3D human gesture capturing and recognition by the IMMU-based data glove

Gestures recognition provides an intelligent, natural, and convenient way for human-robot interaction (HRI). This paper presents a novel data glove for gestures capturing and recognition based on inertial and magnetic measurement units (IMMUs), which are made up of three-axis gyroscopes, three-axis accelerometers and three-axis magnetometers. The proposed data glove has eighteen low-cost IMMUs, which are compact and small enough to wear. The gestures included the three-dimensional motions of arm, palm and fingers are completely captured by the data glove. Meanwhile, we attempt to use extreme learning machine (ELM) for gesture recognition which has not found yet in the relevant application. The ELM-based recognition methods for both static gestures and dynamic gestures are respectively presented. The experimental results of gestures capturing and recognition verify the effectiveness of the proposed methods.