Ultrasonic Hand Gesture Detection and Tracking using CFAR and Kalman Filter

This paper presents a new approach to hand gesture recognition using CFAR(Constant False Alarm Rate) and Kalman filter based on a compact ultrasonic phased array. A 45mm-long linear ultrasonic phased array includes a single transducer element as transmitter and eight transducer elements as receiver. Firstly, the range and azimuth of the targets is determined by offline receiver beamforming. Secondly, the CFAR detection technology in radar system is developed to provide reliable identification of the hand gesture. Furthermore, the Kalman filter is used for tracking the moving target and its motion trajectory can be acquired. Experimental results show that the proposed technique can effectively detect and track the hand gestures, which is applicable to the human-computer interaction.