P000120
A Robust Lane Detection Associated with Quaternion Hardy Filter
*Bi Wenshan (Department of Mathematics, Faculty of Science and Technology, University of Macau, Macau, China)
Cheng Dong (Research Center for Mathematics and Mathematics Education, Beijing Normal University at Zhuhai, 519087, China)
Kit Ian Kou (Department of Mathematics, Faculty of Science and Technology, University of Macau, Macau, China)
In this study, a color-edge feature extraction along with the Quaternion Hardy filter is proposed for the lane marking detection. The Quaternion Hardy filter is along with the Poisson and Conjugate Poisson smoothing kernels. It can handle various type of noises. Combining with the Quaternion Hardy filter, Jin s gradient operator and Hough transform, a color-edge feature lane detection algorithm is proposed. Experiments are presented to demonstrate the validity of the proposed method. The results were accurate and robust with respect to the shadows and damage lane markings.