Detecting and tracking multiple moving objects using temporal integration

  • Michal Irani
  • Benny Rousso
  • Shmuel Peleg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


Tracking multiple moving objects in image sequences involves a combination of motion detection and segmentation. This task can become complicated as image motion may change significantly between frames, like with camera vibrations. Such vibrations make tracking in longer sequences harder, as temporal motion constancy can not be assumed.

A method is presented for detecting and tracking objects, which uses temporal integration without assuming motion constancy. Each new frame in the sequence is compared to a dynamic internal representation image of the tracked object. This image is constructed by temporally integrating frames after registration based on the motion computation. The temporal integration serves to enhance the region whose motion is being tracked, while blurring regions having other motions. These effects help motion analysis in subsequent frames to continue tracking the same motion, and to segment the tracked region.


Optical Flow Motion Analysis Motion Parameter Temporal Integration Motion Computation 
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.
    G. Adiv. Determining three-dimensional motion and structure from optical flow generated by several moving objects. IEEE Trans. on Pattern Analysis and Machine Intelligence, 7(4):384–401, July 1985.Google Scholar
  2. 2.
    J.R. Bergen and E.H. Adelson. Hierarchical, computationally efficient motion estimation algorithm. J. Opt. Soc. Am. A., 4:35, 1987.Google Scholar
  3. 3.
    J.R. Bergen, P.J. Burt, K. Hanna, R. Hingorani, P. Jeanne, and S. Peleg. Dynamic multiple-motion computation. In Y.A. Feldman and A. Bruckstein, editors, Artificial Intelligence and Computer Vision: Proceedings of the Israeli Conference, pages 147–156. Elsevier (North Holland), 1991.Google Scholar
  4. 4.
    J.R. Bergen, P.J. Burt, R. Hingorani, and S. Peleg. Computing two motions from three frames. In International Conference on Computer Vision, pages 27–32, Osaka, Japan, December 1990.Google Scholar
  5. 5.
    P.J. Burt, R. Hingorani, and R.J. Kolczynski. Mechanisms for isolating component patterns in the sequential analysis of multiple motion. In IEEE Workshop on Visual Motion, pages 187–193, Princeton, New Jersey, October 1991.Google Scholar
  6. 6.
    D.J. Heeger. Optical flow using spatiotemporal filters. International Journal of Computer Vision, 1:279–302, 1988.Google Scholar
  7. 7.
    B.K.P. Horn and B.G. Schunck. Determining optical flow. Artificial Intelligence, 17:185–203, 1981.Google Scholar
  8. 8.
    M. Irani and S. Peleg. Improving resolution by image registration. CVGIP: Graphical Models and Image Processing, 53:231–239, May 1991.Google Scholar
  9. 9.
    M. Irani, B. Rousso, and S. Peleg. Detecting multiple moving objects using temporal integration. Technical Report 91–14, The Hebrew University, December 1991.Google Scholar
  10. 10.
    M. Shizawa and K. Mase. Simultaneous multiple optical flow estimation. In International Conference on Pattern Recognition, pages 274–278, Atlantic City, New Jersey, June 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Michal Irani
    • 1
  • Benny Rousso
    • 1
  • Shmuel Peleg
    • 1
  1. 1.Dept. of Computer ScienceThe Hebrew University of JerusalemJerusalemIsrael

Personalised recommendations