Hand Tracking Accuracy Enhancement by Data Fusion Using Leap Motion and Myo Armband

摘要

In this paper, by using the combination of Leap Motion and Myo armband, two methods for hand tracking and online hand gesture identification are proposed. With the proposed methods, We have improved the measurement accuracy of the palm direction and solved the problem of insufficient accuracy when the palm is at the limit of the measurement range. We use the Kalman filter algorithm and the neural network classification method to process the data measured by Leap Motion and Myo, so that the tracking of the operator's hand gesture is more accurate and robust even when the hand is at positions close to the measurement limit of one single sensor. The methods, which improve the hand tracking accuracy, can be used for robotic control, demonstration or teleoperation. The effectiveness of the proposed methods has been demonstrated through comparative experiments.