Extended path prediction using camera and map data for lane keeping support
Aris Polychronopoulos, Angelos Amditis, Manolis Tsogas, Aria Etemad
ICCS, Greece/Ford Research Center Aachen, Germany
IEEE Intelligent Transportation System, Vienna, Austria
13 - 16 September 2005
Lane departure or lane keeping systems should detect in advance when road/lane departure is going to happen.
The goal of the paper is twofold: on the one hand, to achieve accurate detection of such incidents, decreasing system misses; on the other hand, to extend the electronic horizon of the supervised area to 500 meters, minimizing false alarms caused by intentional lane changes. To achieve these goals, the paper proposes an extended lane tracking scheme, based on an information fusion system and a path prediction algorithm that incorporates curvilinear vehicle models for the short term prediction and on-line learning for a wider time perspective.
For more information, please contact SAFELANE SP Leader at