CyberCode: designing augmented reality environments with visual tags
DARE '00 Proceedings of DARE 2000 on Designing augmented reality environments
Geometric Hashing: An Overview
IEEE Computational Science & Engineering
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
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
Improved Topological Fiducial Tracking in the reacTIVision System
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Hi-index | 0.00 |
We developed a novel marker tracking method with shape-free designable markers, which can be visually meaningful to users. The method can work fast enough to provide a real-time camerabased interaction even on low performance CPUs such as one used in mobile Internet devices. Features such as visually communicative design and inexpensive computational cost are very desirable for users with mobile devices in the mobile/pervasive interaction environment. The method utilizes the topological region adjacency to detect the marker candidates and then apply a simple method similar to geometric-hashing to determine the detected maker by voting to the hash tables. By such a combination of two different approaches, our method can distinguish those markers with the same topological structure and is also capable of 6-DoF post estimation whereas most of the existing topology-based systems can not distinguish markers with the same topological.