Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/127880
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLucey, S.en
dc.contributor.authorNavarathna, R.en
dc.contributor.authorAshraf, A.en
dc.contributor.authorSridharan, S.en
dc.date.issued2013en
dc.identifier.citationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013; 35(6):1383-1396en
dc.identifier.issn0162-8828en
dc.identifier.issn1939-3539en
dc.identifier.urihttp://hdl.handle.net/2440/127880-
dc.description.abstractIn this paper, we propose a framework for both gradient descent image and object alignment in the Fourier domain. Our method centers upon the classical Lucas & Kanade (LK) algorithm where we represent the source and template/model in the complex 2D Fourier domain rather than in the spatial 2D domain. We refer to our approach as the Fourier LK (FLK) algorithm. The FLK formulation is advantageous when one preprocesses the source image and template/model with a bank of filters (e.g., oriented edges, Gabor, etc.) as 1) it can handle substantial illumination variations, 2) the inefficient preprocessing filter bank step can be subsumed within the FLK algorithm as a sparse diagonal weighting matrix, 3) unlike traditional LK, the computational cost is invariant to the number of filters and as a result is far more efficient, and 4) this approach can be extended to the Inverse Compositional (IC) form of the LK algorithm where nearly all steps (including Fourier transform and filter bank preprocessing) can be precomputed, leading to an extremely efficient and robust approach to gradient descent image matching. Further, these computational savings translate to nonrigid object alignment tasks that are considered extensions of the LK algorithm, such as those found in Active Appearance Models (AAMs).en
dc.description.statementofresponsibilitySimon Lucey, Rajitha Navarathna, Ahmed Bilal Ashraf, Sridha Sridharanen
dc.language.isoenen
dc.publisherIEEEen
dc.rights© 2013 IEEEen
dc.subjectHumans; Facial Expression; Algorithms; Fourier Analysis; Image Processing, Computer-Assisted; Pattern Recognition, Automateden
dc.titleFourier Lucas-Kanade algorithmen
dc.typeJournal articleen
dc.identifier.rmid1000025597en
dc.identifier.doi10.1109/TPAMI.2012.220en
dc.relation.granthttp://purl.org/au-research/grants/arc/FT0991969en
dc.identifier.pubid535188-
pubs.library.collectionComputer Science publicationsen
pubs.library.teamDS10en
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


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