| ID | 30071 |
| FullText URL | |
| Author | |
| Abstract | We give a formal definition of geometric fitting in a way that suits computer vision applications. We point out that the performance of geometric fitting should be evaluated in the limit of small noise rather than in the limit of a large number of data as recommended in the statistical literature. Taking the KCR lower bound as an optimality requirement and focusing on the linearized constraint case, we compare the accuracy of Kanatani's renormalization with maximum likelihood (ML) approaches including the FNS of Chojnacki et al. and the HEIV of Leedan and Meer. Our analysis reveals the existence of a method superior to all these. |
| Keywords | computer vision
maximum likelihood estimation
surface fitting
|
| Note | Digital Object Identifier: 10.1109/3DIM.2005.49
Published with permission from the copyright holder. This is the institute's copy, as published in 3-D Digital Imaging and Modeling, 2005. 3DIM 2005. Fifth International Conference on, 13-16 June 2005, Pages 2-13. Publisher URL:http://dx.doi.org/10.1109/3DIM.2005.49 Copyright © 2005 IEEE. All rights reserved. |
| Published Date | 2005-6
|
| Publication Title |
Proceedings of the Fifth International Conference on 3-D Digital Imaging and Modeling
|
| Publisher | IEEE Computer Society
|
| Start Page | 2
|
| End Page | 13
|
| ISSN | 1550-6185
|
| NCID | BA75362958
|
| Content Type |
Conference Paper
|
| language |
English
|
| Copyright Holders | IEEE
|
| Event Title | Fifth International Conference on 3-D Digital Imaging and Modeling
|
| Event Location | Ottawa, Ontario, Canada
|
| Event Dates | 2005-6
|
| File Version | publisher
|
| Refereed |
True
|
| DOI | |
| Submission Path | industrial_engineering/112
|
