A data-driven learning approach to image registration

Mustafa, Mohammad A.R. (2016) A data-driven learning approach to image registration. PhD thesis, University of Nottingham.

[img] PDF (Thesis - as examined) - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (6MB)


Handling large displacement optical flow is a remarkably arduous task. For instance, standard coarse-to-fine techniques often struggle to adequately deal with moving objects whose motion exceeds their size. Here we propose a learning approach to the estimation of large displacement between two non-consecutive images in a sequence on the basis of a learning set of optical flows estimated a priori between different consecutive images in the same sequence. Our method refines an initial estimate of the flow field by replacing each displacement vector by a linear combination of displacement vectors at the center of similar patches taken from a code-book built from the learning set. The key idea is to use the accurate flows estimated a priori between consecutive images to help improve the potentially less accurate flows estimated online between images further apart. Experimental results suggest the ability of a purely data-driven learning approach to handle fine scale structures with large displacements.

Item Type: Thesis (University of Nottingham only) (PhD)
Supervisors: Pitiot, A.
Kadir, T.
Peirce, J.
Subjects: B Philosophy. Psychology. Religion > BF Psychology
T Technology > TA Engineering (General). Civil engineering (General) > TA1501 Applied optics. Phonics
Faculties/Schools: UK Campuses > Faculty of Science > School of Psychology
Item ID: 33723
Depositing User: Mustafa, Mohammad
Date Deposited: 16 Aug 2016 11:08
Last Modified: 19 Jul 2020 04:30
URI: https://eprints.nottingham.ac.uk/id/eprint/33723

Actions (Archive Staff Only)

Edit View Edit View