Human Robot Interaction Based on Bayesian Analysis of Human Movements

We present as a contribution to the field of human-machine interaction a system that analyzes human movements online, based on the concept of Laban Movement Analysis (LMA). The implementation uses a Bayesian model for learning and classification, while the results are presented for the application to gesture recognition. Nowadays technology offers an incredible number of applications to be used in humanmachine interaction. Still, it is difficult to find implemented cognitive processes that benefit from those possibilities. Future approaches must offer to the user an effortless and intuitive way of interaction. We present the Laban Movement Analysis as a concept to identify useful features of human movements to classify human actions. The movements are extracted using both, vision and magnetic tracker. The descriptor opens possibilities towards expressiveness and emotional content. To solve the problem of classification we use the Bayesian framework as it offers an intuitive ap...

• Type: Conference
• Year: 2007
• Where: EPIA
• Authors: Jörg Rett, Jorge Dias
• Keywords: EPIA 2007, Human Movements, Human-machine Interaction, Laban Movement Analysis