An in-situ trainable gesture classifier

Gesture recognition, i.e., the recognition of pre-defined gestures by arm or hand movements, enables a natural extension of the way we currently interact with devices (Horsley, 2016). Commercially available gesture recognition systems are usually pre-trained: the developers specify a set of gestures, and the user is provided with an algorithm that can recognize just these gestures. To improve the user experience, it is often desirable to allow users to define their own gestures. In that case, the user needs to train the recognition system herself by a set of example gestures. Crucially, this scenario requires learning gestures from just a few training examples in order to avoid overburdening the user. We present a new in-situ trainable gesture classifier based on a hierarchical probabilistic modeling approach. Casting both learning and recognition as probabilistic inference tasks yields a principled way to design and evaluate algorithm candidates. Moreover, the Bayesian approach facilitates learning of prior knowledge about gestures, which leads to fewer needed examples for training new gestures.