A Framework to Measure and Estimate Video Quality in SVC Real-Time Adaptive Systems

Abstract

Effectively adapting the content to network conditions in real-time is an important matter in best-effort networks like the Internet. Scalable Video Coding (SVC) is an interesting alternative to implement such systems. However, some problems of the performance evaluation of SVC based adaptive systems have not been solved. The authors review the main efforts directed to measure video quality on SVC related systems and discuss the limitations of each one. This paper elaborates a framework to measure video quality metrics in real adaptive SVC based streams. An estimation method for full reference video quality metrics is proposed. This method reduces reference information required and it is able to provide real-time accurate results simply using metadata regarding the video quality of the reference layers. The video quality of several streams that have been generated using a real-time adaptive system is first measured with the elaborated framework and then estimated with the proposed method.