Robust vision system for space teleoperation ground verification platform

In this paper, we design and develop a robust vision system for space teleoperation ground verification platform. It consists four subsystems to achieve the following functions: Image acquisition and monitor, image transmission, cooperative object detection and track, pose estimation for robot. In order to complete visual guidance tasks, we design an novel cooperative object and propose the correspongding object detection and track algorithm. The algorithm is efficient and effective, it can locate the cooperative object accurately. Based on the precise location of the coopertive object, we also propose a pose measurement method by the stereo vision system. The effectiveness of the proposed method is demonstrated with different experiments. The results show that the values of the pose parameters are very close to the ground truth. The translation error is 0.8mm, and the rotation error is 2degree