Title
Image-based augmentation of virtual object for handy camera video sequence using arbitrary multiple planes
Abstract
We propose a novel vision-based registration method for Augmented Reality with merging of arbitrary multiple planes. In our approach, we require neither artificial markers nor sensors, and estimate the camera rotation and translation by an uncalibrated image sequence in which arbitrary multiple planes in the real world exist. Since the geometrical rela- tionship of those planes is unknown, for merging of them, we assign a 3D coordinate system for each plane indepen- dently and construct projective 3D space defined by projec- tive geometry of two reference images. By merging with the projective space, we can use arbitrary multi-planes, and achieve high-accurate registration for every position in the input images.
Year
DOI
Venue
2005
10.1109/ICIP.2005.1529926
Image Processing, 2005. ICIP 2005. IEEE International Conference
Keywords
Field
DocType
augmented reality,image registration,image sequences,video cameras,3D coordinate system,arbitrary multiple planes,augmented reality,camera rotation estimation,handy camera video sequence,image-based augmentation,projective geometry,reference images,translation estimation,uncalibrated image sequence,virtual object,vision-based registration method
Virtual image,Computer vision,Computer graphics (images),Computer science,Projective geometry,Image based,Augmented reality,Artificial intelligence,Merge (version control),Image registration,Cartesian coordinate system,Projective space
Conference
Volume
ISSN
ISBN
1
1522-4880
0-7803-9134-9
Citations 
PageRank 
References 
1
0.36
11
Authors
2
Name
Order
Citations
PageRank
Yuko Uematsu1537.72
Hideo Saito21147169.63