Abstract
We propose an automatic macera calibration method to calibrate the position and orientation parameters of a newly installed camera in our human motion tracking system. In the method, both 3D position tracking results and 2D positions and sizes on camera image planes are used for the calibration. Because we employ a simple 2D to 3D position translation method based on the observed size of the target, the calibration results become stable even if the input data includes large observation errors. Using this method, the cost of installing the camera in the human tracking system is effectively reduced. Experimental results show the effectiveness of the proposed method.
