Adaptive multi-view video streaming over P2P networks considering quality of experience

Abstract

Peer-to-peer (P2P) video streaming has recently drawn significant attention since P2P solutions offer scalability with increasing number of recipients. P2P streaming may be a feasible solution for multi-view video (MVV) delivery, which has significantly higher bandwidth requirements than the legacy 2D video. However, a practical P2P MVV service cannot be achieved without properly addressing the perceived quality of experience (QoE) of MVV. QoE is an important issue especially in adaptive video streaming in which the quality of the content varies to match the available channel capacity. In this study, we first evaluate the perceived quality of MVV, when various adaptation methods are adopted to scale MVV bitrate to a given rate, by using subjective tests. The results of these tests are used to identify the best rate adaptation method. Next, we propose a mesh-based P2P streaming architecture that employs rate adaptation according to the findings to deliver the best QoE under diverse network conditions. We implemented our protocols and ran experiments on PlanetLab testbed to evaluate the performance of our proposed solution. The experimental results validate that the proposed adaptation strategy ensures continuous play-out by prioritizing transmission of the base-layer and augments the video quality when additional bit rate is available.