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

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

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 %.
Luk

Detaljer

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
PublikationsartForskning
Peer reviewJa
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

Kort

ID: 257673301