Global Motion Estimation Using a New Motion Vector Outlier Rejection Algorithm

  • Burak Yıldırım
  • Hakkı Alparslan Ilgın
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 210)


Global Motion Estimation (GME) is mainly performed in either pixel or compressed domain. Compressed domain approaches usually utilize existing block matching motion data. On the other hand, in compressed domain based GME, there are many unwanted existing outliers because of noise and foreground objects which are obstacle for GME. In this paper, a new motion vector dissimilarity measure is proposed to remove motion vector (MV)-outliers to provide fast and accurate GME. In experimental results, it is shown that proposed method is fairly successive in terms of both accuracy and complexity compared to the state of the art methods.


Dissimilarity Measure Motion Vectors Global Motion Estimation Outlier Rejection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Su, Y., Sun, M.-T., Hsu, V.: Global motion estimation from coarsely sampled motion vector field and the applications. IEEE Transactions on Circuits and Systems for Video Technology 15(2), 232–242 (2005)CrossRefGoogle Scholar
  2. 2.
    Stiller, C., Konrad, J.: Estimating motion in image sequences, a tutorial on modeling and computation of 2D motion. IEEE Signal Processing Magazine 16(7), 70–91 (1999)CrossRefGoogle Scholar
  3. 3.
    Yeo, C., Ahammad, P., Ramchandran, K., Sastry, S.: High-speed action recognition and localization in compressed domain videos. IEEE Transactions on Circuits and Systems for Video Technology 18(8), 1006–1015 (2008)CrossRefGoogle Scholar
  4. 4.
    Efros, A., Berg, A., Mori, G., Malik, J.: Recognizing action at a distance. In: Procurement ICCV 2003, Nice, France, pp. 726–733 (2003)Google Scholar
  5. 5.
    Farin, D.: Automatic Video Segmentation Employing Object/Camera Modeling Techniques. Ph.D. Thesis, Technische Univ. Eindhoven, Eindhoven, Netherlands (2005)Google Scholar
  6. 6.
    Nguyen, T.D., Lee, G.: Tensor voting based outlier removal for global motion estimation. International Journal of Innovative Computing, Information and Control 9(1), 179–190 (2013)Google Scholar
  7. 7.
    Chen, Y.-M., Bajic, I.V.: Motion vector outlier rejection cascade for global motion estimation. IEEE Signal Processing Letters 17(2), 197–200 (2010)CrossRefGoogle Scholar
  8. 8.
    Farin, D., de With, P.H.N.: Evaluation of a feature-based global motion estimation system. In: SPIE Visual Communications and Image Processing, pp. 1331–1342 (2005)Google Scholar
  9. 9.
    Smolic, A., Hoeynck, M., Ohm, J.R.: Low-complexity global motion estimation from P-frame motion vectors for MPEG-7 applications. In: Procurement ICIP 2000, pp. 271–274 (2000)Google Scholar
  10. 10.
    Soldatov, S., Strelnikov, K., Vatolin: Low Complexity Global Motion Estimation from Block Motion Vectors (2013),
  11. 11.
    Guerreiro, R.F.C., Aguiar, P.M.Q.: Global Motion Estimation: Feature-Based, Featureless, or Both?! In: Campilho, A., Kamel, M.S. (eds.) ICIAR 2006. LNCS, vol. 4141, pp. 721–730. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Niu, C., Liu, Y.: Moving Object Segmentation Based on Video Coding Information in H.264 Compressed Domain. In: Procurement CSIP 2009, pp. 1–5 (2009)Google Scholar
  13. 13.
    Richardson Iain, E.G.: H.264 and MPEG-4 Video Compression-Video Coding for Next-generation Multimedia, p. 23. John Wiley & Sons Ltd., The Atrium (2003) ISBN 0-470-84837-5CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  1. 1.İnönü Bulvarı Kirazlıdere Mevkii Süleyman EminUndersecretariat for Defense IndustriesAnkaraTurkey
  2. 2.Electrical and Electronics Eng. Dept.Ankara UniversityTandoğanTurkey

Personalised recommendations