A Method for Lane Detection Based on Color Clustering

Author

Ma, Chao ; Xie, Mei

Author_Institution

Sch. of Electron. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

fYear

2010

fDate

9-10 Jan. 2010

Firstpage

200

Lastpage

203

Abstract

Concerning the problem of lane detection in the Lane Departure Warning (LDW) system, this paper presents one method to detect the region of lane marking based on the CIELab color features clustering. Color space can provide us more precious information than gray scale. This algorithm proves that it is feasible to recognize lane marking by using color clustering. According to the geometry feature of road, quadratic curve is adopted to match the lane. And also, least square method is proposed to depict the parameters of quadratic curve.

Keywords

curve fitting; feature extraction; image colour analysis; least squares approximations; road traffic; traffic engineering computing; CIELab color features clustering; Lane Departure Warning system; color clustering; lane detection; least square method; quadratic curve; road geometry feature; Clustering algorithms; Curve fitting; Data mining; Intelligent vehicles; Least squares methods; Machine vision; Roads; Space technology; Vehicle driving; Vehicle safety; color clustering; curve fitting; lane detection; least square;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Discovery and Data Mining, 2010. WKDD '10. Third International Conference on

Conference_Location

Phuket

Print_ISBN

978-1-4244-5397-9

Electronic_ISBN

978-1-4244-5398-6

Type

conf

DOI

10.1109/WKDD.2010.118

Filename

5432669