中国邮电高校学报(英文版) ›› 2016, Vol. 23 ›› Issue (4): 77-82.doi: 10.1016/S1005-8885(16)60048-1

• Others • 上一篇    下一篇

Reduced frame set on wireless distorted video for quality assessment

邵华,温向明,路兆铭,陈亚文,陆镜宇   

  1. 北京邮电大学
  • 收稿日期:2016-05-05 修回日期:2016-07-08 出版日期:2016-08-30 发布日期:2016-08-30
  • 通讯作者: 邵华 E-mail:sarathy@bupt.edu.cn

Reduced frame set on wireless distorted video for quality assessment

  • Received:2016-05-05 Revised:2016-07-08 Online:2016-08-30 Published:2016-08-30
  • Contact: shao hua E-mail:sarathy@bupt.edu.cn

摘要: Objective video quality assessment methods often evaluate all the frames regardless of their importance. For wireless distorted videos, not every frame has the same contribution to the final overall quality due to the channel fading and interference, which may lead to the capacity variation in temporal. Besides, with the content similarity and error propagation pattern in temporal domain, it is possible to evaluate the overall quality with only part of the frames. In this paper, a demonstration is performed to show that the video quality can be evaluated with reduced frames set (RFS), and a state transition model is proposed to extract the RFS. At last, a video quality assessment (VQA) method is carried out based on RFS. Compared with several state-of-the-art methods, our method can achieve a suitable accuracy with less frames to be processed.

关键词: VQA, wireless distortion, quality of experience

Abstract: Objective video quality assessment methods often evaluate all the frames regardless of their importance. For wireless distorted videos, not every frame has the same contribution to the final overall quality due to the channel fading and interference, which may lead to the capacity variation in temporal. Besides, with the content similarity and error propagation pattern in temporal domain, it is possible to evaluate the overall quality with only part of the frames. In this paper, a demonstration is performed to show that the video quality can be evaluated with reduced frames set (RFS), and a state transition model is proposed to extract the RFS. At last, a video quality assessment (VQA) method is carried out based on RFS. Compared with several state-of-the-art methods, our method can achieve a suitable accuracy with less frames to be processed.

Key words: VQA, wireless distortion, quality of experience