Hand/arm Gesture Segmentation by Motion Using IMU and EMG Sensing

Abstract

Gesture recognition is more reliable with a proper motion segmentation process. In this context we can distinguish if gesture patterns are static or dynamic. This study proposes a gesture segmentation method to distinguish dynamic from static gestures, using (Inertial Measurement Units) IMU and Electromyography (EMG) sensors. The performance of the sensors, individually as well as their combination, was evaluated by different users. It was concluded that when considering gestures which only contain arm movement, the lowest error obtained was by the IMU. However, as expected, when considering gestures which have only hand motion, the combination of the 2 sensors achieved the best performance. Results of the sensor fusion modality varied greatly depending on user. The application of different filtering method to the EMG data as a solution to the limb position resulted in a significative reduction of the error.