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

Morten Bornø Jensen, Mark Philip Philipsen, Chris Bahnsen, Andreas Møgelmose, Thomas B. Moeslund, Mohan M. Trivedi

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

13 Citations (Scopus)
1015 Downloads (Pure)

Abstract

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 %.
Original languageEnglish
Title of host publicationAdvances in Visual Computing : 11th International Symposium, ISVC 2015, Las Vegas, NV, USA, December 14-16, 2015, Proceedings, Part I
PublisherSpringer
Publication dateOct 2015
Pages774-783
ISBN (Print)978-3-319-27856-8
ISBN (Electronic)978-3-319-27857-5
DOIs
Publication statusPublished - Oct 2015
EventISVC 2015: 11th International Symposium on Visual Computing - Las Vegas, United States
Duration: 14 Dec 201516 Dec 2015

Conference

ConferenceISVC 2015
Country/TerritoryUnited States
CityLas Vegas
Period14/12/201516/12/2015
SeriesLecture Notes in Computer Science
Volume9474
ISSN0302-9743

Fingerprint

Dive into the research topics of 'Traffic Light Detection at Night: Comparison of a Learning-based Detector and three Model-based Detectors'. Together they form a unique fingerprint.

Cite this