Multicamera Video Summarization from Optimal Reconstruction

  • Carter De Leo
  • B. S. Manjunath
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6468)


We propose a principled approach to video summarization using optimal reconstruction as a metric to guide the creation of the summary output. The spatio-temporal video patches included in the summary are viewed as observations about the local motion of the original input video and are chosen to minimize the reconstruction error of the missing observations under a set of learned predictive models. The method is demonstrated using fixed-viewpoint video sequences and shown to generalize to multiple camera systems with disjoint views, which can share activity already summarized in one view to inform the summary of another. The results show that this approach can significantly reduce or even eliminate the inclusion of patches in the summary that contain activities from the video that are already expected based on other summary patches, leading to a more concise output.


Spectral Cluster Camera View Input Video Video Summarization Bike Path 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wang, X., Tieu, K., Grimson, W.: Correspondence-free activity analysis and scene modeling in multiple camera views. PAMI (2009)Google Scholar
  2. 2.
    Wang, X., Ma, K., Ng, G., Grimson, W.: Trajectory analysis and semantic region modeling using a nonparametric bayesian model. In: CVPR (2008)Google Scholar
  3. 3.
    Piciarelli, C., Micheloni, C., Foresti, G.L.: Trajectory-based anomalous event detection. IEEE Trans. Circuits Systems Vid. Tech. 18, 1544–1554 (2008)CrossRefGoogle Scholar
  4. 4.
    Breitenstein, M., Grabner, H., Gool, L.V.: Hunting nessie – real-time abnormality detection from webcams. In: ICCV WS on VS (2009)Google Scholar
  5. 5.
    Pritch, Y., Ratovitch, S., Hendel, A., Peleg, S.: Clustered synopsis of surveillance video. In: AVSS (2009)Google Scholar
  6. 6.
    Adam, A., Rivlin, E., Shimshoni, I., Reinitz, D.: Robust real-time unusual event detection using multiple fixed-location monitors. PAMI (2008)Google Scholar
  7. 7.
    Zhong, H., Shi, J., Visontai, M.: Detecting unusual activity in video. In: CVPR (2004)Google Scholar
  8. 8.
    Zhu, X., Wu, X., Fan, J., Elmagarmid, A., Aref, W.: Exploring video content structure for hierarchical summarization. Multimedia Systems 10, 98–115 (2004)CrossRefGoogle Scholar
  9. 9.
    Chen, B., Sen, P.: Video carving. Eurographics (2008)Google Scholar
  10. 10.
    Simakov, D., Caspi, Y., Irani, M., Shechtman, E.: Summarizing visual data using bidirectional similarity. In: CVPR (2008)Google Scholar
  11. 11.
    Loy, C., Xiang, T., Gong, S.: Multi-camera activity correlation analysis. In: CVPR, pp. 1988–1995 (2009)Google Scholar
  12. 12.
    Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: NIPS (2004)Google Scholar
  13. 13.
    Akaike, H.: A new look at the statistical model identification. IEEE Trans. Automatic Control 19, 716–723 (1974)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Loy, C., Xiang, T., Gong, S.: Modelling activity global temporal dependencies using time delayed probabilistic graphical model. In: ICCV (2009)Google Scholar
  15. 15.
    Eshelman, L.: The chc adaptive search algorithm. Foundations of Genetic Algorithms, 256–283 (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Carter De Leo
    • 1
  • B. S. Manjunath
    • 1
  1. 1.University of CaliforniaSanta BarbaraUSA

Personalised recommendations