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 hdl:20.500.11880/26349 http://dx.doi.org/10.22028/D291-26293 |
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 | Size | Format | |
---|---|---|---|---|
preprint_106_04.pdf | 317,59 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.