Piano playing gloves are a new intelligent wearable device. The multiinertial sensors in the gloves can sense and analyze the gesture state of piano players in real time, which can make piano learners know whether the playing gestures are standard in real time, thus effectively improving piano learning efficiency and interest, and reducing learning costs. Different from gestures in other application fields, piano playing gestures have the characteristics of diversity, rapidity, great dynamics and strong time-varying. A design scheme of non-contact gesture recognition system is proposed. In this system, infrared and ambient light sensors Si1143 are combined with capacitive touch-sensitive microcontrollers such as C8051F700 and C8051F800 to realize non-contact gesture recognition, which can be used for various actions and gesture detection and distance calibration of target objects.