Introduction to the Special Issue on Measuring Quality of Experience for Advanced Media Technologies and Services
This publication appears in: IEEE Journal of Selected Topics in Signal Processing
Authors: S. Winkler Winkler, C. Wen Chen, A. Raake, P. Schelkens and L. Skorin-Kapov
Publication Date: Feb. 2017
QUALITY of Experience (QoE) has been defined as the degree of delight or annoyance of a person experiencing an application, service, or system. It results from the fulfillment of his or her expectations with respect to the utility and/or enjoyment of the application, service or system in the light of the persons personality and current state. (Qualinet White Paper on Definitions of Quality of Experience P. Le Callet, S. Moller, and A. Perkis, eds. version 1.2, March 2013). This implies that QoE assessment methods must take into account not only sys- tem performance parameters and content quality metrics, but also notions such as user perception, satisfaction, expectations, and context. Recent objective metrics for multimedia quality make use of natural image statistics, machine learning, distortion modeling, to name a few approaches. There is also a strong link to quality issues in communications and networking, as exemplified by recent work on QoE modeling and monitoring solutions for adaptive streaming.
Progress in technology has led to a stunning increase in the quality of multimedia content over the past few decades. Ultra- HD or 3D displays have become affordable nowadays, and high- definition streaming is quickly replacing conventional media libraries at home as well as on mobile devices. At the same time, quality considerations have become a lot more intricate, because of the added complexities in content generation, processing, distribution, and display. New developments in areas such as computational imaging or spatial sound reproduction keep adding to the list of challenges in quality measurement. Quality assessment now goes beyond a technical notion of quality to more holistically addressing QoE in terms of context- and user-awareness. In lab, crowdsourcing, or field tests, re- searchers collect ground-truth data that not only reflect QoE in terms of rating opinion, but also include the users emotional response, physical state, and behavior.
The 16 papers in this special issue cover a wide range of topics, including subjective QoE assessment, quality of stereoscopic video and other immersive experiences, video streaming, and machine learning for QoE.