WiCatch: A Wi-Fi Based Hand Gesture Recognition System

In recent years, a large number of researchers are endeavoring to develop wireless sensing and related applications as Wi-Fi devices become ubiquitous. As a significant research branch, gesture recognition has become one of the research hotspots. In this paper, we propose WiCatch, a novel device free gesture recognition system which utilizes the channel state information to recognize the motion of hands. First of all, with the aim of catching the weak signals reflected from hands, a novel data fusion-based interference elimination algorithm is proposed to diminish the interference caused by signals reflected from stationary objects and the direct signal from transmitter to receiver. Second, the system catches the signals reflected from moving hands and rebuilds the motion locus of the gesture by constructing the virtual antenna array based on signal samples in time domain. Finally, we adopt support vector machines to complete the classification. The extensive experimental results demonstrate that the WiCatch can achieves a recognition accuracy over 0.96. Furthermore, the WiCatch can be applied to two-hand gesture recognition and reach a recognition accuracy of 0.95.