A multi-objective parameter estimator for image mosaicing
Tony Scoleri, Wojciech Chojnacki, Michael J. Brooks · 2006
We consider the image mosaicing task of estimating the homography that defines the transfer function between a pair of overlapping images. A novel homography estimator is proposed that is multi-objective in character in its dealing with a system of underlying equations. Experiments carried out with both synthetic and real images reveal the estimator to be commensurate in accuracy with the Gold Standard maximum likelihood estimator, but with the advantage of being considerably faster. 1.