Single image based camera calibration and pose estimation of the end-effector of a robot

Abstract

A new method is proposed for measurement of six dimensional pose of an industrial robot using a single image from a camera which is not pre-calibrated. Additionally during the pose determination, camera internal parameters are also obtained, which makes the method a suitable alternative for calibrating camera using a single image. Results from the two variants of the proposed approach are compared with Zhang's camera calibration algorithm and has been found to be better. Another utility of the proposed algorithm is to measure six dimensional pose of an industrial robot. Robot repeatability was also measured using the proposed camera calibration algorithm. The repeatability results were compared with the measurements using Artificial Reality toolkit ArUco which is a de-facto standard in the pose measurements using camera. The performance of the proposed method is better than that obtained from ArUco. Another area of application is identification of kinematic parameters. Using the circle point analysis method, identification of KUKA KR5 Arc robot was done using the proposed method.