Object Tracking and Pose Estimation Using Light‐feld Object Models
Matthias Zobel, Mario Fritz, Ingo Scholz · Max Planck Digital Library · 2002
Geometric object models have been widely used for visual object tracking. In this contribution we present particle lter based object tracking with pose estimation using an appearance based lighteld object model. A light-eld is an image-based object representation which can be used to render a photo realistic view of an arbitrarily shaped object from arbitrary viewpoints. It is shown how lighteld object models can be generated and utilized. Furthermore, we show how these models t into the probabilistic framework of dynamic state estimation by dening an appropriate likelihood distribution from an image similarity metric. Finally, we present results and accuracy evaluations from tracking experiments of different objects.