An Augmented Autoregressive Approach to HTTP Video Stream Quality Prediction

2017/07/10 by Christos G. Bampis, Alan C. Bovik, Bampis, Christos G. +1
Computer Science · Social Sciences · #Advanced Data Compression Techniques #FOS: Computer and information sciences #Image and Video Quality Assessment #Multimedia (cs.MM) #Multimedia Communication and Technology

paper · pdf · doi:10.48550/arxiv.1707.02709

openalex publication_date 2017/07/10 · openalex created_date 2017/07/21 · openalex updated_date 2026/07/28

Abstract

HTTP-based video streaming technologies allow for flexible rate selection strategies that account for time-varying network conditions. Such rate changes may adversely affect the user's Quality of Experience; hence online prediction of the time varying subjective quality can lead to perceptually optimised bitrate allocation policies. Recent studies have proposed to use dynamic network approaches for continuous-time prediction; yet they do not consider multiple video quality models as inputs nor consider forecasting ensembles. Here we address the problem of predicting continuous-time subjective quality using multiple inputs fed to a non-linear autoregressive network. By considering multiple network configurations and by applying simple averaging forecasting techniques, we are able to considerably improve prediction performance and decrease forecasting errors.

Citations

• Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
• Image information and visual quality
• Making a “Completely Blind” Image Quality Analyzer

Related

• Low-Delay Adaptive Video Streaming Based on Short-Term TCP Throughput Prediction
• A real-time blind quality-of-experience assessment metric for HTTP adaptive streaming
• Cumulative Quality Modeling for HTTP Adaptive Streaming
• A Brief Survey on Adaptive Video Streaming Quality Assessment
• Streaming Video QoE Modeling and Prediction: A Long Short-Term Memory\n Approach