Retrieving Emotion from Motion Analysis: In a Real Time Parallel Framework for Robots

Abstract

Abstract. This paper presents a parallel real time framework for emotion extraction from video fragments of human movements. Its framework is used for tracking of a waving hand by evaluation of moving skin-colored objects. The tracking analysis demonstrates that acceleration and frequency characteristics of the traced objects are relevant for classification of the emotional expressiveness of human movements. The solution is part of a larger project on interaction between a human and a humanoid robot with the aim of training social behavioral skills to autistic children with robots acting in a natural environment.

Online feedback system for public speakers

“…In fact, most relevant works in the literature have aimed to find the correspondence between physical entities of movements with a particular set of LMA's components, e.g. [25], [28]. The work of Rett [25] has offered significant indications.…”

WikiTherapist

“…So far, the NAO robot is trained to recognize simple instrumental and emotional movements based on emotional primitives (Lourens & Barakova, 2009). Furthermore, it is able to perform rather complex movements.…”

User-Friendly Robot Environment for Creation of Social Scenarios

“…So far the framework has been tested by design students and professionals that have created behaviors within TiVIPE [14,1] and image analysis for robot control [15,16]. Our future focus will be on scenario's and a layered component infrastructure, here the essence is to compound a set of blocks into meaningful partial sub-scenario's.…”