Title :
Feature point based highway curl road recognition
Author :
Guo, Lie ; Huang, Xiaohui ; Zhang, Guangxi ; Nie, Qian
Author_Institution :
Sch. of Automotive Eng., Dalian Univ. of Technol., Dalian, China
Abstract :
This paper introduces a recognition algorithm of highway curl road based on feature point. Firstly, a road model was established and traditional Hough transform was adopt to obtain linear equations of lanes in order to improve the real-time performance and robustness. The curve direction of current lanes was judged with certain criteria, and the feature points in the curvilinear section were extracted and corrected. Finally, the linear and curvilinear section was fitted to realize the ultimate two dimensional rebuilding of the current bent lanes. Experiments proved that both continuous and dashed lanes were recognized accurately with strong robustness.
Keywords :
Hough transforms; automated highways; feature extraction; object recognition; Hough transform; bent lanes; curve direction; curvilinear section; feature point based highway curl road recognition; linear equations; road model; two dimensional rebuilding; Educational institutions; Equations; Feature extraction; IEEE Press; Mathematical model; Roads; bent lanes; curve direction; feature point; highway; intelligent vehicle;
Conference_Titel :
Transportation, Mechanical, and Electrical Engineering (TMEE), 2011 International Conference on
Conference_Location :
Changchun
Print_ISBN :
978-1-4577-1700-0
DOI :
10.1109/TMEE.2011.6199301