A Neural Control System of a Two Joints Robot for Visual Conferencing

Abstract

This paper presents a real time interactive conferencing system that allows people to communicate via animated images. The employed distant cameras act as a remote vision system. The cameras simulate the movement of an observer and return images covering the surrounding view of the pictured person. This paper also describes the neuro-command system that controls a robot with two joints (degrees of freedom) that carries the used camera. This neural system translates the head movements. A methodology from image processing has been adopted for the classification, and facilitation of the phase of neural network learning process.