Quality of experience (QoE) in multimedia traffic has been the focus of extensive research in the last decade. The estimation of the QoE provides valuable input in order to measure the user satisfaction of a particular service. QoE estimation is challenging as it tries to measure a subjective metric where the user experience depends on a number of factors that cannot simply be measured. In this work, we present a methodology and a system based on fuzzy expert system to estimate the impact of network conditions (QoS) on the QoE of video traffic. At first, we conducted subjective tests to correlate network QoS metrics with participants' perceived QoE of video traffic. Second, we propose a No Reference method based on fuzzy expert system to estimate the network impact on the video QoE. The membership functions of the proposed fuzzy system are derived from normalized probability distributions correlating the QoS metrics with QoE. We propose a simple methodology to build the fuzzy inference rules. We evaluated our system in two different sets of experiments. The estimated video quality showed high correlation with the subjective QoE obtained from the participants in a controlled test. We integrated our system as part of a monitoring tool in an industrial IPTV test bed and compared its output with standard Video Quality Monitoring (VQM). The evaluation results show that the proposed video quality estimation method based on fuzzy expert system can effectively measure the network impact on the QoE.

Video quality measurement is an important component in the end-to-end video delivery chain. Video quality is, however, subjective, and thus, there will always be interobserver differences in the subjective opinion about the visual quality of the same video. Despite this, most existing works on objective quality measurement typically focus only on predicting a single score and evaluate their prediction accuracies based on how close it is to the mean opinion scores (or similar average based ratings). Clearly, such an approach ignores the underlying diversities in the subjective scoring process and, as a result, does not allow further analysis on how reliable the objective prediction is in terms of subjective variability. Consequently, the aim of this paper is to analyze this issue and present a machine-learning based solution to address it. We demonstrate the utility of our ideas by considering the practical scenario of video broadcast transmissions with focus on digital terrestrial television (DTT) and proposing a no-reference objective video quality estimator for such application. We conducted meaningful verification studies on different video content (including video clips recorded from real DTT broadcast transmissions) in order to verify the performance of the proposed solution.Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 01/02/2016 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Accuracy (in general) Higher than RR and NR. Higher than NR; lower than FR. Lower than FR and RR.

No abstract

No abstract