Flavia Sparacino, Christopher Wren, Alex Pentland, Glorianna Davenport

Abstract

We present a new environment for browsing a visual landscape inhabited by digital movies that live, interact and play in a graphical virtual world. The movies are modeled as autonomous agents which have their own sensors and goals and which can interpret the actions of the participant and react to them. Our environment allows one---or more---people to interact with the HyperPlex world through the use of vision techniques. No goggles, gloves or wires are needed: interaction takes place with the use of computer vision techniques that analyze the image of the person. An extension of this system to a multi-user game is currently being considered.