华南理工大学学报(自然科学版) ›› 2013, Vol. 41 ›› Issue (9): 28-33.doi: 10.3969/j.issn.1000-565X.2013.09.005

• 电子、通信与自动控制 • 上一篇    下一篇

用于视频质量包层评估模型的帧类型检测方法

苏洪磊 李兵兵 杨付正   

  1. 西安电子科技大学 综合业务网理论及关键技术国家重点实验室,陕西 西安 710071
  • 收稿日期:2013-02-28 修回日期:2013-06-22 出版日期:2013-09-25 发布日期:2013-08-01
  • 通信作者: 杨付正(1977-),男,教授,主要从事视频压缩、视频质量评估研究. E-mail:fzhyang@mail.xidian.edu.cn
  • 作者简介:苏洪磊(1986-),男,博士生,主要从事视频质量评估研究.E-mail:hlsu@mail.xidian.edu.cn
  • 基金资助:

    国家自然科学基金资助项目(60902081, 60902052);高等学校学科创新引智计划项目(B08038)

Frame Type Detection Method for Packet- Layer Model of Video Quality Assessment

Su Hong- lei Li Bing- bing Yang Fu- zheng   

  1. State Key Laboratory of Integrated Services Networks,Xidian University,Xi’ an 710071,Shaanxi,China
  • Received:2013-02-28 Revised:2013-06-22 Online:2013-09-25 Published:2013-08-01
  • Contact: 杨付正(1977-),男,教授,主要从事视频压缩、视频质量评估研究. E-mail:fzhyang@mail.xidian.edu.cn
  • About author:苏洪磊(1986-),男,博士生,主要从事视频质量评估研究.E-mail:hlsu@mail.xidian.edu.cn
  • Supported by:

    国家自然科学基金资助项目(60902081, 60902052);高等学校学科创新引智计划项目(B08038)

摘要: 为提高视频质量包层评估模型的性能,提出了一种用于该模型的帧类型检测方法,该方法仅使用视频数据包头信息而无需对视频流进行解码.首先根据不同类型视频帧的特点,统计出不同类型视频帧的压缩数据量的规律,利用动态阈值法对滑动窗口内的每帧进行初步的帧类型估计; 然后利用图像组的周期性对上一步估计的结果进行修正; 最后应用Spearman 秩相关系数判定B 帧的预测结构.实验结果表明,与仅使用动态阈值的方法相比,该帧类型检测方法的平均准确率提高了20.04%

关键词: 网络视频, 帧类型检测, 包层模型, 视频质量评估

Abstract:

In order to improve the performance of the packet- layer quality assessment model of networked video,a frame type detection method without any help of video decoding is proposed only by using the information extracted from the packet header of the video stream.In this method,first,the statistical law of the compressed data of each type of frame is obtained according to the characteristics of different types of frames.Next,the dynamic threshold method is employed to preliminarily estimate the type of each frame in a sliding window.Then,the preliminary estimation results are modified based on the periodicity of group of pictures.Finally,the prediction structures of B- frames are determined by using the Spearman’ s rank correlation coefficient.Experimental results show that,as compared with the method based only on dynamic thresholds,the proposed method achieves a detection accuracy increment of about 20.04%.

Key words: networked video, frame type detection, packet- layer model, video quality assessment