The epipolar geometry of the log-polar image plane

This work presents an explicit formulation of the epipolar geometry of two oriented log-polar images. A method is derived for efficient pixel-by-pixel computation of epipolar lines in the log-polar plane, which are complicated nonlinear functions. As an example, the method is applied for dense stereo matching: it is shown that it is more efficient to perform one-dimensional disparity estimation in the log-polar plane than to remap the images to Cartesian coordinates.