An Efficient Curvature Lane Recognition Algorithm by Piecewise Linear Approach

Lane recognition is an essential technique for automobile active safety applications. We aim at developing a high speed and high accurate lane recognition system. Especially, curvature lane recognition is not easy and no efficient system has been reported. This paper proposes a new efficient algorithm for lane recognition. The algorithm extracts lanes from a picture of 500 times 350 pixels in 0.8 sec by the PC software.

[1]  Werner von Seelen,et al.  Image processing and behavior planning for intelligent vehicles , 2003, IEEE Trans. Ind. Electron..

[2]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  R. Behringer,et al.  Results on visual road recognition for road vehicle guidance , 1996, Proceedings of Conference on Intelligent Vehicles.

[4]  Ping Kuang,et al.  Real-time road lane recognition using fuzzy reasoning for AGV vision system , 2004, 2004 International Conference on Communications, Circuits and Systems (IEEE Cat. No.04EX914).

[5]  Y. Ninomiya,et al.  Model-based lane recognition , 1996, Proceedings of Conference on Intelligent Vehicles.

[6]  Yoshiaki Shirai,et al.  Toward vision-based intelligent navigator: its concept and prototype , 2002, IEEE Trans. Intell. Transp. Syst..

[7]  Tony DeRose,et al.  Geometric continuity of parametric curves: constructions of geometrically continuous splines , 1990, IEEE Computer Graphics and Applications.