3-D annotation of images captured from a wearer's camera based on object recognition

This paper describes a method for annotating the real scene image sequences with 3-D virtual objects based on image recognition. In order to annotate the real scene with 3-D virtual objects, we have to know not only where is user seeing from, but also what is user seeing. Therefore, we are trying to combine simple image recognition method with a vision based video see-through mixed reality system. In this presentation, it is proposed the method for starting estimation of camera position and orientation using image recognition result. Our demonstration system is a 3-D poster of this research that is a real paper poster annotated with 3-D virtual objects using proposed method.

[1]  P. Milgram,et al.  A Taxonomy of Mixed Reality Visual Displays , 1994 .

[2]  Robert M. Haralick,et al.  Analysis and solutions of the three point perspective pose estimation problem , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Jun Rekimoto,et al.  Matrix: a realtime object identification and registration method for augmented reality , 1998, Proceedings. 3rd Asia Pacific Computer Human Interaction (Cat. No.98EX110).

[4]  Mark A. Livingston,et al.  Superior augmented reality registration by integrating landmark tracking and magnetic tracking , 1996, SIGGRAPH.

[5]  Ronald Azuma,et al.  A Survey of Augmented Reality , 1997, Presence: Teleoperators & Virtual Environments.

[6]  Katsuhiko Sakaue,et al.  Real-Time Camera Parameter Estimation from Images for a Wearable Vision System , 2000, MVA.

[7]  Ivan Poupyrev,et al.  Virtual object manipulation on a table-top AR environment , 2000, Proceedings IEEE and ACM International Symposium on Augmented Reality (ISAR 2000).

[8]  田村 秀行,et al.  Mixed reality : merging real and virtual worlds , 1999 .

[9]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.