Peer-to-peer multipoint video conferencing using layered video

A new peer-to-peer architecture for multipoint video conferencing that targets end points with low bandwidth network connections (single video in and out) is presented. It enables end points to create a multipoint conference without any additional networking and computing resources than what is needed for a point-to-point conference. The new architecture is based on layered video coding with two layers at the end points. It allows each conference participant to see any other participant at any given time under all multipoint configurations of any number of users, with a caveat that some participants may have to receive only the base layer video. Layered encoding techniques usable within this architecture are described. A protocol for implementation of the new approach has been developed and simulated. Its performance is analyzed.