An Efficient Algorithm for Estimating the Inverse Optical Flow

  • Javier Sánchez
  • Agustín Salgado
  • Nelson Monzón
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7887)


The aim of this work is to propose a method for computing the inverse optical flow between two frames in a sequence. We assume that the image registration has already been obtained in one direction and we need to estimate the mapping in the opposite direction. The direct and inverse mappings can easily be related through a simple warping formula, which allows us to propose a fast and efficient algorithm. Nevertheless, it is not possible to estimate the inverse function in the whole domain due to the presence of occlusions and disocclusions. Occlusions occur because some objects move to the same position in the next frame. On the other hand, disocclusions are the opposite situation: no correspondences can be established because there is no object moving to those positions. In this case, there is a lack of information and the best we can do is to guess their values from the surrounding values. In the experimental results, we use standard synthetic sequences to study the performance of the proposed method, and show that it yields very accurate solutions.


Inverse Optical Flow Backward Flow Inverse Mapping Back Registration Occlusions Disocclusions 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alvarez, L., Castaño, C.A., García, M., Krissian, K., Mazorra, L., Salgado, A., Sánchez, J.: Symmetric Optical Flow. In: Moreno Díaz, R., Pichler, F., Quesada Arencibia, A. (eds.) EUROCAST 2007. LNCS, vol. 4739, pp. 676–683. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  2. 2.
    Álvarez, L., Deriche, R., Papadopoulo, T., Sánchez, J.: Symmetrical dense optical flow estimation with occlusions detection. International Journal of Computer Vision 75(3), 371–385 (2007)CrossRefGoogle Scholar
  3. 3.
    Ashburner, J.: A fast diffeomorphic image registration algorithm. NeuroImage 38(1), 95–113 (2007)CrossRefGoogle Scholar
  4. 4.
    Cachier, P., Rey, D.: Symmetrization of the non-rigid registration problem using inversion-invariant energies: Application to multiple sclerosis. In: Delp, S.L., DiGoia, A.M., Jaramaz, B. (eds.) MICCAI 2000. LNCS, vol. 1935, pp. 472–481. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  5. 5.
    Christensen, G.E., Johnson, H.J.: Consistent image registration. IEEE Transactions on Medical Imaging 20(7), 568–582 (2001)CrossRefGoogle Scholar
  6. 6.
    Lieb, D., Lookingbill, A., Thrun, S.: Adaptive road following using self-supervised learning and reverse optical flow. In: Proceedings of Robotics: Science and Systems, Cambridge, USA (June 2005)Google Scholar
  7. 7.
    Lookingbill, A., Rogers, J., Lieb, D., Curry, J., Thrun, S.: Reverse optical flow for self-supervised adaptive autonomous robot navigation. International Journal of Computer Vision 74, 287–302 (2007)CrossRefGoogle Scholar
  8. 8.
    Salgado, A., Sánchez, J.: A temporal regularizer for large optical flow estimation. In: IEEE International Conference on Image Processing, ICIP, pp. 1233–1236 (2006)Google Scholar
  9. 9.
    Sánchez, J., Salgado, A., Monzón, N.: Direct estimation of the backward flow. In: 8th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application (VISAPP), vol. 2, pp. 268–274. INSTICC (2013) ISBN:978-989-8565-47-1 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Javier Sánchez
    • 1
  • Agustín Salgado
    • 1
  • Nelson Monzón
    • 1
  1. 1.Departamento de Informática y SistemasUniversity of Las Palmas de Gran CanariaLas Palmas de Gran CanariaSpain

Personalised recommendations