期刊文献+

逐步求准的视频镜头聚类算法 被引量:1

Stepwise Precise Clustering Algorithm for Video Shots
下载PDF
导出
摘要 提出一种有效的逐步求准的视频镜头聚类算法(SPC).该算法并不是直接处理视频数据的底层高维特征向量,而是先把这些高维特征向量通过小波变换转换到Haar小波系数空间中,然后利用多分辨率分析技术实现逐步求准聚类结果的目的.算法的每一步求准过程都属于层次聚类过程,它利用了一种巧妙的停止准则来使算法中的合并聚类过程结束.该算法解决了以往镜头聚类算法中存在的聚类中心选取问题以及需要给出相关领域经验参数问题的同时,还能够自动的进行聚类个数的估计.理论分析和大量的实验结果表明,该算法是一种非常有效的视频镜头聚类算法. This article proposes an efficient stepwise precise clustering algorithm for video shots (SPC). Instead of working on the low-level feature vectors of video shots, the algorithm works in the Haar wavelet coefficients space by wavelet transformation and utilizes the technology of multi-resolution analysis of wavelet to achieve the goal of getting stepwise precise clustering results. Each iteration of the algorithm is a hierarchical clustering processes, and the iterative merging processes do not stop until a novel stop criterion is satisfied. This algorithm solves the problem of choosing proper cluster centers which is a dilemma of most existing shot clustering algorithms, does not need any parameters to give beforehand and estimates the number of clus- ters automatically. The theoretical analysis and experimental results witness that SPC is an efficient shot clustering algorithm.
出处 《小型微型计算机系统》 CSCD 北大核心 2008年第7期1272-1276,共5页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(60273079 60573089)资助 国家重大基础研究计划"九七三"项目(2006CB303103)资助
关键词 HAAR小波变换 多分辨率分析 层次聚类 Haar wavelet transformation multi-resolution analysis hierarchy clustering algorithm
  • 引文网络
  • 相关文献

参考文献10

  • 1Shen H T, Ooi B C, Zhou X F. Towards effective indexing for very large video sequence database [C].Proceedings of ACM SIGMOD Int. Conf. on Management of Data, 2005,730-741.
  • 2Ngo C W, Pong T C, Zhang H J. On clustering and retrieval of video shots through temporal slices analysis[C].IEEE Transactions on Multimedia, 2002,4 (4) : 446-458.
  • 3Bertini M, Bimbo A D, Cucchiara R,et al. Semantic video adaptation based on automatic annotation of sport videos[C].Proceedings of ACM SIGMM Int. Workshop on Multimedia Information Retrieval, 2004,291-298.
  • 4Gonzalez R C, Woods R E. Digital image processing second edition[M].Pearson Education, USA, 2002.
  • 5Hanjalic A, Zhang H. An integrated scheme for automated video abstraction based on unsupervised cluster-valldity analysis[C]. IEEE Transactions on Circuits and Systems for Video Technology, 1999, 9(8):1280-1289.
  • 6Yeung M, Yeo B L, Liu B. Extracting story units from long programs for video browsing and navigateon[C]. Proceedings of IEEE Conf. on Multimedia Computing and System, 1996,296- 305.
  • 7Jain A K, Murty M N, Flynn P J. Data clustering: a review [J]. ACM Computing Surveys, 1999, 31(3):264-323.
  • 8Pelleg D, Moore A W. X-means: extending k-means with efficient estimation of the number of clusters[C].Proceedings of Int. Conf. on Machine Learning, 2000,727-734.
  • 9Zhu X Q, Fan J P, Elmagarmid A K, et al. Hierarchical video content description and summarization using unified semantic and visual similarity[J]. Journal of Multimedia Systems, 2003, 9(1) :1432-1882.
  • 10Ngo C W, Pong T C, Zhang H J. On clustering and retrieval of video shots[C]. Proceedings of ACM Multimedia Workshops, 2001,51-60.

同被引文献9

  • 1SHEN H T, OOI B C, ZHOU X F. Towards Effective Indexing for very Large Video Sequence Database [ C ]//Proceedings of ACM SIGMOD Int. Conf. on Management of Data, 2005.
  • 2WANG Peng, CAI Rui, YANG ShiQiang. Improving Classification of Video Shots Using Information-theoretic co-clustering: Circuits and Systems [ C ]//ISCAS 2005, IEEE International Symposium on Beijing,2005:964 - 967.
  • 3HANJALIC A, ZHANG Hong-Jiang. An Integrated Scheme for Automated Video Abstraction Based on Unsupervised Cluster-va- lidity Analysis[ C]//IEEE Transactions on Circuits and Systems for Video Technology, Netherlands, 1999 : 1280 - 1289.
  • 4BOTTOU L, BENGIO Y. Convergence Properties of the K-means algorithm[ C ] // Advances in Neural Infor-mation Proeessing Sys- tems 7 Cambridge, America, MIT Press, 1995:585 - 592.
  • 5LI Jinjiang, FAN Hui, YUAN Da, et al. Kernel Function Cluste- ring Based on Ant Colony Algorithm [ C ] //Fourth International Conference on Natural Computation, IEEE 2008 Jinan, 2008:645 -649.
  • 6ZHANG Zhenya, CHENG Hongmei, CHEN Wanli, et al. Corre- lation Clustering Based on Genetic Algorithm for Documents Clus- tering[ C ] //2008 IEEE Congress on Evolutionary Computation Heifei ,2008:3193 - 3198.
  • 7RICHARD Fabera. Dynamic Optimization with Simulated Annea- ling [ J ]. Computers and Chemical Engineering, 2005,29 ( 2 ) : 273 - 290.
  • 8蔺旭东,曾晓宁,薄静仪.一种基于支持向量的镜头聚类算法[J].计算机应用,2007,27(9):2143-2146. 被引量:1
  • 9刘伟民,郑爱云,李苏剑,赵方庚,孙江生.模拟退火K均值聚类算法及其应用研究[J].微计算机信息,2008,24(21):182-184. 被引量:12

引证文献1

二级引证文献3

;
使用帮助 返回顶部