File(s) under permanent embargo
Image registration via geometrically constrained total variation optical flow
conference contribution
posted on 2018-01-01, 00:00 authored by M Shoeiby, M A Armin, Antonio Robles-KellyAntonio Robles-KellyIn this paper, we present a method for registration of image pairs. Our method relates both images to one another for registration purposes making use of optical flow. We formulate the problem in a variational setting making use of an L 1 -norm fidelity term, a total variation (TV) criterion, and a geometric constraint. This treatment leads to a cost function, in which, both the total variation and the homographic constraints are enforced via regularisation. Further, to compute the flow we employ a multiscale pyramid, whereby the total variation is minimized at each layer and the geometric constraint is enforced between layers. In practice, this is carried out by using a Rudin-Osher-Fatemi (ROF) denoising model within each layer and a gated function for the homography computation between layers. We also illustrate the utility of our method for image registration and flow computation and compare our approach to a mainstream non-geometrically constrained variational alternative elsewhere in the literature.
History
Event
Australian Pattern Recognition Society. Conference (2018 : Canberra, A.C.T.)Series
Australian Pattern Recognition Society ConferencePagination
1 - 7Publisher
Institute of Electrical and Electronics EngineersLocation
Canberra, A.C.T.Place of publication
Piscataway, N.J.Publisher DOI
Start date
2018-12-10End date
2018-12-13ISBN-13
9781538666029Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2018, IEEEEditor/Contributor(s)
M Murshed, M Paul, M Asikuzzaman, M PIckering, A Natu, A Robles-Kelly, S You, L Zheng, A RahmanTitle of proceedings
DICTA 2018 : Proceedings of the 2018 International Conference on Digital Image Computing: Techniques and ApplicationsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC