Human gesture segmentation based on change point model for efficient gesture interface

Interacting naturally with artificial agents and environments including virtual avatars and robots rely mainly on gestures. However, the later require heavy setup procedures before any effective use. Specific and personalized training sessions are needed. In addition, performers have to indicate clear separations between gestures, namely, specifying pre- and post-strokes as well as the gesture used to perform the command. Thus, time series segmentation appears as a central problem. Indeed, clustering human motions into meaningful segments or isolating meaningful segments forming a continuous movement flow present the same problem: how to find the post and the pre strokes. For machine learning, this problem is solved by having training sets of carefully labeled data. Good segmentation improves the quality of the gesture recognition-based interface. In our contribution, we focus on developing a non-parametric stochastic segmentation algorithm. Once the segmentation has been validated, we show how any novice user can create in a semi-supervised way, his or her, own gestures library. In addition, we show how the obtained system is efficient in finding meaningful gestures (the once learned earlier) within continuous movements flow, thus removing the constraint of performing manual specification of respectively the beginning of the movement and its end. The proposed technique is assessed through a real-life example, where a novice user creates an ad-hoc interface to control a robot in a natural way.