计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (36): 185-188.

• 数据库与信息处理 • 上一篇    下一篇

基于Rough Set的镜头分割方法

韩加亮1,吴 渝1,林玉宝2   

  1. 1.重庆邮电大学 人工智能研究所,重庆 400065
    2.燕山大学 信息科学与工程学院,河北 秦皇岛 066004
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-21 发布日期:2007-12-21
  • 通讯作者: 韩加亮

Shot boundary detection based on Rough Set

HAN Jia-liang1,WU Yu1,LIN Yu-bao2   

  1. 1.Institute of Artificial Intelligence,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
    2.College of Information Science and Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-21 Published:2007-12-21
  • Contact: HAN Jia-liang

摘要: 综合利用了MPEG视频流P帧的运动特征、像素差和直方图差特征,提出了一种基于Rough Set的镜头分割方法。该方法首先提取视频流中P帧的宏块信息,然后分析得到其运动活力性、宏块类型和运动空间分布,再结合这些帧的像素差特征和直方图差特征,利用Rough Set对这些特征进行约减后,对镜头切换处进行识别。实验表明,该方法能有效地区分镜头的突变,对渐变也能很好地检测。

关键词: Rough Set, 运动信息, 突变, 渐变

Abstract: An approach to shot boundary detection by Rough Set is introduced which comprehensively utilizes the motion features of P frame in MPEG video sequence,the difference of pixel and the difference of histogram.First,some information of macro blocks is extracted in P frame of MPEG video sequence.Then the information analyzed and the motion-activity,the type of macro blocks and the motion-distribution are gotten.Combined these parameters with the difference of pixel and the difference of histogram the shot-boundary detection can be achieved according to the Rough Set after being reduced.Experimental results show that it can effectively distinguish the hard cut and gradual transition.

Key words: Rough Set, motion information, hard cut, gradual transition