach based on an entirely new source of information: The movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real and simulated data sets, resulting in up to 97{\%} accuracy in each set.",
author = "Joseph Campbell and {Ben Amor}, Hani and Ang, {Marcelo H.} and Georgios Fainekos",
year = "2016",
month = "12",
day = "22",
doi = "10.1109/ITSC.2016.7795568",
language = "English (US)",
pages = "283--288",
booktitle = "2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Traffic light status detection using movement patterns of vehicles

AU - Campbell, Joseph

AU - Ben Amor, Hani

AU - Ang, Marcelo H.

AU - Fainekos, Georgios

PY - 2016/12/22

Y1 - 2016/12/22

N2 - Vision-based methods for detecting the status of traffic lights used in autonomous vehicles may be unreliable due to occluded views, poor lighting conditions, or a dependence on unavailable high-precision meta-data, which is troublesome in such a safety-critical application. This paper proposes a complementary detection approach based on an entirely new source of information: The movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real and simulated data sets, resulting in up to 97% accuracy in each set.

AB - Vision-based methods for detecting the status of traffic lights used in autonomous vehicles may be unreliable due to occluded views, poor lighting conditions, or a dependence on unavailable high-precision meta-data, which is troublesome in such a safety-critical application. This paper proposes a complementary detection approach based on an entirely new source of information: The movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real and simulated data sets, resulting in up to 97% accuracy in each set.

UR - http://www.scopus.com/inward/record.url?scp=85010061466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010061466&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2016.7795568

DO - 10.1109/ITSC.2016.7795568

M3 - Conference contribution

SP - 283

EP - 288

BT - 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -