Gesture Recognition for Improved User Experience in a Smart Environment

Ambient Intelligence (AmI) is a new paradigm that specifically aims at exploiting sensory and context information in order to adapt the environment to the user’s preferences; one of its key features is the attempt to consider common devices as an integral part of the system in order to support users in carrying out their everyday life activities without affecting their normal behavior. Our proposal consists in the definition of a gesture recognition module allowing users to interact as naturally as possible with the actuators available in a smart office, by controlling their operation mode and by querying them about their current state. To this end, readings obtained from a state-of-the-art motion sensor device are classified according to a supervised approach based on a probabilistic support vector machine, and fed into a stochastic syntactic classifier which will interpret them as the basic symbols of a probabilistic gesture language. We will show how this approach is suitable to cope with the intrinsic imprecision in source data, while still providing sufficient expressivity and ease of use.