Title :
Homography estimation from correspondences of local elliptical features
Author :
Chum, Ondrej ; Matas, Jose
Author_Institution :
Dept. of Cybern., CTU in Prague, Prague, Czech Republic
Abstract :
We propose a novel unified approach for homography estimation from two or more correspondences of local elliptical features. The method finds a homography defined by first-order Taylor expansions at two (or more) points. The approximations are affine transformations that are constrained by the ellipse-to-ellipse correspondences. Unlike methods based on projective invariants of conics, the proposed method generates only a single homography model per pair of ellipse correspondences. We show experimentally, that the proposed method generates models of precision comparable or better than the state-of-the-art at lower computational costs.
Keywords :
affine transforms; approximation theory; geometry; image processing; affine transformations; approximations; ellipse-to-ellipse correspondences; first-order Taylor expansions; homography estimation; local elliptical features; novel unified approach; point- based homography matrix; projective invariants; single homography model; Approximation methods; Equations; Estimation; Geometry; Mathematical model; Robustness; Transmission line matrix methods;
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4673-2216-4