Dimensionality Reduction for Distance Based Video Clustering

Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 339)


Clustering of video sequences is essential in order to perform video summarization. Because of the high spatial and temporal dimensions of the video data, dimensionality reduction becomes imperative before performing Euclidean distance based clustering. In this paper, we present non-adaptive dimensionality reduction approaches using random projections on the video data. Assuming the data to be a realization from a mixture of Gaussian distributions allows for further reduction in dimensionality using random projections. The performance and computational complexity of the K-means and the K-hyperline clustering algorithms are evaluated with the reduced dimensional data. Results show that random projections with an assumption of Gaussian mixtures provides the smallest number of dimensions, which leads to very low computational complexity in clustering.


Clustering Random projections Gaussian mixtures Video summarization 


  1. 1.
    Alpaydin, E.: Introduction to Machine Learning. In: Adaptive Computation and Machine Learning. The MIT Press, Cambridge (2004)Google Scholar
  2. 2.
    Kannan, R., Vempala, S.S.: Spectral Algorithms. In: Foundations and Trends in Theoretical Computer Science. Now Publishers Inc. (2009)Google Scholar
  3. 3.
    Vailaya, A., Jain, A.K., Zhang, H.: Video Clustering. Technical report, Michigan State University (1996)Google Scholar
  4. 4.
    Vempala, S.S.: The Random Projection Method. Discrete Mathematics and Theoretical Computer Science. American Mathematical Society, Providence (2004)zbMATHGoogle Scholar
  5. 5.
    He, Z., Cichoki, A., Li, Y., Xie, S., Sanei, S.: K-hyperline clustering learning for sparse component analysis. Signal Processing 89, 1011–1022 (2009)zbMATHCrossRefGoogle Scholar
  6. 6.
    Dasgupta, S.: Learning Mixtures of Gaussians. In: Proceedings of the 40th Annual Symposium on Foundations of Computer Science, Washington, DC, USA, pp. 634–644 (1999)Google Scholar
  7. 7.

Copyright information

© IFIP 2010

Authors and Affiliations

  1. 1.SenSIP Center, School of ECEEArizona State UniversityTempeUSA

Personalised recommendations