Extraction of Semantic Dynamic Content from Videos with Probabilistic Motion Models

  • Gwenaëlle Piriou
  • Patrick Bouthemy
  • Jian-Feng Yao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3023)


The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer “concepts” from low-level video features. We adopt a statistical approach and we focus on motion information. Because of the diversity of dynamic video content (even for a given type of events), we have to design appropriate motion models and learn them from videos. We have defined original and parsimonious probabilistic motion models, both for the dominant image motion (camera motion) and the residual image motion (scene motion). These models are learnt off-line. Motion measurements include affine motion models to capture the camera motion, and local motion features for scene motion. The two-step event detection scheme consists in pre-selecting the video segments of potential interest, and then in recognizing the specified events among the pre-selected segments, the recognition being stated as a classification problem. We report accurate results on several sports videos.


Motion Model Camera Motion Video Segment Residual Motion Sport Video 
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.


  1. 1.
    Biernacki, C., Celeux, G., Govaert, G.: Assessing a mixture model for clustering with the Integrated Completed Likelihood. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(3), 719–725 (2000)CrossRefGoogle Scholar
  2. 2.
    Divakaran, A., Radhakrishnan, R., Peker, K.A.: Motion activity-based extraction of key-frame from video shots. In: ICIP 2002, Rochester (September 2002)Google Scholar
  3. 3.
    Ekin, A., Tekalp, A.M., Mehrotra, R.: Automatic soccer video analysis and summarization. IEEE Int. Trans. on Image Processing 12(7), 796–807 (2003)CrossRefGoogle Scholar
  4. 4.
    Fablet, R., Bouthemy, P., Pérez, P.: Non-parametric motion characterization using causal probabilistic models for video indexing and retrieval. IEEE Trans. on Image Processing 11(4), 393–407 (2002)CrossRefGoogle Scholar
  5. 5.
    Li, J., Wang, J.Z.: Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. on PAMI 25(9), 1075–1088 (2003)Google Scholar
  6. 6.
    Ngo, C.-W., Pong, T.-C., Zhang, H.-J.: On clustering and retrieval of video shots through temporal slices analysis. IEEE Trans. Multimedia 4(4), 446–458 (2002)CrossRefGoogle Scholar
  7. 7.
    Odobez, J.-M., Bouthemy, P.: Robust multiresolution estimation of parametric motion models. J. of Visual Comm. and Image Repr. 6(4), 348–365 (1995)CrossRefGoogle Scholar
  8. 8.
    Rui, Y., Anandan, P.: Segmenting visual actions based on spatio-temporal motion patterns. In: CVPR 2000, Hilton Head, SC (2000)Google Scholar
  9. 9.
    Vasconcelos, N., Lippman, A.: Statistical models of video structure for content analysis and characterization. IEEE Trans. on IP 9(1), 3–19 (2000)Google Scholar
  10. 10.
    Yacoob, Y., Black, J.: Parametrized modeling and recognition of activities. In: Sixth IEEE Int. Conf. on Computer Vision, Bombay, India (1998)Google Scholar
  11. 11.
    Zelnik-Manor, L., Irani, M.: Event-based video analysis. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition, Kauai, Hawaii (December 2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Gwenaëlle Piriou
    • 1
  • Patrick Bouthemy
    • 1
  • Jian-Feng Yao
    • 1
    • 2
  2. 2.IRMARRennes cedexFrance

Personalised recommendations