HSI color model based lane-marking detection

Author

Sun, Tsung-Ying ; Tsai, Shang-Jeng ; Chan, Vincent

Author_Institution

Nat. Dong Hwa Univ., Hualien

fYear

2006

fDate

17-20 Sept. 2006

Firstpage

1168

Lastpage

1172

Abstract

Lane-marking detection is one of the major concerned topics in the field of driving safety and intelligent vehicle. In this paper, a new method using HSI color model for lane-marking detection, HSILMD, is proposed. In HSILMD, full color images are converted into HSI color representation, within the region of interest (ROI) aiming to detect road surface on host vehicle, the difference of intensity distribution of a row of pixels within ROI is recorded and clustered with fuzzy c-means algorithm. Thresholds of intensity and saturation are selected accordingly. With simple thresholds and operations, lane markings on various road scene images are detected. Results are compared with the same scheme using RGB color model and a different scheme. Robustness of this reduced computation consumption system is observed

Keywords

fuzzy set theory; image colour analysis; object detection; pattern clustering; road traffic; traffic engineering computing; full color image conversion; fuzzy c-means algorithm; hue-saturation-intensity color model based lane-marking detection; intensity threshold selection; pixel clustering; road surface detection; saturation threshold selection; Clustering algorithms; Color; Image converters; Intelligent vehicles; Layout; Pixel; Road vehicles; Robustness; Vehicle detection; Vehicle safety;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE

Conference_Location

Toronto, Ont.

Print_ISBN

1-4244-0093-7

Electronic_ISBN

1-4244-0094-5

Type

conf

DOI

10.1109/ITSC.2006.1707380

Filename

1707380