Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier6qtX3pFwXQZG2LgkFdY/LQsmP
Repositorysid.inpe.br/sibgrapi@80/2006/07.22.18.53
Last Update2006:07.22.18.53.30 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi@80/2006/07.22.18.53.31
Metadata Last Update2022:06.14.00.13.18 (UTC) administrator
DOI10.1109/SIBGRAPI.2006.46
Citation KeyDoriniGold:2006:NoFeUn
TitleUnscented KLT: nonlinear feature and uncertainty tracking
FormatOn-line
Year2006
Access Date2024, Apr. 28
Number of Files1
Size271 KiB
2. Context
Author1 Dorini, Leyza Elmeri Baldo
2 Goldenstein, Siome Klein
Affiliation1 Unicamp - Universidade Estadual de Campinas
2 Unicamp - Universidade Estadual de Campinas
EditorOliveira Neto, Manuel Menezes de
Carceroni, Rodrigo Lima
e-Mail Addressleyza.dorini@gmail.com
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 19 (SIBGRAPI)
Conference LocationManaus, AM, Brazil
Date8-11 Oct. 2006
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2006-07-22 18:53:31 :: leyza -> banon ::
2006-08-30 21:50:52 :: banon -> leyza ::
2008-07-17 14:11:03 :: leyza -> administrator ::
2009-08-13 20:38:10 :: administrator -> banon ::
2010-08-28 20:02:24 :: banon -> administrator ::
2022-06-14 00:13:18 :: administrator -> :: 2006
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsfeature tracking
uncertainty tracking
outlier rejection
AbstractAccurate 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.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2006 > Unscented KLT: nonlinear...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Unscented KLT: nonlinear...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/6qtX3pFwXQZG2LgkFdY/LQsmP
zipped data URLhttp://urlib.net/zip/6qtX3pFwXQZG2LgkFdY/LQsmP
Languageen
Target Filedorini-Uklt.pdf
User Groupleyza
administrator
Visibilityshown
5. Allied materials
Next Higher Units8JMKD3MGPEW34M/46RFT7E
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2022/05.08.00.20 5
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage edition electronicmailaddress group isbn issn label lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close