A vision-based traffic surveillance system is presented which relies extensively on the use of geometrical and scene context. Firstly, a highly parametrized 3D model is reported, able to adopt the shape of a wide variety of different classes of vehicle (e.g., cars, vans, buses etc.), and its subsequent specialization to a generic car class which accounts for commonly encountered types of car (including saloon, hatchback and estate cars). Sample data collected from video images, by means of an interactive tool, have been subjected to PCA (Principal Component Analysis) to define a deformable model having 6 degrees of freedom. Secondly, a new pose refinement technique using active models is described, able to recover both the pose of a rigid object, and the structure of a deformable model; an assessment of its performance is examined in comparison with previously reported passive model-based techniques in the context of traffic surveillance. The new method is more stable, and requires fewer iterations, especially when the number of free parameters increases, but shows somewhat poorer convergence. Typical applications for this work include robot surveillance and navigation tasks.
Visual surveillance using deformable models of vehicles
Visuelle Verkehrsüberwachung mit Kraftfahrzeugerkennung unter Verwendung von veränderbaren dreidimensionalen Fahrzeugmodellen
Robotics and Autonomous Systems ; 19 , 3-4 ; 315-335
1997
21 Seiten, 12 Bilder, 3 Tabellen, 32 Quellen
Article (Journal)
English
Visual Object Recognition Using Deformable Models of Vehicles
British Library Conference Proceedings | 1995
|Visual surveillance of moving vehicles
Automotive engineering | 1993
|Visual Surveillance for Moving Vehicles
British Library Online Contents | 2000
|Visual surveillance of moving vehicles
Tema Archive | 1993
|