Abstract | ||
---|---|---|
In this paper the problem of computing the point correspon- dences in a sequence of time-varying images of a 3D object undergoing nonrigid (affine) motion is addressed. It is assumed that the images are obtained through affine projections. The correspondences are established only from the analysis of the unknown 3D affine structure of the object, without making use of any attributes of the feature points. It is shown that it is possible to establish the point correspondences uniquely (up to symmetry) in the sense that they yield a unique affine structure of the object and that the computation is possible in polynomial time. Two different algorithms for computing the point corre- spondences are presented. Results on various real image se- quences, including a sequence containing independently mov- ing objects, demonstrate the applicability of the structure based approach to motion correspondence. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1006/cviu.1997.0545 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
point correspondence,affine structure | Affine transformation,Computer vision,Affine shape adaptation,Discrete mathematics,Harris affine region detector,Algebra,Affine combination,Computer science,Affine coordinate system,Artificial intelligence,Affine hull | Journal |
Volume | Issue | ISSN |
68 | 2 | Computer Vision and Image Understanding |
Citations | PageRank | References |
8 | 5.13 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
G. Sudhir | 1 | 8 | 5.13 |
Andrew Zisserman | 2 | 45998 | 3200.71 |
Subhashis Banerjee | 3 | 297 | 37.65 |