Estimation of Multiple Periodic Motions from Video

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)


The analysis of periodic or repetitive motions is useful in many applications, both in the natural and the man-made world. An important example is the recognition of human and animal activities. Existing methods for the analysis of periodic motions first extract motion trajectories, e.g. via correlation, or feature point matching. We present a new approach, which takes advantage of both the frequency and spatial information of the video. The 2D spatial Fourier transform is applied to each frame, and time-frequency distributions are then used to estimate the time-varying object motions. Thus, multiple periodic trajectories are extracted and their periods are estimated. The period information is finally used to segment the periodically moving objects. Unlike existing methods, our approach estimates multiple periodicities simultaneously, it is robust to deviations from strictly periodic motion, and estimates periodicities superposed on translations. Experiments with synthetic and real sequences display the capabilities and limitations of this approach. Supplementary material is provided, showing the video sequences used in the experiments.


Video Sequence Motion Estimation Periodic Motion Real Sequence Period Estimate 
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.
    Boyd, J., Little, J.: Motion from transient oscillations. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR (2001)Google Scholar
  2. 2.
    Seitz, S., Dyer, C.R.: View-invariant analysis of cyclic motion. International Journal of Computer Vision 25, 231–251 (1997)CrossRefGoogle Scholar
  3. 3.
    Tsai, P., Shah, M., Keiter, K., Kasparis, T.: Cyclic motion detection for motion based recognition. Pattern Recognition 27, 1591–1603 (1994)CrossRefGoogle Scholar
  4. 4.
    Cutler, R., Davis, L.S.: Robust real-time periodic motion detection, analysis, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 781–796 (2000)CrossRefGoogle Scholar
  5. 5.
    Polana, R., Nelson, R.: Detection and recognition of periodic, nonrigid motion. International Journal of Computer Vision 23, 261–282 (1997)CrossRefGoogle Scholar
  6. 6.
    Lu, C., Ferrier, N.: Repetitive motion analysis: Segmentation and event classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 258–263 (2004)CrossRefGoogle Scholar
  7. 7.
    Cohen, L.: Time-frequency distributions-a review. Proceedings of the IEEE 77, 941–981 (1989)CrossRefGoogle Scholar
  8. 8.
    Pepin, M.P., Clark, M.P.: On the performance of several 2-d harmonic retrieval techniques. In: Conference Record of the Twenty-Eighth Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 254–258 (1994)Google Scholar
  9. 9.
    Briassouli, A., Ahuja, N.: Fusion of frequency and spatial domain information for motion analysis. In: ICPR 2004, Proceedings of the 17th International Conference on Pattern Recognition, vol. 2, pp. 175–178 (2004)Google Scholar
  10. 10.
    Chen, W., Giannakis, G.B., Nandhakumar, N.: A harmonic retrieval framework for discontinuous motion estimation. IEEE Transactions on Image Processing 7, 1242–1257 (1998)CrossRefGoogle Scholar
  11. 11.
    Kojima, A., Sakurai, N., Kishigami, J.I.: Motion detection using 3D-FFT spectrum. In: 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 213–216 (1993)Google Scholar
  12. 12.
    Czerwinski, R., Jones, D.: Adaptive short-time Fourier analysis. IEEE Signal Processing Letters 4, 42–45 (1997)CrossRefGoogle Scholar
  13. 13.
    Boashash, B.: Estimating and interpreting the instantaneous frequency of a signal - Part 1: Fundamentals. Proceedings of the IEEE 80, 520–538 (1992)CrossRefGoogle Scholar
  14. 14.
    Djurovic, I., Stankovic, S.: Estimation of time-varying velocities of moving objects by time-frequency representations. IEEE Transactions on Signal Processing 47, 493–504 (1999)CrossRefGoogle Scholar
  15. 15.
    Kay, S.M.: Modern Spectral Estimation, Theory and Applications. Prentice-Hall, Englewood Cliffs (1988)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  1. 1.Beckman InsituteUniversity of Illinois, Urbana-ChampaignUrbanaUSA

Personalised recommendations