Camera-to-Camera Geometry Estimation Requiring no Overlap in their Visual Fields

Calibrating the relative geometry between cameras which would move against one another from time to time is an important problem in multi-camera system. Most of the existing calibration technologies are based on the cross-camera feature correspondences. This paper presents a new solution method. The method demands image data captured under a rigid motion of the camera pair, but unlike the existing motion correspondence-based calibration methods, it does not estimate optical flows nor motion correspondences explicitly. Instead it estimates the inter-camera geometry from the observations that are directly available from the two image streams -the monocular normal flows. Experimental results on real image data are shown to illustrate the feasibility of the solution.