Utilizing deep learning architectures for in-air hand-gesture recognition with multi-modal audio Doppler and infrared signals
We introduce AirWare, an in-air hand-gesture recognition system that uses the already embedded speaker and microphone in most electronic devices, together with low-cost infrared proximity sensors. Gestures identified by AirWare are performed in the air above a touchscreen or a mobile phone. AirWare utilizes deep neural networks to identify complex hand gestures using multi-modal audio Doppler signatures and infrared (IR) sensor information. This work is an improvement on present-day systems which use high frequency Doppler radars or depth cameras to uniquely identify in-air gestures.