Qualitative Monitoring of Video Quality of Experience

Abstract

Abstract-Real-time monitoring of multimedia Quality of Experience is a critical task for the providers of multimedia delivery services: from television broadcasters to IP content delivery networks or IPTV. For such scenarios, meaningful metrics are required which can generate useful information to the service providers that overcome the limitations of pure Quality of Service monitoring probes. However, most of objective multimedia quality estimators, aimed at modeling the Mean Opinion Score, are difficult to apply to massive quality monitoring. Thus we propose a lightweight and scalable monitoring architecture called Qualitative Experience Monitoring (QuEM), based on detecting identifiable impairment events such as the ones reported by the customers of those services. We also carried out a subjective assessment test to validate the approach and calibrate the metrics. Preliminary results of this test set support our approach.

Validation of a novel approach to subjective quality evaluation of conventional and 3D broadcasted video services

“…Obviously, this is not feasible, but it is clear that the subjective assessment tests designed to analyze these effects should emulate real viewing conditions. This way, the results obtained from the subjects will be representative of what they would perceive in their real-life experiences, and will help in the design of monitoring tools to automatically estimate the perceived quality [3].…”

“…Taking into account the most common degradations reported by the end users [10], and following with our previous studies [3][5], the impairments that have been simulated are described in Table I.…”

“…However, the development of this type of algorithms is still an open issue due to their limited performance, especially in the case of no-reference metrics [2], which, in fact, are the most interesting in broadcasting video services since they could be used for monitoring tasks [3]. Therefore, subjective assessment tests are still considered the most reliable way to evaluate the users' QoE, and they are an essential tool to measure the performance of the video distribution systems.…”

Rule-based combination of video quality metrics

“…In fact, the efficiency of the existing metrics depends mainly on the degradations that affect the video quality and the data that can be used to estimate it. Although, as a first approach, the work in this paper has been focused on the efficient use of standardized FR metrics, thanks to their verified high-performance, the concept could be also useful in the case of NR metrics, especially for developing efficient architectures for video quality monitoring [19].…”

Analysis of quality of experience in 3D video systems

“…), the design principles of this methodology make it very useful to help in the design of monitoring tools to automatically estimate the perceived quality [140], especially the use of realistic long sequences divided into segments that could correspond to monitoring windows used in this type of mechanisms.…”