ABSTRACT
This paper extends the topic of monocular pose estimation of an object using Aruco tags imaged by RGB cameras. The accuracy of the Open CV Camera calibration and Aruco pose estimation pipelines is tested in detail by performing standardized tests with multiple Intel Realsense D435 Cameras. Analyzing the results led to a way to significantly improve the performance of Aruco tag localization which involved designing a 3D Aruco board, which is a set of Aruco tags placed at an angle to each other, and developing a library to combine the pose data from the individual tags for both higher accuracy and stability.
ABSTRACT
In this analysis, we present results from measurements performed to determine the stability of a hand tracking system and the accuracy of the detected palm and finger's position. Measurements were performed for the evaluation of the sensor for an application in an industrial robot-assisted assembly scenario. Human-robot interaction is a relevant topic in collaborative robotics. Intuitive and straightforward control tools for robot navigation and program flow control are essential for effective utilisation in production scenarios without unnecessary slowdowns caused by the operator. For the hand tracking and gesture-based control, it is necessary to know the sensor's accuracy. For gesture recognition with a moving target, the sensor must provide stable tracking results. This paper evaluates the sensor's real-world performance by measuring the localisation deviations of the hand being tracked as it moves in the workspace.
