Video quality estimator for wireless mesh networks

Abstract

As Wireless Mesh Networks (WMNs) have been increasingly deployed, where users can share, create and access videos with different characteristics, the need for new quality estimator mechanisms has become important because operators want to control the quality of video delivery and optimize their network resources, while increasing the user satisfaction. However, the development of in-service Quality of Experience (QoE) estimation schemes for Internet videos (e.g., real-time streaming and gaming) with different complexities, motions, Group of Picture (GoP) sizes and contents remains a significant challenge and is crucial for the success of wireless multimedia systems. To address this challenge, we propose a real-time quality estimator approach, HyQoE, for real-time multimedia applications. The performance evaluation in a WMN scenario demonstrates the high accuracy of HyQoE in estimating the Mean Opinion Score (MOS). Moreover, the results highlight the lack of performance of the well-known objective methods and the Pseudo-Subjective Quality Assessment (PSQA) approach.Index Terms-Multimedia, wireless networks, video streaming, quality of experience, video quality prediction, random neural networks, wireless mesh networks.

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

“…This article extends our previous work [11] with a modular and parametric packet-layer wireless video quality estimator, called MultiQoE. MultiQoE uses IP and MPEG packet header information to predict the quality level of a variety of videos (different genres and content), which reduces the system complexity and processing.…”

A distributed beaconless routing protocol for real-time video dissemination in multimedia VANETs

“…As presented in [5], it is important to have MOS experiments to really understand the video quality level from according to the human perception. The correlation between the PSNR and SSIM results and MOS scores does not have a high accuracy.…”

“…With the same principle, the video is then forwarded from the source to the requester (yellow message). Our proposal can also be easily supported together with VANET ICN (Information Centric Networking) systems [5], where an event is announced and the requesting nodes ask for the content (Interest video flows).…”

“…The perception of videos shared and watched by humans, characterized in terms of Quality of Experience (QoE), is directly measured by the acceptability of the users and is related to, but differs from the extensively studied concept Quality of Service (QoS) [5]. QoS-based approaches and metrics, such as the ones based on link/network-related parameters (packet loss, packet delay, and/ or Received Signal Strength Indicator (RSSI)) fail to capture subjective aspects of video content related to human visual system as expected for human-centric environments.…”

More than I ever wanted or just good enough? User expectations and subjective quality perception in the context of networked multimedia services

“…Table 6 provides an overview of the involved user studies. In general, there are several ways to generate quantitative QoS/QoE-models, e.g., via machine learning techniques like decision trees (Menkovski et al 2009) or neuronal networks (Aguiar et al 2012). It is also common to gain less complex solutions to describe the relationship between technical and perceived quality, e.g., curve fitting like discussed in Sackl et al (2013).…”