Recovering Euclidean structure by conics and spheres: application to camera calibration.

Abstract

A novel method of two-dimensional Euclidean structure recovery in one view from the projections of N parallel conics is proposed, which can be applied to camera calibration. Without considering the conic dual to the absolute points, we transform conic features from the homogeneous coordinates to the lifted coordinates. In the lifted space, the conic features have similar properties to the point or line features, which especially means that the homography can also be deduced by conic features directly. Our work gives a generic framework of recovering the Euclidean structure from conic features. A series of experiments with simulated and real data are conducted. The experiment results show that the proposed method has its validity in practical applications to camera calibration.