Global Motion Estimation: Feature-Based, Featureless, or Both ?!

  • Rui F. C. Guerreiro
  • Pedro M. Q. Aguiar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4141)


The approaches to global motion estimation have been naturally classified into one of two main classes: feature-based methods and direct (or featureless) methods. Feature-based methods compute a set of point correspondences between the images and, from these, estimate the parameters describing the global motion. Although the simplicity of the second step has made this approach rather appealing, the correspondence step is a quagmire and usually requires human supervision. In opposition, featureless methods attempt to estimate the global motion parameters directly from the image intensities, using complex nonlinear optimization algorithms. In this paper, we propose an iterative scheme that combines the feature-based simplicity with the featureless robustness. Our experiments illustrate the behavior of the proposed scheme and demonstrate its effectiveness by automatically building image mosaics.


Video Sequence Input Image Motion Estimation Global Motion Point Correspondence 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dufaux, F., Konrad, J.: Efficient, robust, and fast global motion estimation for video coding. IEEE Trans. on Image Processing 9(3), 497–501 (2000)CrossRefGoogle Scholar
  2. 2.
    Petrovic, N., Jojic, N., Huang, T.: Hierarchical video clustering. In: Proc. of IEEE Multimedia Signal Processing Workshop, Siena, Italy (2004)Google Scholar
  3. 3.
    Aguiar, P., Jasinschi, R., Moura, J., Pluempitiwiriyawej, C.: Content-based image sequence representation. In: Reed, T. (ed.) Digital Video Processing, ch. 2, pp. 7–72. CRC Press, Boca Raton (2004)Google Scholar
  4. 4.
    Mann, S., Piccard, R.: Video orbits of the projective group: a simple approach to featureless estimation of parameters. IEEE Trans. on Image Processing 6(9), 1281–1295 (1997)CrossRefGoogle Scholar
  5. 5.
    Kim, D., Hong, K.: Fast global registration for image mosaicing. In: Proc. of IEEE Int. Conf. Image Processing, Barcelona, Spain (2003)Google Scholar
  6. 6.
    Faugeras, O.: Three-Dimensional Computer Vision. MIT Press, Cambridge (1993)Google Scholar
  7. 7.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  8. 8.
    Lee, J., Ra, J.: Block motion estimation based on selective integral projections. In: Proc. of IEEE Int. Conf. Image Processing, Rochester NY, USA (2002)Google Scholar
  9. 9.
    Reddy, B., Chattery, B.: An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans. on Image Processing 5(8), 1266–1271 (1996)CrossRefGoogle Scholar
  10. 10.
    Perez, P., Garcia, N.: Robust and accurate registration of images with unknown relative orientation and exposure. In: Proc. of IEEE Int. Conf. Image Processing, Genova, Italy (2005)Google Scholar
  11. 11.
    Shi, J., Tomasi, C.: Good features to track. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition (1994)Google Scholar
  12. 12.
    Aguiar, P., Moura, J.: Image motion estimation – convergence and error analysis. In: Proc. of IEEE Int. Conf. on Image Processing, Thessaloniki, Greece (2001)Google Scholar
  13. 13.
    Altunbasak, Y., Merserau, R., Patti, A.: A fast parametric motion estimation algorithm with illumination and lens distortion correction. IEEE Trans. on Image Processing 12(4) (2003)Google Scholar
  14. 14.
    Pires, B., Aguiar, P.: Featureless global alignment of multiple images. In: Proc. of IEEE Int. Conf. Image Processing, Genova, Italy (2005)Google Scholar
  15. 15.
    Irani, M., Anandan, P.: About direct methods. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, Springer, Heidelberg (2000)Google Scholar
  16. 16.
    Torr, P.: Feature based methods for structure and motion estimation. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  17. 17.
    Rosenfeld, A. (ed.): Multiresolution Image Processing and Analysis. Springer Series in Information Sciences, vol. 12. Springer, Heidelberg (1984)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rui F. C. Guerreiro
    • 1
  • Pedro M. Q. Aguiar
    • 2
  1. 1.Philips ResearchEindhovenNetherlands
  2. 2.Institute for Systems and Robotics / Instituto Superior TécnicoLisboaPortugal

Personalised recommendations