Michal Perdoch, Jiri Matas, Ondrej Chum: Epipolar Geometry from Two
Correspondences
Abstract:
A novel algorithm for robust RANSAC-like estimation of epipolar geometry
(of uncalibrated camera pair) from two correspondence s of local affine frames
(LAFs) is presented. Each LAF is constructed from three points independently
detected on a maximally stable extremal region. The algorithm assumes that a
sufficiently accurate approximation of the fundamental matrix is obtained from
two LAF correspondence s by the 6-point algorithm of Stéwenius et al. The
so-far-the-best hypotheses are further processed by so-called local
optimization to estimate the epipolar geometry. Special attention is paid to
planar sample degeneracy, since the probability of drawing two coplanar LAF
correspondences is not negligible. Combining the 6-point solver, local
optimization, and the degeneracy test enables RANSAC to draw samples of only
two LAFs to generate hypotheses and thus to reduce the number of samples
drawn. We experimentally show that using the 6-point algorithm (restricting to
cameras with unit aspect ratio, zero skew, principal point in the center of
image, and a common unknown focal length) generates hypotheses that are
sufficient for epipolar geometry estimation in LO-RANSAC framework.