The authors present a robust road detection and tracking method using multiple vanishing points and the condensation filter. The authors represent the road using an extended hyperbola model with an added non-linear term to handle transitions between straight and curved road segments. The parameters of the road model are estimated using multiple vanishing points located in road segments. A vanishing line is then determined using a robust iterative curve fitting technique to recover parameters of the road model. These are then fed into a robust condensation trackerto track the road. The tracker is able to deal with difficult road conditions. Experiments using real road videos demonstrate the suitability of the approach for real-time applications. A comparison with the Kalman filtering technique demonstrates the robustness of this approach.
An extended hyperbola model for road tracking for video-based personal navigation
Ein erweitertes Hyperbel-Modell zur Straßenverlaufsverfolgung für die videobasierte persönliche Navigation
2008
14 Seiten, 8 Bilder, 1 Tabelle, 35 Quellen
Aufsatz (Konferenz)
Englisch
A Hyperbola-Pair Based Road Detection System for Autonomous Vehicles
Springer Verlag | 2011
|A Hyperbola-Pair Based Road Detection System for Autonomous Vehicles
British Library Conference Proceedings | 2011
|Weighted-Hyperbola Technique for Locating Pulsed Sources
Online Contents | 1998
A Real-time Lane Detection Algorithm Based on a Hyperbola-Pair Model
British Library Conference Proceedings | 2006
|