Skip to main content
Springer Nature Link
Log in

Region and Graph-Based Motion Segmentation

  • Conference paper
Image Analysis and Recognition (ICIAR 2008)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 5112))

Included in the following conference series:

  • 1719 Accesses

Abstract

This paper describes an approach for integrating motion estimation and region clustering techniques with the purpose of obtaining precise multiple motion segmentation. Motivated by the good results obtained in static segmentation we propose a hybrid approach where motion segmentation is achieved within a region-based clustering approach taken the initial result of a spatial pre-segmentation and extended to include motion information. Motion vectors are first estimated with a multiscale variational method applied directly over the input images and then refined by incorporating segmentation results into a region-based warping scheme. The complete algorithm facilitates obtaining spatially continuous segmentation maps which are closely related to actual object boundaries. A comparative study is made with some of the best known motion segmentation algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Ayer, S., Sawhney, H.S.: Layered representation of motion video using robust maximum-likelihood estimation of mixture models and mdl encoding. In: Proc. IEEE International Conference on Computer Vision, June 1995, pp. 777–784 (1995)

    Google Scholar 

  2. Brox, T.: From pixels to regions: Partial differential equation in image analysis. PhD thesis, Department of Mathematics and Computer Science, Saarland University, Germany (2005)

    Google Scholar 

  3. Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)

    Google Scholar 

  4. Bruhn, A., Weickert, J., Schnörr, C.: Lucas/Kanade meets Horn/ Schunck: combining local and global optic flow methods. International Journal of Computer Vision 61(3), 1–21 (2005)

    Article  Google Scholar 

  5. Chang, S.-F., Sikora, T., Puri, A.: Overview of the MPEG-7 standard. IEEE Transactions on Circuits and Systems for Video Technology 11(6), 688–695 (2001)

    Article  Google Scholar 

  6. Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17(1-3), 185–203 (1981)

    Article  Google Scholar 

  7. Monteiro, F.C.: Region-based spatial and temporal image segmentation. PhD thesis, Faculdade de Engenharia da Universidade do Porto, Portugal (2007)

    Google Scholar 

  8. Monteiro, F.C., Campilho, A.: Spectral Methods in Image Segmentation: A Combined Approach. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3523, pp. 191–198. Springer, Heidelberg (2005)

    Google Scholar 

  9. MPEG4. MPEG-4 video verification model, version 15.0. ISO/IEC/JTC1/SC29/ WG11 N3093 (1999)

    Google Scholar 

  10. Papenberg, N., Bruhn, A., Brox, T., Didas, S., Weickert, J.: Highly accurate optic flow computation with theoretically justified warping. Int. Journal of Computer Vision 67(2), 141–158 (2006)

    Article  Google Scholar 

  11. Shi, J., Malik, J.: Motion segmentation and tracking using normalized cuts. In: Proc. of IEEE Int. Conference on Computer Vision, pp. 1154–1160 (1998)

    Google Scholar 

  12. Smith, P.: Edge-based motion segmentation. PhD thesis, Department of Engineering, University of Cambridge (2001)

    Google Scholar 

  13. Vasconcelos, N., Lippman, A.: Empirical bayesian motion segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(2), 217–221 (2001)

    Article  Google Scholar 

  14. Wang, J., Adelson, E.: Representing moving images with layers. IEEE Transactions on Image Processing 3(5), 625–638 (1994)

    Article  Google Scholar 

  15. Weiss, Y., Adelson, E.H.: A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models. In: Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, USA, June 1996, pp. 321–326 (1996)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. INEB - Instituto de Engenharia Biomédica,  ,  

    Fernando C. Monteiro & Aurélio Campilho

  2. Instituto Politécnico de Bragança,  , Portugal

    Fernando C. Monteiro

  3. FEUP - Faculdade de Engenharia, Universidade do Porto, Portugal

    Aurélio Campilho

Authors
  1. Fernando C. Monteiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aurélio Campilho
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Aurélio Campilho Mohamed Kamel

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Monteiro, F.C., Campilho, A. (2008). Region and Graph-Based Motion Segmentation. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2008. Lecture Notes in Computer Science, vol 5112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69812-8_60

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-69812-8_60

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-69811-1

  • Online ISBN: 978-3-540-69812-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics