Global parametric image alignment via high-order approximation

Y. Keller, A. Averbuch

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

The estimation of parametric global motion is one of the cornerstones of computer vision. Such schemes are able to estimate various motion models (translation, rotation, affine, projective) with subpixel accuracy. The parametric motion is computed using a first order Taylor expansions of the registered images. But, it is limited to the estimation of small motions, and while large translations and rotations can be coarsely estimated by Fourier domain algorithms, no such techniques exist for affine and projective motions. This paper offers two contributions: first, we improve both the convergence range and rate using a second order Taylor expansion and show first order methods to be a degenerate case of the proposed scheme. Second, we extend the scheme using a symmetrical formulation which further improves the convergence properties. The results are verified by rigorous analysis and experimental trials.

Original languageEnglish
Pages (from-to)244-259
Number of pages16
JournalComputer Vision and Image Understanding
Volume109
Issue number3
DOIs
StatePublished - Mar 2008
Externally publishedYes

Keywords

  • Large motions
  • Motion estimation
  • Non-linear optimization

Fingerprint

Dive into the research topics of 'Global parametric image alignment via high-order approximation'. Together they form a unique fingerprint.

Cite this