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。
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.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第36期185-188,共4页
Computer Engineering and Applications
基金
重庆市自然科学基金(the Natural Science Foundation of Chongqing of China under Grant No.2005BB2063)
国家教育部新世纪人才支持计划(the New Century Excellent Talent Foundation from MOE of China under Grant)
重庆市教委科学技术项目(No.050509
No.060517)
关键词
ROUGH
SET
运动信息
突变
渐变
Rough Set
motion information
hard cut
gradual transition
