Determine the Camera Eigenmatrix from Large Parallax Images

Abstract

Recovering camera parameters from a group of image pairs is an important problem in computer vision. The traditional 4-point solution is vulnerable to insufficient or too concentrated number of corresponding point pairs when the viewpoint changes greatly, which leads to the failure of camera parameter recovery. This paper presents a method to quickly determine the corresponding point pairs from a group of image pairs with parallax by calculating the polar geometry. By using: for the pixel $p$ in camera (viewpoint) $A$, all pixels corresponding to $p$ in camera (viewpoint) $B$ are located at the same epipolar line. Similarly, the line passing through the center of $A$ and $p$ on $B$ is located at a epipolar line. Therefore, when $A$ and $B$ are synchronized, the instantaneous point of two objects projecting to the same pixel $p$ at time $t_1$ and $t_2$ of $A$ is located on a epipolar line of $B$. The camera eigenmatrix is calculated by using epipolar line pairs instead of points, and the search space for polar line matching is greatly reduced by using pixels recording multiple depths to accelerate the calculation of camera eigenmatrix, so as to achieve camera parameters quickly and accurately.