ISVC 2009: Advances in Visual Computing pp 480-488 | Cite as

Recognition of Semantic Basketball Events Based on Optical Flow Patterns

  • Li Li
  • Ying Chen
  • Weiming Hu
  • Wanqing Li
  • Xiaoqin Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5876)

Abstract

This paper presents a set of novel features for classifying basketball video clips into semantic events and a simple way to use prior temporal context information to improve the accuracy of classification. Specifically, the feature set consists of a motion descriptor, motion histogram, entropy of the histogram and texture. The motion descriptor is defined based on a set of primitive motion patterns which are derived form optical flow field. The event recognition is achieved by using kernel SVMs and a temporal contextual model. Experimental results have verified the effectiveness of the proposed method.

Keywords

Video Clip Semantic Event Sport Video Video Event Motion Descriptor 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ekin, A., Tekalp, A., Mehrotra, R.: Automatic soccer video analysis and summarization. IEEE Transactions on Image Processing 12, 796–807 (2003)CrossRefGoogle Scholar
  2. 2.
    Duan, L., Xu, M., Chua, T., Tian, Q., Xu, C.: A unified framework for semantic shot classification in sports video. IEEE Transaction on Multimedia 7, 1066–1083 (2005)CrossRefGoogle Scholar
  3. 3.
    Wang, F., Jiang, Y., Ngo, C.: Video event detection using motion relativity and visual relatedness. In: ACM Multimediaa, pp. 239–248 (2008)Google Scholar
  4. 4.
    Xu, C., Wang, J., Lu, H., Zhang, Y.: A novel framework for semantic annotation and personalized retrieval of sports video. IEEE Transaction on Multimedia 10, 421–435 (2008)CrossRefGoogle Scholar
  5. 5.
    Xu, D., Chang, S.: Video event recognition using kernel methods with multilevel temporal alignment. IEEE Transaction on Pattern Analysis and Machine Intelligence 30, 1–13 (2008)CrossRefGoogle Scholar
  6. 6.
    Xu, G., Ma, Y., Zhang, H., Yang, S.: An hmm-based framework for video semantic analysis. In: IEEE Transaction on Circuits and Systems for video technology, pp. 1422–1431 (2005)Google Scholar
  7. 7.
    Wang, T., Li, J., Diao, Q., Hu, W., Zhang, Y.: Semantic event detection using conditional random fields. In: Computer Vision and Pattern Recognition Workshop, vol. 109, pp. 17–22 (2006)Google Scholar
  8. 8.
    Qi, G., Hua, X., Rui, Y.: Correlative multi-label video annotation. In: ACM Multimedia, pp. 17–26 (2007)Google Scholar
  9. 9.
    Lucas, B., Kanada, T.: An iterative image registration technique with an application to stereo vision. In: DARPA Image Understanding Workshop, pp. 121–130 (1981)Google Scholar
  10. 10.
    Sudhir, G., John, C., Lee, M.: Video annotation by motion interpretation using optical flow streams. Visual Commun Image Represent 7, 354–368 (1996)CrossRefGoogle Scholar
  11. 11.
    Liu, S., Yi, H., Chia, L., Rajan, D., Chan, S.: Multi-modal semantic analysis and annotation for basketball video. Special Issue on Information Mining from Multimedia Databases of EURASIP Journal on Applied Signal Processing, 1–13 (2006)Google Scholar
  12. 12.
    Wu, Y., Tseng, B., Smith, J.: Ontology-based multi-classification learning for video concept dedetection. In: Proceeding of IEEE International Conferences on Multimedia and Expo, pp. 1003–1006 (2004)Google Scholar
  13. 13.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/cjlin/libsvm

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Li Li
    • 1
  • Ying Chen
    • 2
  • Weiming Hu
    • 1
  • Wanqing Li
    • 3
  • Xiaoqin Zhang
    • 1
  1. 1.Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.Institute Department of Basic SciencesBeijing Electronic and Science TechnologyBeijingChina
  3. 3.University of WollongongSydneyAustralia

Personalised recommendations