TY - JOUR
T1 - Global parametric image alignment via high-order approximation
AU - Keller, Y.
AU - Averbuch, A.
PY - 2008/3
Y1 - 2008/3
N2 - 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.
AB - 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.
KW - Large motions
KW - Motion estimation
KW - Non-linear optimization
UR - http://www.scopus.com/inward/record.url?scp=38949167126&partnerID=8YFLogxK
U2 - 10.1016/j.cviu.2007.05.003
DO - 10.1016/j.cviu.2007.05.003
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:38949167126
SN - 1077-3142
VL - 109
SP - 244
EP - 259
JO - Computer Vision and Image Understanding
JF - Computer Vision and Image Understanding
IS - 3
ER -