Reconstructing While Registering: A Novel Approach for Markerless Augmented Reality
ISMAR '02 Proceedings of the 1st International Symposium on Mixed and Augmented Reality
Immersive Observation of Virtualized Soccer Match at Real Stadium Model
ISMAR '03 Proceedings of the 2nd IEEE/ACM International Symposium on Mixed and Augmented Reality
ARTag, a Fiducial Marker System Using Digital Techniques
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
AR baseball presentation system with integrating multiple planar markers
ICAT'06 Proceedings of the 16th international conference on Advances in Artificial Reality and Tele-Existence
Vision-Based registration for augmented reality with integration of arbitrary multiple planes
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Virtual Viewpoint Replay for a Soccer Match by View Interpolation From Multiple Cameras
IEEE Transactions on Multimedia
Arbitrary viewpoint video synthesis from multiple uncalibrated cameras
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
We present an AR display system for observing sports events on a desktop stadium based on fcamera tracking using pattern of the desktop ground by overlaying players in real sports events captured with multiple cameras. In this paper, we take soccer as the sports event. In the proposed system, the pose and the position of an observing camera are estimated in real-time by using a soccer field pattern on the desk top and an AR marker. The soccer field pattern in the desktop stadium on which the object soccer game is observed via AR display is previously registered with the real soccer stadium in which the real soccer game is captured with multiple cameras. In the previous procedure, we also estimate camera parameters (projection matrices) of the multiple cameras capturing the real soccer game using planar structures in the soccer field. Positions of soccer player and ball are also previously estimated based on the camera parameters. In the on-line procedure for AR display, the textures of the players captured in the multiple soccer video are simply overlaid onto AR camera videos with CG models which are generated for giving additional visual information.