Understanding lane is an essential step to provide more realistic information for video-based navigation systems. In this paper, the authors present a novel idea to understand lane from a live video captured in a moving vehicle. More specifically, 1) lane markings are extracted first. Then, 2) color information of lane markings are fed into support vector machines to decide if it is yellow lane or not. By combining information from database, it is possible to decide if we are in the leftmost, middle, or the rightmost lane, which allows us to provide more realistic navigation information to drivers. Exhaustive simulation results are provided to show the robustness of the proposed idea.
Lane detection using support vector machines
2007
5 Seiten, 7 Bilder, 3 Tabellen, 13 Quellen
Conference paper
English
Incident detection using support vector machines
Online Contents | 2003
|NTRS | 2004
|Aerodynamic Data Modeling Using Support Vector Machines
AIAA | 2004
|