Lane detection based on guided RANSAC

Yi Hu, You Sun Kim, Kwang Wook Lee, Sung-Jea Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a robust and real-time lane detection method is proposed. The method consists of two steps, the lane-marking detection and lane model fitting. After detecting the lane marking by the Intensity bump algorithm, we apply the post filters by constraining the parallelism of lane boundary. Then, a novel model fitting algorithm called Guided RANSAC is presented. The Guided RANSAC searches lanes from initial lane segments and the extrapolation of lane segments is used as the guiding information to elongate lane segments recursively. With the proposed method, the accuracy of the model fitting is greatly increased while the computational cost is reduced. Both theoretical and experimental analysis results are given to show the efficiency.

Original languageEnglish
Title of host publicationVISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages457-460
Number of pages4
Volume1
Publication statusPublished - 2010 Sep 10
Event5th International Conference on Computer Vision Theory and Applications, VISAPP 2010 - Angers, France
Duration: 2010 May 172010 May 21

Other

Other5th International Conference on Computer Vision Theory and Applications, VISAPP 2010
CountryFrance
CityAngers
Period10/5/1710/5/21

Fingerprint

Extrapolation
Costs

Keywords

  • Computer vision
  • Driving assistance
  • Lane detection
  • RANSAC

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Hu, Y., Kim, Y. S., Lee, K. W., & Ko, S-J. (2010). Lane detection based on guided RANSAC. In VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 1, pp. 457-460)

Lane detection based on guided RANSAC. / Hu, Yi; Kim, You Sun; Lee, Kwang Wook; Ko, Sung-Jea.

VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2010. p. 457-460.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hu, Y, Kim, YS, Lee, KW & Ko, S-J 2010, Lane detection based on guided RANSAC. in VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 1, pp. 457-460, 5th International Conference on Computer Vision Theory and Applications, VISAPP 2010, Angers, France, 10/5/17.
Hu Y, Kim YS, Lee KW, Ko S-J. Lane detection based on guided RANSAC. In VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1. 2010. p. 457-460
Hu, Yi ; Kim, You Sun ; Lee, Kwang Wook ; Ko, Sung-Jea. / Lane detection based on guided RANSAC. VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2010. pp. 457-460
@inproceedings{9bebdea7cc6743429a4754cb1d9f31a5,
title = "Lane detection based on guided RANSAC",
abstract = "In this paper, a robust and real-time lane detection method is proposed. The method consists of two steps, the lane-marking detection and lane model fitting. After detecting the lane marking by the Intensity bump algorithm, we apply the post filters by constraining the parallelism of lane boundary. Then, a novel model fitting algorithm called Guided RANSAC is presented. The Guided RANSAC searches lanes from initial lane segments and the extrapolation of lane segments is used as the guiding information to elongate lane segments recursively. With the proposed method, the accuracy of the model fitting is greatly increased while the computational cost is reduced. Both theoretical and experimental analysis results are given to show the efficiency.",
keywords = "Computer vision, Driving assistance, Lane detection, RANSAC",
author = "Yi Hu and Kim, {You Sun} and Lee, {Kwang Wook} and Sung-Jea Ko",
year = "2010",
month = "9",
day = "10",
language = "English",
isbn = "9789896740283",
volume = "1",
pages = "457--460",
booktitle = "VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Lane detection based on guided RANSAC

AU - Hu, Yi

AU - Kim, You Sun

AU - Lee, Kwang Wook

AU - Ko, Sung-Jea

PY - 2010/9/10

Y1 - 2010/9/10

N2 - In this paper, a robust and real-time lane detection method is proposed. The method consists of two steps, the lane-marking detection and lane model fitting. After detecting the lane marking by the Intensity bump algorithm, we apply the post filters by constraining the parallelism of lane boundary. Then, a novel model fitting algorithm called Guided RANSAC is presented. The Guided RANSAC searches lanes from initial lane segments and the extrapolation of lane segments is used as the guiding information to elongate lane segments recursively. With the proposed method, the accuracy of the model fitting is greatly increased while the computational cost is reduced. Both theoretical and experimental analysis results are given to show the efficiency.

AB - In this paper, a robust and real-time lane detection method is proposed. The method consists of two steps, the lane-marking detection and lane model fitting. After detecting the lane marking by the Intensity bump algorithm, we apply the post filters by constraining the parallelism of lane boundary. Then, a novel model fitting algorithm called Guided RANSAC is presented. The Guided RANSAC searches lanes from initial lane segments and the extrapolation of lane segments is used as the guiding information to elongate lane segments recursively. With the proposed method, the accuracy of the model fitting is greatly increased while the computational cost is reduced. Both theoretical and experimental analysis results are given to show the efficiency.

KW - Computer vision

KW - Driving assistance

KW - Lane detection

KW - RANSAC

UR - http://www.scopus.com/inward/record.url?scp=77956329027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956329027&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77956329027

SN - 9789896740283

VL - 1

SP - 457

EP - 460

BT - VISAPP 2010 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -