Advertisement

N-View Human Silhouette Segmentation in Cluttered, Partially Changing Environments ,

  • Tobias Feldmann
  • Björn Scheuermann
  • Bodo Rosenhahn
  • Annika Wörner
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)

Abstract

The segmentation of foreground silhouettes of humans in camera images is a fundamental step in many computer vision and pattern recognition tasks. We present an approach which, based on color distributions, estimates the foreground by automatically integrating data driven 3d scene knowledge from multiple static views. These estimates are integrated into a level set approach to provide the final segmentation results. The advantage of the presented approach is that ambiguities based on color distributions of the fore- and background can be resolved in many cases utilizing the integration of implicitly extracted 3d scene knowledge and 2d boundary constraints. The presented approach is thereby able to automatically handle cluttered scenes as well as scenes with partially changing backgrounds and changing light conditions.

Keywords

Color Distribution Probabilistic Fusion Foreground Segmentation Segmentation Framework Variational Segmentation 
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.
    Grauman, K., Shakhnarovich, G., Darrell, T.: A bayesian approach to image-based visual hull reconstruction. In: IEEE CVPR, vol. 1, pp. 187–194 (2003)Google Scholar
  2. 2.
    Gordon, G., Darrell, T., Harville, M., Woodfill, J.: Background estimation and removal based on range and color. In: IEEE CVPR, vol. 2, pp. 24–59 (1999)Google Scholar
  3. 3.
    Cheung, G.K., Kanade, T., Bouguet, J.Y., Holler, M.: A real time system for robust 3d voxel reconstruction of human motions. In: IEEE CVPR, vol. 2, pp. 714–720 (2000)Google Scholar
  4. 4.
    Kolev, K., Brox, T., Cremers, D.: Robust variational segmentation of 3d objects from multiple views. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 688–697. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Feldmann, T., Dießelberg, L., Wörner, A.: Adaptive foreground/background segmentation using multiview silhouette fusion. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 522–531. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Vogiatzis, G., Torr, P.H.S., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: IEEE CVPR, vol. 2, pp. 391–398 (2005)Google Scholar
  7. 7.
    Lim, S.N., Mittal, A., Davis, L.S., Paragios, N.: Fast illumination-invariant background subtraction using two views: Error analysis, sensor placement and applications. In: IEEE CVPR, pp. 1071–1078 (2005)Google Scholar
  8. 8.
    Lee, W., Woo, W., Boyer, E.: Identifying foreground from multiple images. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 580–589. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Schmaltz, C., Rosenhahn, B., Brox, T., Weickert, J.: Localised mixture models in region-based tracking. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 21–30. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  10. 10.
    Kim, K., Chalidabhongse, T., Harwood, D., Davis, L.: Background modeling and subtraction by codebook construction. In: ICIP, vol. 5, pp. 3061–3064 (October 2004)Google Scholar
  11. 11.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: IEEE CVPR, vol. 2, pp. 2246–2252 (1999)Google Scholar
  12. 12.
    Chan, T., Vese, L.: Active contours without edges. IEEE TIP 10(2), 266–277 (2001)zbMATHGoogle Scholar
  13. 13.
    Zhu, S.C., Yuille, A.: Region competition: unifying snakes, region growing, and bayes/mdl for multiband image segmentation. IEEE TPAMI 18(9), 884–900 (1996)Google Scholar
  14. 14.
    Rother, C., Kolmogorov, V., Blake, A.: “grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)CrossRefGoogle Scholar
  15. 15.
    Franco, J.S., Boyer, E.: Fusion of multi-view silhouette cues using a space occupancy grid. Technical Report 5551, INRIA (April 2005)Google Scholar
  16. 16.
    Scheuermann, B., Rosenhahn, B.: Analysis of numerical methods for level set based image segmentation. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Kuno, Y., Wang, J., Pajarola, R., Lindstrom, P., Hinkenjann, A., Encarnação, M.L., Silva, C.T., Coming, D. (eds.) ISVC 2009, Part II. LNCS, vol. 5876, pp. 196–207. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  17. 17.
    Mumford, D., Shah, J.: Boundary detection by minimizing functionals. In: IEEE CVPR, San Francisco, CA, pp. 22–26 (1985)Google Scholar
  18. 18.
    Osher, S., Sethian, J.: Fronts propagating with curvature dependent speed: Algorithm based on hamilton-jacobi formulation. J. Comput. Phys. 79, 12–49 (1988)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Kim, J., Fisher III, J., Yezzi Jr., A., Cetin, M., Willsky, A.: Nonparametric methods for image segmentation using information theory and curve evolution. In: ICIP, pp. 797–800 (2002)Google Scholar
  20. 20.
    Dempster, A.P.: A generalization of bayesian inference. Journal of the Royal Statistical Society, Series B (Methodological) 30(2), 205–247 (1968)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Tobias Feldmann
    • 1
  • Björn Scheuermann
    • 2
  • Bodo Rosenhahn
    • 2
  • Annika Wörner
    • 1
  1. 1.Karlsruhe Institute of Technology (KIT)Germany
  2. 2.Leibniz Universität HannoverGermany

Personalised recommendations