Real-Time 3D Object Recognition for Automatic Tracker Initialization

We propose a vision based real-time object recognition system, that provides object identification and 3D position data for the automatic initialization of a 3D tracking system. A-priori information is generated using the models of objects which may be present in the image. During recognition this data is accessed, using the position of corner features in the video image for indexing. A voting scheme is used to recognize objects and their positions in a single run. Upon recognition, a 3D object tracker can be automatically provided with initialization data