Applicability of Existing Objective Metrics of Perceptual Quality for Adaptive Video Streaming

Jacob Søgaard (1) , Lukáš Krasula (2, 3) , Muhammad Shahid (4) , Dogancan Temel (5) , Kjell Brunnström (6, 7) , Manzoor Razaak (8)

1 Department of Photonics
2 IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes
3 CTU - Czech Technical University in Prague
4 Blekinge Institute of Technology, School of Computing, School of Health
5 Georgia Institute of Technology [Atlanta]
6 Acreo AB
7 Mid Sweden University
8 Faculty of Science, Engineering and Computing, Kingston University

Objective video quality metrics are designed to estimate the quality of experience of the end user. However, these objective metrics are usually validated with video streams degraded under common distortion types. In the presented work, we analyze the performance of published and known full-reference and no-reference quality metrics in estimating the perceived quality of adaptive bit-rate video streams knowingly out of scope. Experimental results indicate not surprisingly that state of the art objective quality metrics overlook the perceived degradations in the adaptive video streams and perform poorly in estimating the subjective quality results.

Domains: Signal and Image Processing; Multimedia [cs.MM]

Jacob Søgaard, Lukáš Krasula, Muhammad Shahid, Dogancan Temel, Kjell Brunnström, et al.. Applicability of Existing Objective Metrics of Perceptual Quality for Adaptive Video Streaming. Electronic Imaging, Image Quality and System Performance XIII, Feb 2016, San Francisco, CA, United States. ⟨hal-01395510⟩