Please use this identifier to cite or link to this item: doi:10.22028/D291-26293
Title: Confidence measures for variational optic flow methods
Author(s): Bruhn, Andrés
Weickert, Joachim
Language: English
Year of Publication: 2004
Free key words: differential techniques
variational methods
DDC notations: 510 Mathematics
Publikation type: Other
Abstract: In this paper we investigate the usefulness of confidence measures for variational optic flow computation. To this end we discuss the frequently used sparsification strategy based on the image gradient. Its drawbacks motivate us to propose a novel, energy-based confidence measure that is parameter-free and applicable to the entire class of energy minimising optic flow techniques. Experimental evaluations show that this confidence measure leads to excellent results, independently of the image sequence or the underlying variational approach.
Link to this record: urn:nbn:de:bsz:291-scidok-44647
Series name: Preprint / Fachrichtung Mathematik, Universität des Saarlandes
Series volume: 106
Date of registration: 26-Jan-2012
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Mathematik
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
preprint_106_04.pdf317,59 kBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.