Vehicle Detection at Night Based on Tail-Light Detection

Ronan O'Malley; Martin Glavin; Edward Jones

1st International ICST Symposium on Vehicular Computing Systems

Research Article

Vehicle Detection at Night Based on Tail-Light Detection

Download468 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/ICST.ISVCS2008.3546,
    author={Ronan O'Malley and Martin Glavin and Edward Jones},
    title={Vehicle Detection at Night Based on Tail-Light Detection},
    proceedings={1st International ICST Symposium on Vehicular Computing Systems},
    proceedings_a={ISVCS},
    year={2010},
    month={5},
    keywords={vehicle detection forward collision advanced driver assist automotive image processing rear light detection},
    doi={10.4108/ICST.ISVCS2008.3546}
}

Ronan O'Malley
Martin Glavin
Edward Jones
Year: 2010
Vehicle Detection at Night Based on Tail-Light Detection
ISVCS
ICST
DOI: 10.4108/ICST.ISVCS2008.3546

Ronan O'Malley¹^,*, Martin Glavin¹^,*, Edward Jones¹^,*

1: Connaught Automotive Research Group Department of Electronic Engineering National University of Ireland, Galway +353-91-492605

*Contact email: ronan.omalley@nuigalway.ie, martin.glavin@nuigalway.ie, edward.jones@nuigalway.ie

Abstract

Automated detection of vehicles in front can be used as a component of systems for forward collision avoidance and mitigation. When driving in dark conditions, vehicles in front are generally visible by their tail and brake lights. We present an algorithm that detects vehicles at night using a camera by searching for tail lights. Knowledge of colour, size, symmetry and position of rear facing vehicle lights, taken from relevant legislation, is exploited. We develop an image processing system that can reliably detect vehicles at diﬀerent distances and in diﬀerent weather and lighting conditions.

Keywords: vehicle detection forward collision advanced driver assist automotive image processing rear light detection

Published: 2010-05-16
Modified: 2010-05-16

: http://dx.doi.org/10.4108/ICST.ISVCS2008.3546