Title :
A fast and stable lane detection method based on B-spline curve
Author :
Xu, Huarong ; Wang, Xiaodong ; Huang, Hongwu ; Wu, Keshou ; Fang, Qiu
Author_Institution :
Dept. of Phys., Xiamen Univ., Xiamen, China
Abstract :
A new structure road detection algorithm based on open uniform B-spline curve model is proposed. Firstly, Canny edge detection algorithm is used to extract the road edge. Then road markings are gotten from the edge map by the least square method. Lastly, the road model (B-spline model) is fitted after the central points of the road are gotten from the lane markings. In order to accurate the position of the road bend, the algorithm introduces the maximum deviation of position shift (MDPS) method to search control points. A large number of experiments show that the algorithm is fast, stable, and flexible. It is able to meet the requirements of intelligent navigation.
Keywords :
edge detection; least squares approximations; object detection; splines (mathematics); traffic engineering computing; Canny edge detection algorithm; least square method; maximum deviation; position shift; stable lane detection method; structure road detection algorithm; uniform B-spline curve model; Computer science; Detection algorithms; Educational institutions; Image edge detection; Least squares methods; Navigation; Partitioning algorithms; Physics; Roads; Spline; Canny edge detection; Least square method; Open Uniform B-Spline; Road detection;
Conference_Titel :
Computer-Aided Industrial Design & Conceptual Design, 2009. CAID & CD 2009. IEEE 10th International Conference on
Conference_Location :
Wenzhou
Print_ISBN :
978-1-4244-5266-8
Electronic_ISBN :
978-1-4244-5268-2
DOI :
10.1109/CAIDCD.2009.5375392
