Open AccessPredictive multi‐view content buffering applied to interactive streaming system
Author(s) -
Costa T.S.,
Andrade M.T.,
Viana P.
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2019.0713
Subject(s) - computer science , quality of experience , adaptation (eye) , focus (optics) , encoding (memory) , multimedia , quality (philosophy) , human–computer interaction , real time computing , machine learning , artificial intelligence , computer network , quality of service , philosophy , physics , epistemology , optics
This Letter discusses the benefits of introducing Machine Learning techniques in multi‐view streaming applications. Widespread use of machine learning techniques has contributed to significant gains in numerous scientific and industry fields. Nonetheless, these have not yet been specifically applied to adaptive interactive multimedia streaming systems where, typically, the encoding bit rate is adapted based on resources availability, targeting the efficient use of network resources whilst offering the best possible user quality of experience (QoE). Intrinsic user data could be coupled with such existing quality adaptation mechanisms to derive better results, driven also by the preferences of the user. Head‐tracking data, captured from camera feeds available at the user side, is an example of such data to which Recurrent Attention Models could be applied to accurately predict the focus of attention of users within videos frames. Information obtained from such models could be used to assist a preemptive buffering approach of specific viewing angles, contributing to the joint goal of maximising QoE. Based on these assumptions, a research line is presented, focusing on obtaining better QoE in an already existing multi‐view streaming system