WristMouse: Wearable Mouse Controller based on Pressure Sensors

Abstract

In this paper, we present a wearable mouse controller based on the pressure sensors, which can recognize the hand gestures in real-time and translate them into the movements of mouse. Only four force sensitive resistors (FSRs) are placed around the wrist to capture the wrist pressure distribution of different hand gestures. A novel real-time recognition framework is proposed which can accurately and quickly identify the starting and ending position of the gesture. In the proposed framework, a pressure-parameter adaptive updating strategy is designed for improving the robust of the system. For different hand positions, different users and re-wear, the system still has a good performance. To ensure the real-time of the system, we choose some simple features and classifiers to recognize hand gestures for decreasing the time complexity. In addition, the WristMouse prototype has a small volume, a low energy consumption and is easy to integrate with the normal wearable devices like smart watch and smart wristband. Our study shows that the proposed system has a good performance in real-time hand gesture recognition with a high F-score of 92.55%, and the average time delay per second is less than 50ms for processing data.