中国邮电高校学报(英文) ›› 2018, Vol. 25 ›› Issue (1): 70-77.doi: 10.19682/j.cnki.1005-8885.2018.0008

• Artificial Intelligence • 上一篇    下一篇

Network video quality assessment based on fuzzy inference system

史志明,黄诚惕   

  1. 华侨大学
  • 收稿日期:2017-08-08 修回日期:2018-01-14 出版日期:2018-02-28 发布日期:2018-02-28
  • 通讯作者: 史志明 E-mail:szmi_2007@126.com

Network video quality assessment based on fuzzy inference system

  • Received:2017-08-08 Revised:2018-01-14 Online:2018-02-28 Published:2018-02-28

摘要: The objective assessment method of network video quality is a challenge, because the video quality will be distorted by various factors, including transmission and compression. In order to improve the objective method, an objective assessment method based on fuzzy inference system of Mamdani is proposed. Firstly, six quality parameters are introduced. All the quality parameters are inputted to fuzzy logic controller system. Secondly, the outputs are used as next inputs and inferred by another fuzzy logic controller system to obtain the objective quality of network video. Lastly, the performance of proposed method is validated on four videos with different network environment. Meanwhile this method is compared with other methods. The experimental results show that the proposed method can improve the similarity between subjective and objective assessment.

关键词: network video, quality parameter, fuzzy inference system, objective assessment

Abstract: Nowadays, network video is widely deployed everywhere. But the objective quality assessment of network video is a challenge, because it will be distorted by various factors, including transmission and compression. This paper proposes a new objective assessment methodology based on fuzzy inference system of Mamdani. Firstly six quality parameters [initial buffering time (Tinit), mean re-buffering duration (Trebuf), re-buffering frequency (Frebuf), Noise standard deviation (Nsd), Blur degree (Bd), and Block effect (Be)] are introduced, and they are all used as input for the fuzzy logic controller system. Secondly, the outputs are used as inputs to another fuzzy logic controller system to obtain the objective quality of network video. Lastly the proposed method is tested on four videos under different network environment and compared with other methods. The experimental results show that the proposed method can improve the similarity between subjective and objective assessment.

Key words: network video, quality parameter, fuzzy inference system, objective quality assessment