A real-time video quality estimator for emerging wireless multimedia systems

Abstract

Wireless Mesh Networks (WMNs) are increasingly deployed to enable thousands of users to share, create, and access live video streaming with different characteristics and content, such as video surveillance and football matches. In this context, there is a need for new mechanisms for assessing the quality level of videos because operators are seeking to control their delivery process and optimize their network resources, while increasing the user's satisfaction. However, the development of in-service and non-intrusive Quality of Experience assessment schemes for real-time Internet videos with different complexity and motion levels, Group of Picture lengths, and characteristics, remains a significant challenge. To address this issue, this article proposes a nonintrusive parametric real-time video quality estimator, called MultiQoE that correlates wireless networks' impairments, videos' characteristics, and users' perception into a predicted Mean Opinion Score. An instance of MultiQoE was implemented in WMNs and performance evaluation results demonstrate the efficiency and accuracy of MultiQoE in predicting the user's perception of live video streaming services when compared to subjective, objective, and well-known parametric solutions.

Beacon-less video streaming management for VANETs based on QoE and link-quality

“…The routing decisions must adapt to topology changes and be aware of QoE requirements to recover or maintain the video flows with at least a good quality level for humans. Thus, the route decision process for video packets must be done not only based on networking and vehicle parameters, such as loss and position, but also based on application parameters, e.g., frame importance of the videos and the impact of that on the human perception [2].…”

A hybrid prediction model for video quality by QoS/QoE mapping in wireless streaming

“…In this work, both QoS and QoE parameters were used as input parameters to estimate the overall QoE of a user as output, but real-time QoE estimation was not studied. However, a real-time estimator was proposed by Aguiar et al [20], which utilized Multiple Artificial Neural Network (MANN) as a prediction engine for Abstract Wireless Mesh Networks (WMNs). The selected QoS parameters on application layer covered group of pictures (GoP) but not bitrate or QP, and one spatial resolution only.…”

QoE-aware dynamic virtual network resource adaptation for EaaS environment

“…As a consequence, in the past years, the multimedia content accessed has increased exponentially (video streams download, videoconferencing, or even broadcasting their own video streams to the Internet) [1]. This is due to the fact that multimedia services over wireless networks are becoming part of our lives, allowing new video sharing experiences for millions of people across the world.…”