Estimation of nonlinear errors-in-variables models for computer vision applications.

Bogdan Matei(1) and Peter Meer(2)

(1)Vision Technologies Laboratory
Sarnoff Corporation, 201 Washington Road
Princeton, NJ 08540.

(2)Department of Electrical and Computer Engineering
Rutgers University, Piscataway, NJ 08854-8058, USA

In an errors-in-variables (EIV) model all the measurements are corrupted by noise. The class of EIV models with constraints separable into the product of two nonlinear functions, one solely in the variables and one solely in the parameters, is general enough to represent most computer vision problems. We show that the estimation of such nonlinear EIV models can be reduced to iteratively estimating a linear model having point dependent, i.e., heteroscedastic, noise process. Particular cases of the proposed heteroscedastic errors-in-variables (HEIV) estimator are related to other techniques described in the vision literature: the Sampson method, renormalization and the fundamental numerical scheme. In a wide variety of tasks the HEIV estimator exhibits the same, or superior performance as these techniques, and has a weaker dependence on the quality of the initial solution than the Levenberg-Marquardt method, the standard approach toward estimating nonlinear models.

IEEE Trans. Pattern Anal. Machine Intell. , 28, 1537-1552, 2006.
Return to Research: Estimation under heteroscedasticity       Return to List of Publications
Download the paper