@InProceedings{DoriniGold:2006:NoFeUn,
author = "Dorini, Leyza Elmeri Baldo and Goldenstein, Siome Klein",
affiliation = "{Unicamp - Universidade Estadual de Campinas} and {Unicamp -
Universidade Estadual de Campinas}",
title = "Unscented KLT: nonlinear feature and uncertainty tracking",
booktitle = "Proceedings...",
year = "2006",
editor = "Oliveira Neto, Manuel Menezes de and Carceroni, Rodrigo Lima",
organization = "Brazilian Symposium on Computer Graphics and Image Processing, 19.
(SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "feature tracking, uncertainty tracking, outlier rejection.",
abstract = "Accurate feature tracking is the foundation of several high level
tasks, such as 3D reconstruction and motion analysis. Although
there are many feature tracking algorithms, most of them do not
maintain information about the error of the data being tracked. In
this paper, we propose a new generic framework that uses the
Scaled Unscented Transform (SUT) to augment arbitrary feature
tracking algorithms, by introducing Gaussian Random Variables
(GRV) for the representation of features' locations uncertainties.
Here, we apply the framework to the well-understood
Kanade-Lucas-Tomasi (KLT) feature tracker, giving birth to what we
call Unscented KLT (UKLT). It tracks probabilistic confidences and
better rejects errors, all on-line, and leads to more robust
computer vision applications. We also validade the experiments
with a bundle adjustment procedure, using real and synthetic
sequences.",
conference-location = "Manaus, AM, Brazil",
conference-year = "8-11 Oct. 2006",
doi = "10.1109/SIBGRAPI.2006.46",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2006.46",
language = "en",
ibi = "6qtX3pFwXQZG2LgkFdY/LQsmP",
url = "http://urlib.net/ibi/6qtX3pFwXQZG2LgkFdY/LQsmP",
targetfile = "dorini-Uklt.pdf",
urlaccessdate = "2025, Feb. 16"
}