Name
Title | ||
|---|---|---|
Fitting Undeformed Superquadrics to Range Data: Improving Model Recovery and Classification |
Abstract | ||
|---|---|---|
Undeformed superquadrics are volumetric modeling primitives with an extensive shape vocabulary that are described by only 5 parameters. Fitting these models viewpoint invariantly to range data enables classification based on the superquadric parameters. However, current recovery routines show several limitations, especially when the algorithms are applied to range images instead of true 3D images. In this paper problems with the common superquadric recovery procedure are identified and solutions are presented. |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1109/CVPR.1998.698636 | CVPR |
Keywords | Field | DocType |
current recovery routine,undeformed superquadrics,extensive shape vocabulary,range data,improving model recovery,volumetric modeling primitive,common superquadric recovery procedure,models viewpoint invariantly,superquadric parameter,paper problem,gaussian noise,image segmentation,shape,3d imaging,object recognition,classification,maximum likelihood estimation,robustness,image classification | Computer vision,Pattern recognition,Computer science,Surface fitting,Superquadrics,Image representation,Artificial intelligence,Contextual image classification,Vocabulary,Recovery procedure | Conference |
Volume | Issue | ISSN |
1998 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-8186-8497-6 | 7 | 0.58 |
References | Authors | |
7 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| E. R. Van Dop | 1 | 7 | 0.58 |
| P P. L. Regtien | 2 | 35 | 6.10 |