This paper presents a robust method for vehicle tracking with a monocular camera. A previously published model-based tracking method uses a particle filter which needs an initial vehicle hypothesis both at system start and in case of a tracking loss. We present a template-based solution using different features to estimate a 3D vehicle pose roughly but fast. Combining model- and template-based object tracking keeps the advantages of each algorithm: Precise estimation of the 3D vehicle pose and velocity combined with a fast (re-) initialization approach. The improved tracking system was evaluated while driving autonomously in urban and unstructured environments. The results show that poorly visible vehicles can be tracked during different weather conditions in real-time.
Combining model- and template-based vehicle tracking for autonomous convoy driving
2013 IEEE Intelligent Vehicles Symposium (IV) ; 1022-1027
01.06.2013
1887754 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
COMBINING MODEL AND TEMPLATE-BASED VEHICLE TRACKING FOR AUTONOMOUS CONVOY DRIVING
British Library Conference Proceedings | 2013
|Evaluation of semi-autonomous convoy driving
British Library Online Contents | 2008
|Control structure for vehicle convoy driving
Kraftfahrwesen | 1996
|