Several camera geometry models and error analysis for image matching in 3-D machine vision

An important task in stereo machine vision is to determine the three-dimensional location of objects from different views (images)of the object scene. The actual location of a scene element can be determined from the disparity of two (each in deferent image) of its depicted entities . Prior to establishing disparity,however,the correspondence problem (or matching problem) must be solved.in this paper, we concentrate on the problem of camera geometry modeling. We discuss several kinds of camera geometry for image matching in 3D machine vision. And their error analysis is also studied.