Shot Boundary Detection Algorithm in Compressed Domain Based on Adaboost and Fuzzy Theory

  • Zhi-Cheng Zhao
  • An-Ni Cai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4222)


A shot boundary detection algorithm based on fuzzy theory and Adaboost is proposed in this paper. According to changes of color and camera motion, videos are classified into six types. By using features in compress domain such as DCT coefficients, the type of the MB, HSV color histogram difference, camera motion difference and so on, videos are segmented into three classes, that is, cut shot, gradual shot and non-change. The results of experiment have shown that this algorithm is robust for camera motion and walk-in of large objects in videos, and have better precision of shot boundary detection compared with the classic double-threshold method and the method of presented by Kuoet al.. There is no problem of threshold selection in our algorithm but it exists in most of other algorithms.


Camera Motion Fuzzy Theory Fuzzy Classification Adaboost Algorithm Gaussian Membership Function 
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.
    Over, P., Ianeva, T.: TRECVID 2005 - An Overview. In: Proceedings of TRECVID 2005 Workshop (March 2006)Google Scholar
  2. 2.
    Mezaris, V., Kompatsiaris, I.: Real-Time Compressed Domain Spatiotemporal Segmentation and Ontologies for Video Indexing and Retrieval. IEEE Trans. on Circuits and Systems for Video Technology 14, 606–621 (2004)CrossRefGoogle Scholar
  3. 3.
    Koprinska, I., Carrato, S.: Tepmoral Video Segmentation: A survey. In: EURASIP Sig. Proc.: Image Communication, January 5, 2001, pp. 477–500 (2001)Google Scholar
  4. 4.
    Zhang, H.J., Kankanhalli, A.: Automatic Partitioning of Full-motion Video. Multimedia System (1), 10–28 (1993)Google Scholar
  5. 5.
    Boccignone, G., Santo, M.D.: Automated Threshold Selection for Detection of Dissolves in MPEG Videos. In: IEEE International Conference on Multimedia and Expo (ICME), July 1 (2000)Google Scholar
  6. 6.
    Freund, Y., Schapire, R.E.: A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Science (55), 119–139 (1997)Google Scholar
  7. 7.
    Schapire, R.E.: The Boosting Approach to Machine Learning an Overview. In: MSRI. Workshop on Nonlinear Estimation and Classification (2002)Google Scholar
  8. 8.
    Yang, P., Shan, S.G., Gao, W.: Face Recognition Using Ada-Boosted Gabor Features. In: Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR 2004) (2004)Google Scholar
  9. 9.
    Paul, V., Michael, J.: Robust Real-time Object Detection. In: Second International Workshop on Statistical and Computational Theories of Vision – Modeling, Learning, Computing, and Sampling Vancouver, Canada, July 12 (2001)Google Scholar
  10. 10.
    Tan, Y.P., Saur, D.D., Kulkarni, S.R.: Rapid Estimation of Camera Motion from Compressed Video with Application to Video Annotation. IEEE Trans. on Circuits and Systems for Video Technology, 133–146 (January 1, 2000)Google Scholar
  11. 11.
    Kuo, T.C.T., Lin, Y.B.: Efficient Shot Change Detection on Compressed Video Data. IEEE Trans. On Circuit and Systems for Video Technology, 101–108 (May 5, 1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Zhi-Cheng Zhao
    • 1
  • An-Ni Cai
    • 1
  1. 1.School of Telecommunication EngineeringBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations