Quality of Experience of Web-based Adaptive HTTP Streaming Clients in Real-World Environments using Crowdsourcing

Multimedia streaming over HTTP has gained momentum with the approval of the MPEG-DASH standard and many research papers evaluated various aspects thereof but mainly within controlled environments. However, the actual behaviour of a DASH client within real-world environments has not yet been evaluated. The aim of this paper is to compare the QoE performance of existing DASH-based Web clients within real-world environments using crowdsourcing. Therefore, we select Google's YouTube player and two open source implementations of the MPEG-DASH standard, namely the DASH-JS from Alpen-Adria-Universitaet Klagenfurt and the dash.js which is the official reference client of the DASH Industry Forum. Based on a predefined content configuration, which is comparable among the clients, we run a crowdsourcing campaign to determine the QoE of each implementation in order to determine the current state-of-the-art for MPEG-DASH systems within real-world environments. The gathered data and its analysis will be presented in the paper. It provides insights with respect to the QoE performance of current Web-based adaptive HTTP streaming systems.