Real-time illumination invariant lane detection for lane departure warning system

Jongin Son, Hunjae Yoo, Sanghoon Kim, Kwanghoon Sohn

Research output: Contribution to journalArticle

88 Citations (Scopus)

Abstract

Lane detection is an important element in improving driving safety. In this paper, we propose a real-time and illumination invariant lane detection method for lane departure warning system. The proposed method works well in various illumination conditions such as in bad weather conditions and at night time. It includes three major components: First, we detect a vanishing point based on a voting map and define an adaptive region of interest (ROI) to reduce computational complexity. Second, we utilize the distinct property of lane colors to achieve illumination invariant lane marker candidate detection. Finally, we find the main lane using a clustering method from the lane marker candidates. In case of lane departure situation, our system sends driver alarm signal. Experimental results show satisfactory performance with an average detection rate of 93% under various illumination conditions. Moreover, the overall process takes only 33 ms per frame.

Original languageEnglish
Pages (from-to)1816-1824
Number of pages9
JournalExpert Systems with Applications
Volume42
Issue number4
DOIs
Publication statusPublished - 2015 Mar

Fingerprint

Alarm systems
Lighting
Computational complexity
Color

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Son, Jongin ; Yoo, Hunjae ; Kim, Sanghoon ; Sohn, Kwanghoon. / Real-time illumination invariant lane detection for lane departure warning system. In: Expert Systems with Applications. 2015 ; Vol. 42, No. 4. pp. 1816-1824.
@article{235bccd6f51e4bc3bbf9db9587d2bd0e,
title = "Real-time illumination invariant lane detection for lane departure warning system",
abstract = "Lane detection is an important element in improving driving safety. In this paper, we propose a real-time and illumination invariant lane detection method for lane departure warning system. The proposed method works well in various illumination conditions such as in bad weather conditions and at night time. It includes three major components: First, we detect a vanishing point based on a voting map and define an adaptive region of interest (ROI) to reduce computational complexity. Second, we utilize the distinct property of lane colors to achieve illumination invariant lane marker candidate detection. Finally, we find the main lane using a clustering method from the lane marker candidates. In case of lane departure situation, our system sends driver alarm signal. Experimental results show satisfactory performance with an average detection rate of 93{\%} under various illumination conditions. Moreover, the overall process takes only 33 ms per frame.",
author = "Jongin Son and Hunjae Yoo and Sanghoon Kim and Kwanghoon Sohn",
year = "2015",
month = "3",
doi = "10.1016/j.eswa.2014.10.024",
language = "English",
volume = "42",
pages = "1816--1824",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

Real-time illumination invariant lane detection for lane departure warning system. / Son, Jongin; Yoo, Hunjae; Kim, Sanghoon; Sohn, Kwanghoon.

In: Expert Systems with Applications, Vol. 42, No. 4, 03.2015, p. 1816-1824.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time illumination invariant lane detection for lane departure warning system

AU - Son, Jongin

AU - Yoo, Hunjae

AU - Kim, Sanghoon

AU - Sohn, Kwanghoon

PY - 2015/3

Y1 - 2015/3

N2 - Lane detection is an important element in improving driving safety. In this paper, we propose a real-time and illumination invariant lane detection method for lane departure warning system. The proposed method works well in various illumination conditions such as in bad weather conditions and at night time. It includes three major components: First, we detect a vanishing point based on a voting map and define an adaptive region of interest (ROI) to reduce computational complexity. Second, we utilize the distinct property of lane colors to achieve illumination invariant lane marker candidate detection. Finally, we find the main lane using a clustering method from the lane marker candidates. In case of lane departure situation, our system sends driver alarm signal. Experimental results show satisfactory performance with an average detection rate of 93% under various illumination conditions. Moreover, the overall process takes only 33 ms per frame.

AB - Lane detection is an important element in improving driving safety. In this paper, we propose a real-time and illumination invariant lane detection method for lane departure warning system. The proposed method works well in various illumination conditions such as in bad weather conditions and at night time. It includes three major components: First, we detect a vanishing point based on a voting map and define an adaptive region of interest (ROI) to reduce computational complexity. Second, we utilize the distinct property of lane colors to achieve illumination invariant lane marker candidate detection. Finally, we find the main lane using a clustering method from the lane marker candidates. In case of lane departure situation, our system sends driver alarm signal. Experimental results show satisfactory performance with an average detection rate of 93% under various illumination conditions. Moreover, the overall process takes only 33 ms per frame.

UR - http://www.scopus.com/inward/record.url?scp=84910594170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910594170&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2014.10.024

DO - 10.1016/j.eswa.2014.10.024

M3 - Article

AN - SCOPUS:84910594170

VL - 42

SP - 1816

EP - 1824

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -