Presentation 1997/12/18
Theoretical Accuracy Bounds and Optimal Algorithm in Geometric Estimation
Kenichi Kanatani,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper gives a general mathematical framework to the computer vision task of inferring 3-D structures of scenes and objects based on image data and geometric constraints, viewing the problem as model fitting. It can be shown that by modeling the statistical behavior of noise, we can derive a theoretical accuracy bound and a computational scheme that attains that bound. Such a method is truly optimal in the sense that accuracy cannot be improved by any other methods. We illustrate our theory by taking the structure-from-motion problem as an example. Various related topics are also discussed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) optimization / geometric estimation / structure from motion / statistical estimation / theoretical accuracy bound / model fitting
Paper # PRMU97-179
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/12/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Theoretical Accuracy Bounds and Optimal Algorithm in Geometric Estimation
Sub Title (in English)
Keyword(1) optimization
Keyword(2) geometric estimation
Keyword(3) structure from motion
Keyword(4) statistical estimation
Keyword(5) theoretical accuracy bound
Keyword(6) model fitting
1st Author's Name Kenichi Kanatani
1st Author's Affiliation Department of Computer Science, Gunma University()
Date 1997/12/18
Paper # PRMU97-179
Volume (vol) vol.97
Number (no) 458
Page pp.pp.-
#Pages 8
Date of Issue