Abstract: Video as a fast-growing contributor to Internet traffic makes the ISP and video provider pay more attention to the Quality of Experience（QoE）. However, due to the complex process, it’s difficult to get QoE estimation during the video delivery in real time. In this paper, the network parameters are which experimentally analyzed influences video QoE, and an objective measurable QoE model between these parameters and video QoE is established. The model is simple in form, suitable for real-time monitoring. The results of experiments show the model can accurately and fast estimate video QoE.

Key words: video stream, quality of service, quality of experience, objective assessment, regression model

摘要： 网络视频业务的兴起使网络运营商和服务提供商更加关注视频的用户体验（QoE），然而视频用户体验（QoE）值由于其主观性且评价过程复杂，难以在视频流传输中实时获取。通过实验分析了视频传输过程中服务质量（QoS）参数变化对视频QoE的影响，建立了客观、可测量的QoS参数与视频QoE之间映射模型，用可量化的QoS参数来评定视频QoE受网络性能的影响程度，以评估网络视频质量，该模型形式简单，能够实时监测视频质量。实验结果表明，该模型的评价结果能较好反映视频QoE。

关键词: 视频流, 服务质量, 用户体验质量, 客观评价, 回归模型