UKF-based visual tracking with eye-in-hand camera

This paper presents a new image-based visual tracking method for a robot manipulator to trace a moving target using monocular camera mounted on the end-effector. The intrinsic and extrinsic parameters of the camera are already known. In order to estimate the 3D position of the rigid body target, three points (not collinear) from the rigid body were selected as reference. We assumed that these three points will never be occluded by the rigid body itself. Based on this assumption, we employ a new point adaptive Unscented Kalman Filter (UKF) algorithm to track the rigid body and estimate its motion in real-Time. Simulation and experimental results are included to illustrate the performance of the proposed method on a 3-degree-of-freedom (DOF) robot manipulator.