RGBD Sensors for Human Activity Detection in AAL Environments

Abstract

This paper aims to propose a novel idea of an embedded intelligent system where a low cost embedded vision system can analyze human behaviors to obtain interactivity and statistical data, mainly devoted to human behavior analysis in Ambient Assisted Living environments. We construct a system that uses vertical RGBD sensor for people tracking and interaction analysis, where the depth information has been used to remove the affect of the appearance variation and to evaluate users activities inside the home and in front of the fixtures. Also group interactions are monitored and analyzed with the main goal of having a better knowledge of the users activities, using real data in real time. All information coming from this human behavior analysis tool can be used to provide basic data gathered in real time for an Ambient Assisted Living environment. Even if preliminary, the results are convincing and most of all the general architecture is affordable in this specific application, robust, easy to install and to maintain and low cost.