一种改进的无监督聚类的关键帧提取算法

李全栋, 陈树越, 张微

李全栋, 陈树越, 张微. 一种改进的无监督聚类的关键帧提取算法[J]. 应用光学, 2010, 31(5): 741-744.
引用本文: 李全栋, 陈树越, 张微. 一种改进的无监督聚类的关键帧提取算法[J]. 应用光学, 2010, 31(5): 741-744.
LI Quan-dong, CHEN Shu-yue, ZHANG Wei. Improved algorithm for key frame extraction based on unsupervised clustering[J]. Journal of Applied Optics, 2010, 31(5): 741-744.
Citation: LI Quan-dong, CHEN Shu-yue, ZHANG Wei. Improved algorithm for key frame extraction based on unsupervised clustering[J]. Journal of Applied Optics, 2010, 31(5): 741-744.

一种改进的无监督聚类的关键帧提取算法

详细信息
    通讯作者:

    李全栋(1985-),男,浙江安吉人,硕士研究生,主要从事数字图像处理研究。

  • 中图分类号: TN911.73 ;TP391

Improved algorithm for key frame extraction based on unsupervised clustering

  • 摘要: 针对关键帧提取方法中一般聚类算法的阈值只能预先指定的缺陷,提出一种基于无监督聚类的自适应阈值改进算法。对视频帧进行区域分割并提取纹理特征,然后根据视频内容的复杂度自适应获取阈值,通过无监督聚类得到视频关键帧。大量不同视频类型的关键帧提取实验表明:该算法简单,无需预定义任何阈值便能有效地提取合适数目的关键帧。
    Abstract: Key frame extraction plays a very important role in content-based video retrieval. Since general clustering algorithm can only predefine a threshold in key frame extraction, this paper presents an improved method of adaptive threshold based on unsupervised clustering. The video frames texture feature is extracted based on regional segmentation. The adaptive threshold is determined by video content, and then the key frames are obtained through unsupervised clustering. This algorithm is simple and effective, it extracts key frames without predefined threshold. Experimental results of some videos with different traits demonstrate the good performance of the proposed algorithm.
  • [1]YANG Shu-ping, LIN Xing-gang. Key frame extra-ction using unsupervised clustering based on a stati-stical model[J]. Tsinghua Science and Technology, 2005,10(2):169-173.(in Chinese with an English abstract)
    [2]许文竹, 徐立鸿. 结合主成分分析和聚类的关键帧提取[J]. 计算机工程与应用, 2009,45(15):9-10.
    XU Wen-zhu,XU Li-hong. Combining principal components analysis and clustering to extract key frame[J].Computer Engineering and Applications,2009,45(15):9-10.(in Chinese with an English abstract)
    [3]杨鹏,裴继红,杨火亘. 基于不变矩和Mean Shift聚类的视频关键帧提取[J]. 计算机应用与软件,2009,26(2):238-241.
    YANG Peng,PEI Ji-hong,YANG Xuan. Video key frame extraction using invariant moment and Mean Shift clustering[J].Computer Applications and Software,2009,26(2):238-241. (in Chinese with an English abstract)
    [4]曹晋高.视频关键帧提取方法研究[D].重庆:重庆大学,2008.
    CAO Jin-gao. Study on method of video key frame extraction[D]. Chongqing: Chongqing University, 2008. (in Chinese)
    [5]ZHUANG Y, RUI Y, HANG T S. Adaptive key frame extraction using unsupervised clustering[J]. IEEE Int Conf on Image Processing,1998,1:866-870.
    [6]ANJULAN A, CANAGARAJAH N. Object based video retrieval with local region tracking[J]. Signal Processing: Image Communication, 2007,22:607-621.
    [7]王惠明, 史萍. 图像纹理特征的提取方法[J].中国传媒大学学报,2006,13(1):49-52.
    WANG Hui-ming, SHI Ping. Methods to extract images texture features[J].Journal of Communi-cation University of China,2006,13(1):49-52. (in Chinese with an English abstract)
    [8]王方石,须德,吴伟鑫.基于自适应阈值的自动提取关键帧的聚类算法[J]. 计算机研究与发展,2005,42(10):1752-1757.
    WANG Fang-shi, XU De, WU Wei-xin. A cluster algorithm of automatic key frame extraction based on adaptive threshold[J].2005,42(10):1752-1757. (in Chinese with an English abstract)
计量
  • 文章访问数:  2654
  • HTML全文浏览量:  124
  • PDF下载量:  998
  • 被引次数: 0
出版历程
  • 刊出日期:  2010-09-14

目录

    /

    返回文章
    返回