Real-time 3D object recognition for automatic tracker initialization

Author

Blaskó, Gábor ; Fua, Pascal

Author_Institution

Comput. Graphics Lab, Swiss Fed. Inst. of Technol., Lausanne, Switzerland

fYear

2001

fDate

2001

Firstpage

175

Lastpage

176

Abstract

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

Keywords

augmented reality; object recognition; real-time systems; tracking; 3D position data; a-priori information; augmented reality systems; automatic tracker initialization; corner features; indexing; object identification; real-time 3D object recognition; video image; vision based real-time object recognition system; voting scheme; Augmented reality; Computer graphics; Histograms; Image databases; Image processing; Image recognition; Indexing; Object recognition; Spatial databases; Voting;

fLanguage

English

Publisher

ieee

Conference_Titel

Augmented Reality, 2001. Proceedings. IEEE and ACM International Symposium on

Conference_Location

New York, NY

Print_ISBN

0-7695-1375-1

Type

conf

DOI

10.1109/ISAR.2001.970529

Filename

970529