We built an acoustic, gesture-based recognition system called Multiwave, which leverages the Doppler Effect to translate multidimensional movements into user interface commands.
Our dynamic time warping based approach for both segmented and continuous data is designed to be a robust, go-to method for gesture recognition across a variety of modalities using only limited training samples.
We introduce a novel technique called gesture path stochastic resampling (GPSR) that is computationally efficient, has minimal coding overhead, and yet despite its simplicity is able to achieve higher accuracy than competitive, state-of-the-art approaches.
We present the results of a user study of Multiwave to evaluate recognition rates for different gestures and report accuracy rates comparable to or better than the current state of the art.
We explore the benefits of intelligent prototype selection for $-family recognizers.