Tracking posture and head movements of impaired people during interactions with robots

Abstract

Social robots are starting to be used in assistive scenarios as natural tool to help impaired people in their daily life activities and in rehabilitation activities. A central problem of such kind of systems is the tracking of humans activity in a reliable way. The system presented in this paper tries to address this problem through the use of an RGB-D sensor. State of art algorithms are used to detect and track the body posture and the heads pose of each human partner. © 2013 Springer-Verlag.