Title :
Robot vision-based registration utilizing bird´s-eye view with user´s view
Author :
Satoh, Kiyohide ; Uchiyama, Shinji ; Yamamoto, Hiroyuki ; Tamura, Hideyuki
Author_Institution :
MRS Syst. Lab., Canon Inc., Tokyo, Japan
Abstract :
This paper describes new vision-based registration methods utilizing not only cameras on a user´s head-mounted display but also a bird´s-eye view camera that observes the user from an objective viewpoint. Two new methods, the line constraint method (LCM) and global error minimization method (GEM), are proposed. The former method reduces the number of unknown parameters concerning the user´s viewpoint by restricting it to be on the line of sight from the bird´s-eye view. The other method minimizes the sum of errors, which is the sum of the distance between the fiducials on the view and the calculated positions of them based on the current viewing parameters, for both the user´s view and the bird´s-eye view. The methods proposed here reduce the number of points that should be observed from the user´s viewpoint for registration, thus improving the stability. In addition to theoretical discussions, this paper demonstrates the effectiveness of our methods by experiments in comparison with methods that use only a user´s view camera or a bird´s-eye view camera.
Keywords :
augmented reality; cameras; image registration; robot vision; bird eye view camera; cameras; fiducials; global error minimization method; head-mounted display; line constraint method; robot vision; unknown parameters; user view camera; user viewpoint; viewing parameters; vision-based registration; Augmented reality; Cameras; Displays; Laboratories; Magnetic sensors; Minimization methods; Position measurement; Robust stability; Robustness; Space technology;
Conference_Titel :
Mixed and Augmented Reality, 2003. Proceedings. The Second IEEE and ACM International Symposium on
Print_ISBN :
0-7695-2006-5
DOI :
10.1109/ISMAR.2003.1240687