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 centre and camera projection centre 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.
To illustrate the quality of the results, the calibration we have obtained is used for the insertion of graphics into the video. We have chosen this kind of experiments because these applications require an accurate video calibration estimation. We have tested our method on different video sequences using both, scale models and real scenes from soccer matches. The sequences acquired using the scale model consist of 1440 x 809 frames. Real soccer sequences are 1920 x 1080 high definition video sequences.
In this paper we study the difficult problem of camera calibration of video sequences in scenarios where, in each frame, there are usually a small number of visible primitives which can be considered to perform the calibration. To solve this problem, we firstly assume that the camera is mounted on a tripod (which is a common situation in practice) and we study the geometry of the tripod from a mathematical point of view. This assumption strongly simplifies the calibration problem and allows recovering the frame calibration in situations where general calibration techniques fail. In the proposed model, one of the main novelties is the fact that the tripod rotation centre and camera projection centre are not supposed to be the same. Secondly, we use a new method for primitive tracking based on a CART (Classification and Regression Tree). This method is used in the calibration procedure and takes into account color information. We present some experiments using HD videos of soccer matches in both, scale models and real scenarios. In order to validate our approach, we insert some graphics into the video sequences using the estimated calibration parameters. We use this kind of validation because the insertion of graphics in video sequences requires an accurate video calibration estimation. The numerical results we present are precise and very promising .
This research has partially been supported by the MICINN project reference MTM2010-17615 (Ministerio de Ciencia e Innovación. Spain). We acknowledge MEDIAPRODUCCION S.L. for providing us with the real HD video we use in the numerical experiments.