Human body language analysis: A preliminary study based on kinect skeleton tracking

Abstract

The nonverbal communication can be informally defined as the communicative process between two or more entities (e.g., persons) which achieving an informative exchange without using the semantic meaning of the words. This process can be accomplished by using one or more language forms, including the body language (i.e., movements, gestures, and postures) which in turn can be composed by voluntary and involuntary behaviours. The analysis and interpretation of these behaviours can infer different internal states of persons (e.g., feelings, attitudes, emotions) which in turn can support the development of a wide range of automatic applications in different fields, such as: rehabilitation, security, people identification, human behaviour analysis, biometric. In recent years, we have focused our efforts in developing a first implementation of Kinematic, a novel multimodal framework designed to support advanced human-machine interfaces. The purpose of the framework is to provide a tool to analyze and interpret verbal and nonverbal human-to-human communication in order to transfer this ability to the human-machine interaction. In this paper we face a specific aspect of the framework regarding the first calibration phase of the numerical measures related to the Kinect skeleton used to analyze and interpret the body language. The numerical measures was obtained analyzing the movements of the skeleton during individual and social contexts. A preliminary qualitative and quantitative study has been reported and discussed. © 2013 Springer-Verlag.