Improving User Experience via Motion Sensors in an Ambient Intelligence Scenario

Ambient Intelligence (AmI) is a new paradigm in Artificial Intelligence that aims at exploiting the information about the environment state in order to adapt it to the user preferences. AmI systems are usually based on several cheap and unobtrusive sensing devices that allow for continuous monitoring in different scenarios. In this work we present a gesture recognition module for the management of an office environment using a motion sensor device, namely Microsoft Kinect, as the primary interface between the user and the AmI system. The proposed gesture recognition method is based on both RGB and depth information for detecting the hand of the user and a fuzzy rule for determining the state of the detected hand. The shape of the hand is interpreted as one of the basic symbols of a grammar expressing a set of commands for the actuators of the AmI system. In order to maintain a high level of pervasiveness, the Kinect sensor is connected to a miniature computer capable of real-time processing.