This paper presents a robust method to track a moving object under occlusion using an off-the-shelf monocular camera and a 6 Degree of Freedom (DOF) articulated arm. The visual servoing problem of tracking a known object using data from a monocular camera can be solved with a simple closed loop controller. However, this system frequently fails in situations where the object cannot be detected and to overcome this problem an estimation based tracking system is required. This work employs an Adaptive Kalman Filter (AKF) to improve the visual feedback of the camera. The role of the AKF is to estimate the position of the object when it is occluded/out of view and remove the noise and uncertainties associated with visual data. Two estimation models for the AKF are selected for comparison and among them, the Mean-Adaptive acceleration model is implemented on a 6-DOF UR5 articulated arm with a monocular camera mounted in eye-in-hand configuration to follow the known object in 2D cartesian space (without using depth information). © 2019 Association for Computing Machinery.