采用模糊控制的网络视频质量评估方法  

Network Video Quality Assessment Method Using Fuzzy Control

作　　者：史志明 黄诚惕[1,2] SHI Zhi-ming;HUANG Cheng-ti(College of Engineering, Huaqiao University, Quanzhou, Fujian 362021, China;Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems,Huaqiao University, Quanzhou, Fujian 362021, China)

机构地区：[1]华侨大学工学院,福建泉州362021 [2]<工业智能化技术与系统>福建省高校工程研究中心华侨大学,福建泉州362021

出　　处：《信号处理》2019年第1期115-124,共10页Journal of Signal Processing

基　　金：福建省教育厅中青年教师教育科研项目(JAT160032);泉州市科技计划项目(2018C106R);华侨大学高层次人才引进项目(600005-Z14Y0041)

摘　　要：随着宽带通信技术的快速发展,网络视频业务迅猛普及。尽管人们可以方便收看网络视频,但是由于网络视频在传输过程中,会受到各种因素干扰,降低用户感受。本文针对网络视频质量评估问题,提出一种采用模糊控制的评估方法。首先分析了影响视频质量的网络、应用、图像等主要指标;通过仿真实验提取了不同情况下的影响指标,构造了三层模糊控制的评估模型;为了进一步提高方法的准确性,对每个模糊层赋予了不同权值,同时给出了两种去模糊化方法。该方法综合考虑了不同影响因素,适用性广,且具有较好的实用性。实验结果表明,该算法能够有效地提高视频质量评估的主客观相似度。With the rapid development of broadband communication technology, the service of network video was popular anywhere. Although people can watch network video conveniently, network video quality may be impaired by various factors during the transmission process, leading to the quality of experience (QoE) decrease. In order to solve the problem of network video quality assessment, an assessment method using fuzzy control was proposed in this paper. Firstly the main impair indexes of video quality were analyzed,such as network, application and image indexes;secondly these indexes were extracted by simulation experiments under different environment, next three levels fuzzy control of assessment model was built;to further improve the accuracy of this method, every fuzzy level was given different weight, and two kinds of de-fuzzification methods were given. This method considered different factors, and had wide applicability and good practicability. Experimental results show that the proposed method can improve the similarity between the subjective and objective better.

关 键 词：网络视频质量 用户感受 模糊控制 影响指标 相似度 

分 类 号：TN911.22[电子电信—通信与信息系统]