Research Article
Content classification-based and QoE-driven video send bitrate adaptation scheme
@INPROCEEDINGS{10.4108/ICST.MOBIMEDIA2009.7687, author={Asiya Khan and Lingfen Sun and Emmanuel Jammeh and Emmanuel Ifeachor}, title={Content classification-based and QoE-driven video send bitrate adaptation scheme}, proceedings={5th International Mobile Multimedia Communications Conference}, publisher={ICST}, proceedings_a={MOBIMEDIA}, year={2010}, month={5}, keywords={Content classification Video Send Bitrate (SBR) PSNR QoE.}, doi={10.4108/ICST.MOBIMEDIA2009.7687} }- Asiya Khan
Lingfen Sun
Emmanuel Jammeh
Emmanuel Ifeachor
Year: 2010
Content classification-based and QoE-driven video send bitrate adaptation scheme
MOBIMEDIA
ICST
DOI: 10.4108/ICST.MOBIMEDIA2009.7687
Abstract
Initial video quality requirement is not well understood and content providers usually send video at the highest send bitrate resulting in over-provisioning. The main aim of this paper is to present a new scheme that can adapt video send bitrate according to the dynamics of the content and the user's Quality of Experience (QoE) requirement at the pre-encoding stage. Contents are classified based on their spatio-temporal feature extraction. Video quality is predicted in terms of the Peak-Signal-to-Noise-Ratio (PSNR). Statistical analysis of the experimental results confirms that the proposed adaptation scheme performs well for all content types and hence, improves the perceived end-to-end video quality. The proposed scheme makes it possible for content providers to achieve an optimum streaming scheme (with an appropriate send bitrate) suitable for the content type for a requested QoE.