Traffic Light Detection at Night: Comparison of a Learning-based Detector and three Model-based Detectors

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

Traffic light recognition (TLR) is an integral part of any in- telligent vehicle, it must function both at day and at night. However, the majority of TLR research is focused on day-time scenarios. In this paper we will focus on detection of traffic lights at night and evalu- ate the performance of three detectors based on heuristic models and one learning-based detector. Evaluation is done on night-time data from the public LISA Traffic Light Dataset. The learning-based detector out- performs the model-based detectors in both precision and recall. The learning-based detector achieves an average AUC of 51.4 % for the two night test sequences. The heuristic model-based detectors achieves AUCs ranging from 13.5 % to 15.0 %.
Luk

Detaljer

Traffic light recognition (TLR) is an integral part of any in- telligent vehicle, it must function both at day and at night. However, the majority of TLR research is focused on day-time scenarios. In this paper we will focus on detection of traffic lights at night and evalu- ate the performance of three detectors based on heuristic models and one learning-based detector. Evaluation is done on night-time data from the public LISA Traffic Light Dataset. The learning-based detector out- performs the model-based detectors in both precision and recall. The learning-based detector achieves an average AUC of 51.4 % for the two night test sequences. The heuristic model-based detectors achieves AUCs ranging from 13.5 % to 15.0 %.
OriginalsprogEngelsk
TitelAdvances in Visual Computing : 11th International Symposium, ISVC 2015, Las Vegas, NV, USA, December 14-16, 2015, Proceedings, Part I
ForlagSpringer
Publikationsdatookt. 2015
Sider774-783
ISBN (Trykt)978-3-319-27856-8
ISBN (Elektronisk)978-3-319-27857-5
DOI
StatusUdgivet - okt. 2015
PublikationsartForskning
Peer reviewJa
BegivenhedISVC 2015 - Las Vegas, USA
Varighed: 14 dec. 201516 dec. 2015

Konference

KonferenceISVC 2015
LandUSA
ByLas Vegas
Periode14/12/201516/12/2015
SerieLecture Notes in Computer Science
Vol/bind9474
ISSN0302-9743

Download-statistik

Ingen data tilgængelig
ID: 220454452