Abstract | ||
---|---|---|
In this paper, we propose an algorithm for estimating dense shape and motion of dynamic piecewise planar scenes from region correspondences using factorization. Region correspondences are used since they are easier to establish and more reliable than either line or point correspondences. The image measurements required are the centroid and area for each region. Singular value decomposition is employed to find the basis of range space of the motion, shape, and surface normal matrices. By imposing model constraints, motion, shape, and surface normal can be recovered only from region correspondences. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/CVPR.1998.698612 | Santa Barbara, CA |
Keywords | Field | DocType |
image recognition,motion estimation,singular value decomposition,factorization,model constraints,motion,piecewise planar scenes,region correspondence,region correspondences,shape,singular value decomposition,surface normal,surface normal matrices | Matrix (mathematics),Artificial intelligence,Motion estimation,Geometry,Piecewise,Computer vision,Singular value decomposition,Algorithm,Planar,Factorization,Mathematics,Normal,Centroid | Conference |
Volume | Issue | ISSN |
1998 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-8186-8497-6 | 2 | 0.40 |
References | Authors | |
10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ma, J. | 1 | 2 | 0.40 |
Narendra Ahuja | 2 | 7726 | 956.74 |