Advertisement

Multi-body Segmentation and Motion Number Estimation via Over-Segmentation Detection

  • Guodong Pan
  • Kwan-Yee Kenneth Wong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6469)

Abstract

This paper studies the problem of multi-body segmentation and motion number estimation. It is well known that motion number plays a critical role in the success of multi-body segmentation. Most of the existing methods exploit only motion affinity to segment and determine the number of motions. Motion number estimated in this way is often seriously affected by noise. In this paper, we recast the problem of multi-body segmentation and motion number estimation into an over-segmentation detection problem, and introduce three measures, namely loss of spatial locality (LSL), split ratio (SR) and cluster distance (CD), for over-segmentation detection. A hierarchical clustering method based on motion affinity is applied to split the motion clusters recursively until over-segmentation occurs. Over-segmentation is detected by Kernel Support Vector Machines trained under supervised learning using the above three measures. We leverage on Hopkins155 database to test our method and, with the same motion affinity measure, our method outperforms another state-of-the-art method. To the best of our knowledge, this paper is the first to tackle the problem of multi-body segmentation and motion number estimation from the perspective of over-segmentation detection.

Keywords

Support Vector Machine Split Ratio Spectral Cluster Subspace Cluster Rigid Object 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Costeira, J.P., Kanade, T.: A multibody factorization method for independently moving objects. International Journal of Computer Vision 29, 159–179 (1998)CrossRefGoogle Scholar
  2. 2.
    Gear, C.: Multibody grouping from motion images. International Journal of Computer Vision 29, 133–150 (1998)CrossRefGoogle Scholar
  3. 3.
    Vidal, R., Ma, Y., Soatto, S., Sastry, S.: Two-view multibody structure from motion. International Journal of Computer Vision 68, 7–25 (2006)CrossRefGoogle Scholar
  4. 4.
    Yan, J., Pollefeys, M.: A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In: European Conference on Computer Vision, pp. 94–106 (2006)Google Scholar
  5. 5.
    Chin, T.J., Wang, H., Suter, D.: The ordered residual kernel for robust motion subspace clustering. In: Neural Information Processing Systems (2009)Google Scholar
  6. 6.
    Luxburg, U.V.: A tutorial on spectral clustering. Technical report, Max Planck Institute for Biological Cybernetics (2007)Google Scholar
  7. 7.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. In: Computer Vision and Pattern Recognition, pp. 395–416 (1997)Google Scholar
  8. 8.
    Ma, Y., Derksen, H., Hong, W., Wright, J.: Segmentation of multivariate mixed data via lossy data coding and compression. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 1546–1562 (2007)CrossRefGoogle Scholar
  9. 9.
    Schindler, K., Suter, D.: Two-view multibody structure-and-motion with outliers through model selection. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 983–995 (2006)CrossRefGoogle Scholar
  10. 10.
    Schindler, K., Suter, D., Wang, H.: A model-selection framework for multibody structure-and-motion of image sequences. International Journal of Computer Vision 79, 159–177 (2008)CrossRefGoogle Scholar
  11. 11.
    Bab-Hadiashar, A., Suter, D.: In: Data Segmentation and Model Selection for Computer Vision Ch.6, pp. 143–178. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  12. 12.
    Jian, Y.D., Chen, C.S.: Two-view motion segmentation with model selection and outlier removal by ransac-enhanced dirichlet process mixture models. International Journal of Computer Vision 88, 489–501 (2010)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Ozden, K.E., Schindler, K., Gool, L.V.: Multibody structure-from-motion in practice. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 1134–1141 (2010)CrossRefGoogle Scholar
  14. 14.
    Schindler, K., Suter, D.: Two-view multibody structure-and-motion with outliers. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 676–683. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  15. 15.
    Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus (2006)zbMATHGoogle Scholar
  16. 16.
    Tron, R., Vidal, R.: A benchmark for the comparison of 3-d motion segmentation algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Guodong Pan
    • 1
  • Kwan-Yee Kenneth Wong
    • 1
  1. 1.Department of Computer ScienceThe University of Hong KongHong Kong

Personalised recommendations