Super-resolution with perceptual quality for improved live streaming delivery on edge computing

Abstract

According to Cisco projections, mobile connection throughput is anticipated to more than triple by the year 2023, with the expected typical 5G connection throughput reaching 575 Mbps. Additionally, smartphones and TV sets equipped with computational capabilities for decoding 4K videos have significantly redefined the landscape of Internet video traffic, accounting for 82% of the total Internet traffic. This surge in connection throughput, coupled with the escalating demand for video-centric content, presents an unprecedented challenge in effectively managing traffic across the backhaul infrastructure of 5G networks. In this article, we introduce and evaluate the On-edge enhanced live streaming with super-resolution (ELiveSR) framework for live video delivery, which takes advantage of throughput improvements, in the access networks, and makes use of real-time super-resolution procedure to reduce transmission rate demands in the backhaul segment of the network. This SR procedure is carried by a deep neural network based model and is capable of coping with video content of different subjects. Experimental assessments conducted revealed that the proposed framework can reduce video-related traffic in the backhaul segment by up to 88.37%. Additionally, it simultaneously enhances the quality of experience metrics observed during live video streaming sessions.