Implementing a Variant of the Kanatani's Estimation Method - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2000

Implementing a Variant of the Kanatani's Estimation Method

Thierry Viéville
  • Function : Author
  • PersonId : 830072
Diane Lingrand

Abstract

We revisit the problem of parameter estimation in computer vision, reconsideri- ng and implementing what may be called the Kanatani's estimation reconsidering and implementing what may be called the Kanatani's estimation method, presented here as a simple optimisation problem, so (a) without any method, presented here as a simple optimisation problem, so (a) without any direct reference to a probabilistic framework but (b) considering (i) direct reference to a probabilistic framework but (b) considering (i) non-linear implicit measurement equations and parameter constraints, plus non-linear implicit measurement equations and parameter constraints, plus (ii) robust estimation in the presence of outliers and (iii) multi-model (ii) robust estimation in the presence of outliers and (iii) multi-model comparisons. comparisons. Here, (A) a projection algorithm based on generalisations of square-root Here, (A) a projection algorithm based on generalisations of square-root decompositions allows an efficient and numerically stable local resolution decompositions allows an efficient and numerically stable local resolution of a set of non-linear equations. On the other hand, (B) a robust estimation of a set of non-linear equations. On the other hand, (B) a robust estimation module of a hierarchy of non-linear models has been designed and validated. module of a hierarchy of non-linear models has been designed and validated. A step ahead, (C) the software architecture of the estimation module is A step ahead, (C) the software architecture of the estimation module is discussed with the goal of being integrated in reactive software discussed with the goal of being integrated in reactive software environments or within applications with time constraints, while an environments or within applications with time constraints, while an experimentation considering the parameterisation of retinal displacements experimentation considering the parameterisation of retinal displacements between two views is proposed as an illustration of the estimation module.

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-4050.pdf (1.01 Mo) Télécharger le fichier

Dates and versions

inria-00072587 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00072587 , version 1

Cite

Thierry Viéville, Diane Lingrand, François Gaspard. Implementing a Variant of the Kanatani's Estimation Method. [Research Report] RR-4050, INRIA. 2000. ⟨inria-00072587⟩
62 View
126 Download

Share

Gmail Facebook Twitter LinkedIn More