Superior augmented reality registration by integrating landmark tracking and magnetic tracking
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Visual Marker Detection and Decoding in AR Systems: A Comparative Study
ISMAR '02 Proceedings of the 1st International Symposium on Mixed and Augmented Reality
Marker Tracking and HMD Calibration for a Video-Based Augmented Reality Conferencing System
IWAR '99 Proceedings of the 2nd IEEE and ACM International Workshop on Augmented Reality
Combining Edge and Texture Information for Real-Time Accurate 3D Camera Tracking
ISMAR '04 Proceedings of the 3rd IEEE/ACM International Symposium on Mixed and Augmented Reality
Scene Modelling, Recognition and Tracking with Invariant Image Features
ISMAR '04 Proceedings of the 3rd IEEE/ACM International Symposium on Mixed and Augmented Reality
Adaptive Line Tracking with Multiple Hypotheses for Augmented Reality
ISMAR '05 Proceedings of the 4th IEEE/ACM International Symposium on Mixed and Augmented Reality
An all-in-one solution to geometric and photometric calibration
ISMAR '06 Proceedings of the 5th IEEE and ACM International Symposium on Mixed and Augmented Reality
Hi-index | 0.00 |
In many applications of Augmented Reality (AR), rectangular markers are tracked in real time by capturing with cameras. In this paper, we consider the AR application in which virtual objects are displayed onto markers while the markers and the cameras are freely moving. In this situation, the marker cannot be tracked when the marker is occluded by some objects. In this paper, we propose a method for tracking the projection matrix between the image and the marker even when the maker is occluded, by using cameras. In this method, we transfer the projection matrix for the marker that is detected by the cameras in order to estimate the relative projection matrix for the occluded marker. After computing the relative projection matrices using multiple cameras, we compute a more accurate projection matrix by using particle filter. As a result, we can continuously track the markers even when the marker is occluded.