Title :
High-speed lane detection for road geometry estimation and vehicle localization
Author :
Maeda, Tomoki ; Hu, Zhencheng ; Wang, Chenhao ; Uchimura, Keiichi
Author_Institution :
Grad. Sch. of Sci. & Technol., Kumamoto Univ., Kumamoto
Abstract :
This paper presents a fast and robust lane detection method designed to track 3D road shape and estimate accurate vehicle location in real-time. This method is based upon road curvature calculated from digital road network. This curvature gives cues for detection in some difficult situation like road lane markers are occupied by other vehicles, dirt and shadow. Moreover, to stabilize estimated road parameters, we applied AMF&PDF to handle the variation of road parameters in every frame and provide continuous vehicle location data. Experiment results show the effectiveness and robustness of our approach under different kinds of environment conditions.
Keywords :
Global Positioning System; automated highways; automobiles; computational geometry; computer vision; gyroscopes; object detection; shape recognition; tracking; traffic engineering computing; 3D gyro sensor; 3D road shape tracking; GPS; digital road network; high-speed lane detection; lane recognition; road curvature; road geometry estimation; speed sensor; vehicle localization; vision-based car navigation system; Geometry; Global Positioning System; Navigation; Parameter estimation; Real time systems; Road vehicles; Robustness; Shape; Vehicle detection; Working environment noise;
Conference_Titel :
SICE Annual Conference, 2008
Conference_Location :
Tokyo
Print_ISBN :
978-4-907764-30-2
Electronic_ISBN :
978-4-907764-29-6
DOI :
10.1109/SICE.2008.4654775
