This paper proposes a new control method for Pan-Tilt stereo camera system to track a moving object when there are many uncertainties in the parameters of both camera and Pan-Tilt platform. If a pair of cameras placed on the Pan-Tilt robot, it is unnecessary for its installation location to be determined accurately. | Journal of Computer Science and Cybernetics, , (2015), 107–122 DOI: A NEW CONTROL METHOD FOR STEREO VISUAL SERVOING SYSTEM WITH PAN-TILT PLATFORM LE VAN CHUNG1 AND PHAM THUONG CAT2 1 Thai Nguyen University of Information and Communication Technology; chunglv84@ 2 Institute of Information Technology, Vietnam Academy of Science and Technology; ptcat@ Abstract. This paper proposes a new control method for Pan-Tilt stereo camera system to track a moving object when there are many uncertainties in the parameters of both camera and Pan-Tilt platform. If a pair of cameras placed on the Pan-Tilt robot, it is unnecessary for its installation location to be determined accurately. Assuming that the optical parameters like focal length of two cameras in the simulation are the same. A two degree of freedom Pan-Tilt platform holding camera has many uncertain parameters such as inertial moment, Jacobian matrix, the friction and noise impact, etc. The proposed control algorithm is highly adaptive and robust due to the use of a compensating neural network with on-line learning rule. The asymptotic stability of overall control system is proved by Lyapunov’s stability method. Keywords. Target tracking, pan/tilt, stereo camera, neural network, Lyapunov stability. 1. INTRODUCTION Tracking moving targets is mainly applied in the security and military. Recently, this research topic attracts many researchers. Many visual servoing systems have been studied and developed. Most of all use one [3, 6] or two cameras to track moving targets. With stereo visual servoing system [7, 8, 13] the posture of the target can be determined in 3D Cartesian coordinates. From control methods point of view one can classify the visual servoing systems into kinematic [8] and dynamic controls. With the kinematics control method, the controllers of the systems have to calculate the necessary speeds of robot joints so that the tracking errors must .
