Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

13 Citationer (Scopus)
71 Downloads (Pure)

Resumé

Traffic light detection (TLD) is a vital part of both intel- ligent vehicles and driving assistance systems (DAS). Gen- eral for most TLDs is that they are evaluated on small and private datasets making it hard to determine the exact per- formance of a given method. In this paper we apply the state-of-the-art, real-time object detection system You Only Look Once, (YOLO) on the public LISA Traffic Light dataset available through the VIVA-challenge, which contain a high number of annotated traffic lights, captured in varying light and weather conditions.
The YOLO object detector achieves an AUC of impres- sively 90.49 % for daysequence1, which is an improvement of 50.32 % compared to the latest ACF entry in the VIVA- challenge. Using the exact same training configuration as the ACF detector, the YOLO detector reaches an AUC of 58.3 %, which is in an increase of 18.13 %.
OriginalsprogEngelsk
Titel2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops : Traffic Surveillance Workshop and Challenge
ForlagIEEE
Publikationsdato21 jul. 2017
ISBN (Trykt)978-1-5386-0734-3
ISBN (Elektronisk)978-1-5386-0733-6
DOI
StatusUdgivet - 21 jul. 2017
Begivenhed2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge - Hawaii Convention Center, Honolulu, USA
Varighed: 21 jul. 201726 jul. 2017

Konference

Konference2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge
LokationHawaii Convention Center
LandUSA
ByHonolulu
Periode21/07/201726/07/2017
NavnIEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
ISSN2160-7516

Fingerprint

Telecommunication traffic
Detectors
Intelligent vehicle highway systems

Citer dette

Jensen, M. B., Nasrollahi, K., & Moeslund, T. B. (2017). Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. I 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge IEEE. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) https://doi.org/10.1109/CVPRW.2017.122
Jensen, Morten Bornø ; Nasrollahi, Kamal ; Moeslund, Thomas B. / Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge. IEEE, 2017. (IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)).
@inproceedings{d66ada98bc78476aaf487af9f3c2f655,
title = "Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data",
abstract = "Traffic light detection (TLD) is a vital part of both intel- ligent vehicles and driving assistance systems (DAS). Gen- eral for most TLDs is that they are evaluated on small and private datasets making it hard to determine the exact per- formance of a given method. In this paper we apply the state-of-the-art, real-time object detection system You Only Look Once, (YOLO) on the public LISA Traffic Light dataset available through the VIVA-challenge, which contain a high number of annotated traffic lights, captured in varying light and weather conditions.The YOLO object detector achieves an AUC of impres- sively 90.49 {\%} for daysequence1, which is an improvement of 50.32 {\%} compared to the latest ACF entry in the VIVA- challenge. Using the exact same training configuration as the ACF detector, the YOLO detector reaches an AUC of 58.3 {\%}, which is in an increase of 18.13 {\%}.",
author = "Jensen, {Morten Born{\o}} and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2017",
month = "7",
day = "21",
doi = "10.1109/CVPRW.2017.122",
language = "English",
isbn = "978-1-5386-0734-3",
series = "IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)",
publisher = "IEEE",
booktitle = "2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops",
address = "United States",

}

Jensen, MB, Nasrollahi, K & Moeslund, TB 2017, Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. i 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge. IEEE, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge, Honolulu, USA, 21/07/2017. https://doi.org/10.1109/CVPRW.2017.122

Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. / Jensen, Morten Bornø; Nasrollahi, Kamal; Moeslund, Thomas B.

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge. IEEE, 2017. (IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data

AU - Jensen, Morten Bornø

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2017/7/21

Y1 - 2017/7/21

N2 - Traffic light detection (TLD) is a vital part of both intel- ligent vehicles and driving assistance systems (DAS). Gen- eral for most TLDs is that they are evaluated on small and private datasets making it hard to determine the exact per- formance of a given method. In this paper we apply the state-of-the-art, real-time object detection system You Only Look Once, (YOLO) on the public LISA Traffic Light dataset available through the VIVA-challenge, which contain a high number of annotated traffic lights, captured in varying light and weather conditions.The YOLO object detector achieves an AUC of impres- sively 90.49 % for daysequence1, which is an improvement of 50.32 % compared to the latest ACF entry in the VIVA- challenge. Using the exact same training configuration as the ACF detector, the YOLO detector reaches an AUC of 58.3 %, which is in an increase of 18.13 %.

AB - Traffic light detection (TLD) is a vital part of both intel- ligent vehicles and driving assistance systems (DAS). Gen- eral for most TLDs is that they are evaluated on small and private datasets making it hard to determine the exact per- formance of a given method. In this paper we apply the state-of-the-art, real-time object detection system You Only Look Once, (YOLO) on the public LISA Traffic Light dataset available through the VIVA-challenge, which contain a high number of annotated traffic lights, captured in varying light and weather conditions.The YOLO object detector achieves an AUC of impres- sively 90.49 % for daysequence1, which is an improvement of 50.32 % compared to the latest ACF entry in the VIVA- challenge. Using the exact same training configuration as the ACF detector, the YOLO detector reaches an AUC of 58.3 %, which is in an increase of 18.13 %.

U2 - 10.1109/CVPRW.2017.122

DO - 10.1109/CVPRW.2017.122

M3 - Article in proceeding

SN - 978-1-5386-0734-3

T3 - IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

BT - 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops

PB - IEEE

ER -

Jensen MB, Nasrollahi K, Moeslund TB. Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. I 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Traffic Surveillance Workshop and Challenge. IEEE. 2017. (IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)). https://doi.org/10.1109/CVPRW.2017.122