Mathematical models for the calibration of cameras mounted on a tripod using primitive tracking

Abstract

In this paper we present new mathematical models for video sequence calibration when cameras are mounted on a tripod. One of the main novelties is that tripod rotation center and camera projection center are not supposed to be the same. The calibration is based on the geometry of the tripod and a primitive tracking procedure which uses lines and circles as primitives. For the extraction of primitive information, we use a CART (Classification and Regression Tree). We have applied the method proposed to sport event scenarios, specifically, soccer matches. In order to illustrate its performance, it has been applied to real HD (High Definition) video sequences and some numerical experiments are shown. The quality of the camera calibration procedure is validated by inserting virtual elements in the video sequence.