Lane marker parameters for vehicle's steering signal prediction

Authors:
Andriejus Demčenko;Minija Tamošiunaite;Aušra Vidugiriene;Leonas Jakevičius
Affiliations:
Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania;Department of System Analysis, Vytautas Magnus University, Kaunas, Lithuania;Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania;Department of Physics, Kaunas University of Technology, Kaunas, Lithuania
Venue:
WSEAS TRANSACTIONS on SYSTEMS
Year:
2009

Citing 4
Cited 0

Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
Applied Geometry for Computer Graphics

Applied Geometry for Computer Graphics
Video-Based Driver Assistance—From Basic Functions to Applications

International Journal of Computer Vision
Time to line crossing for lane departure avoidance: a theoretical study and an experimental setting

IEEE Transactions on Intelligent Transportation Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The work considers road lane parameters that correlate with steering angle of a car and which are suitable for accurate prediction of steering signal using neural network technique. Four different parameters, which can be used in driver's assistance system and are based on position, angles and curvature of the lane marker, are proposed and their correspondence to steering signal is analyzed. The steering signal is predicted with the precision of 95% to 97%, depending on a combination of the visually-based parameters provided for the neural network. The work is performed using signals from real road driving.