Vision-based lane detection for mobile robot navigation

Hao Fang*, Haifeng Wang, Ze Zhang, Liying Qiu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Lane detection is very important for autonomous navigation of mobile robots. In this paper a method which utilizes both color and texture features to extract lane regions from images is proposed. First based on color features, an improved region-growing algorithm is used to segment the images providing roughly approximated lane regions. However due to variances of scene illumination and shadows, some lane regions may be missed. In order to improve lane detection accuracy, texture features are computed and space adjacencies are also considered, which allow retrieving the lost lane regions. To meet the needs of practical applications, a video processing platform for lane detection is developed. It can detect lanes from dynamic video sequences accurately and show results in real-time. Experimental results show that the proposed algorithm can fulfill the requirements of real-time applications of robots and is robust to different environment conditions.

Original languageEnglish
Title of host publicationProceedings of the 7th World Congress on Intelligent Control and Automation, WCICA'08
Pages3854-3857
Number of pages4
DOIs
Publication statusPublished - 2008
Event7th World Congress on Intelligent Control and Automation, WCICA'08 - Chongqing, China
Duration: 25 Jun 200827 Jun 2008

Publication series

NameProceedings of the World Congress on Intelligent Control and Automation (WCICA)

Conference

Conference7th World Congress on Intelligent Control and Automation, WCICA'08
Country/TerritoryChina
CityChongqing
Period25/06/0827/06/08

Keywords

  • Color features
  • Lane detection
  • Region growth
  • Texture features

Fingerprint

Dive into the research topics of 'Vision-based lane detection for mobile robot navigation'. Together they form a unique fingerprint.

Cite this