We deal with the calibration problem of an active head-eye system, which consists of a pair of cameras mounted on a head with 13 degrees of freedom. The aim of the calibration is to establish relative positions of different 3D systems: between camera and neck, eye and neck, etc., so that we can keep track of the camera position in a fixed (calibration) reference system as a function of the visual parameters of the head-eye system. We formulate the problem and propose both closed-form and nonlinear optimization approaches to solve it. Experiments were carried out and comparison of results with other algorithms were made on both simulated and real data.