Name
Abstract | ||
|---|---|---|
In this paper we propose a framework of factorization-based non-rigid shape modeling and tracking in stereo-motion. We construct a measurement matrix with the stereo-motion data captured from a stereo-rig. Organized in a particular way this matrix could be decomposed by singular value decomposition (SVD) into the 3D basis shapes, their configuration weights, rigid motion and camera geometry. Accordingly, the stereo correspondences can be inferred from motion correspondences only requiring that a minimum of 3K point stereo correspondences (where K is the dimension of shape basis space) are created in advance. Basically this framework still keeps the property of rank constraints, meanwhile it owns other advantages such as simpler correspondence and accurate reconstruction even with short image sequences. Results with real data are given to demonstrate its performance. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/ICASSP.2008.4517797 | ICASSP |
Keywords | Field | DocType |
stereo vision,motion correspondences,measurement matrix,visual tracking,nonrigid objects,factorization-based nonrigid shape modeling,rigid motion,camera geometry,3d basis shapes,image reconstruction,stereo correspondences,factorization method,image sequences,index terms— visual tracking,stereo-rig,stereo image processing,singular value decomposition,stereo-motion data,rank constraints,configuration weights,image motion analysis,indexing terms,data capture | Iterative reconstruction,Factorization method,Computer vision,Singular value decomposition,Rigid motion,Computer science,Stereopsis,Matrix (mathematics),Eye tracking,Factorization,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4244-1484-0 | 978-1-4244-1484-0 | 1 |
PageRank | References | Authors |
0.34 | 17 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yu Huang | 1 | 1 | 0.34 |
| Jilin Tu | 2 | 342 | 21.34 |
| Thomas S. Huang | 3 | 27815 | 2618.42 |