Refinement of optical flow estimation and detection of motion edges

  • Andrea Giachetti
  • Vincent Torre
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1065)


In this paper a multi-scale method for the estimation of optical flow and a simple technique for the extraction of motion edges from an image sequence are presented. The proposed method is based on a differential neighborhood-sampling technique combined with a multi-scale approach and flow filtering techniques. The multi-scale approach is introduced to overcome the aliasing problem in the computation of spatial and temporal derivatives. The flow filtering is useful near motion boundaries to preserve discontinuities. A residual function, which is a confidence measure of the least-squares fit used to compute the optical flow, is introduced and used to filter the flow and to detect motion boundaries. These boundaries, that we call motion edges are extracted by searching for the directional maxima of the map obtained by thinning this residual function. The proposed method has been tested in a variety of conditions. The results obtained with test images show that the proposed approach is an improvement of previous techniques available in the literature.


Optical Flow Coarse Scale Motion Boundary Residual Function Confidence Measure 
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.
    B.K.P. Horn & B.G. Schunck, “Determining optical flow,” Art. Int. 17, 185–203 (1981).Google Scholar
  2. 2.
    B. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision” Proc. DARPA Image Und. Workshop 121–130 (1981).Google Scholar
  3. 3.
    M. Campani and A. Verri, “Motion analysis from first order properties of optical flow,” CVGIP — Image Understanding 56, 1:90–107 (1992).Google Scholar
  4. 4.
    J.L. Barron, D.J. Fleet and S.S. Beauchemin, “Performance of optical flow techniques” Int. J. Comp. Vision 12, 1:43–77 (1994).Google Scholar
  5. 5.
    M. Otte and H.H. Nagel, “Optical flow estimation: advances and comparisons” Proc. Third ECCV, 14, 51–60 (1994).Google Scholar
  6. 6.
    H. H. Nagel, “Optical Flow Estimation and the Interaction Between Measurement Errors at Adjacent Pixel Positions” Int. J. Comp. Vision 15:3, 271–288 (1995).Google Scholar
  7. 7.
    E.De Micheli, S. Uras & V. Torre, “The accuracy of the computation of optical flow and of the recovery of motion parameters,” IEEE Trans. PAMI 15, 5:434–447 (1993).Google Scholar
  8. 8.
    F. Bartolini, V. Cappellini, C. Colombo, A. Mecocci, “Multiwindow least-square approach to the estimation of optical flow with discontinuities” Opt. Eng., 32, 6: 1250–1256, (1993).Google Scholar
  9. 9.
    R. Battiti, E. Amaldi and C. Koch, “Computing Optical Flow Across Multiple Scales: An Adaptive Coarse to Fine Strategy”, Int. J. Comp. Vision 6:2, 133–145 (1991).Google Scholar
  10. 10.
    J. Weber and J. Malik “Robust Computation of Optical Flow in a Multi-Scale Differential Framework” Int. J. Comp. Vision 14, 1:67–81 (1995).Google Scholar
  11. 11.
    S. Xu “Motion and Optical Flow in Robot Vision” Linköping Studies in Science and Technology — Thesis No. 442 (1994).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Andrea Giachetti
    • 1
  • Vincent Torre
    • 1
  1. 1.Dip. FisicaUniversità di GenovaGenova

Personalised recommendations