The Vision Television detects the faces of its viewers and can transmit them to other locations or incorporate them in the image, creating a community of viewers in different locations who can talk to one another as if they were in the same room. It can also use information gathered from the faces (number, location, attentiveness, expression, identity) to modify the presentation in some way.
The Vision Television is a distributed application written in the Isis programming langauge. It uses a standard neural network face detection system. Multiple faces can be tracked from multiple cameras at different sites in real time.
For more information, contact V Michael Bove, Jr. or Stefan Agamanolis.