Full Body Statistical Shape Modeling with Posture Normalization

  • Femke Danckaers
  • Toon Huysmans
  • Ann Hallemans
  • Guido De Bruyne
  • Steven Truijen
  • Jan Sijbers
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 591)

Abstract

Realistic virtual mannequins, that represent body shapes that occur in the target population, are valuable tools for product developers who design near-body products. Statistical shape modeling is a promising approach to map out the variability of body shapes. The strength of statistical shape models (SSM) is their ability to capture most of the shape variation with only a few shape modes. Unfortunately, the shape variation captured by SSMs of human bodies is often polluted by variations in posture, which substantially reduces the compactness of those models. In this paper, we propose a fast and data driven framework to build a posture invariant SSM. The normalized SSM is shown to be substantially more compact than the non-normalized SSM. Using five shape modes, the normalized SSM is 23% more compact than the non-normalized SSM.

Keywords

Posture normalization Human body modeling 3D anthropometry Statistical shape model SSM 

Notes

Acknowledgements

This work was supported by the Agency for Innovation by Science and Technology in Flanders (IWT-SB 141520).

References

  1. 1.
    Moes, N.C.: Digital human models: an overview of development and applications in product and workplace design. In: TMCE International Conference (2010)Google Scholar
  2. 2.
    Reed, M.P., Park, B.-K.D., Corner, B.D.: Predicting seated body shape from standing body shape. In: 4th International Digital Human Modeling Conference (2016)Google Scholar
  3. 3.
    Robinette, K.M., Daanen, H., Paquet, E.: The CAESAR project: a 3-D surface anthropometry survey. In: Second International Conference on 3-D Digital Imaging and Modeling (Cat. No. PR00062), pp. 380–386 (1999)Google Scholar
  4. 4.
    Baran, I., Popović, J.: Automatic rigging and animation of 3D characters. ACM Trans. Graph. 26(3), 72 (2007)CrossRefGoogle Scholar
  5. 5.
    Wuhrer, S., Shu, C., Xi, P.: Posture-invariant statistical shape analysis using Laplace operator. Comput. Graph. 36(5), 410–416 (2012)CrossRefGoogle Scholar
  6. 6.
    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: shape completion and animation of people. ACM Trans. Graph. 24(3), 408 (2005)CrossRefGoogle Scholar
  7. 7.
    Danckaers, F., Huysmans, T., Lacko, D., Ledda, A., Verwulgen, S., Van Dongen, S., Sijbers, J.: Correspondence preserving elastic surface registration with shape model prior. In: Proceedings - International Conference on Pattern Recognition (2014)Google Scholar
  8. 8.
    Danckaers, F., Huysmans, T., Lacko, D., Sijbers, J.: Evaluation of 3D body shape predictions based on features. In: Proceedings of the 6th International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 27–28 October 2015, pp. 258–265 (2015)Google Scholar
  9. 9.
    Allen, B., Curless, B., Popović, Z.: The space of human body shapes. ACM Trans. Graph. 22(3), 587 (2003)CrossRefGoogle Scholar
  10. 10.
    Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: A minimum description length approach to statistical shape modeling. IEEE Trans. Med. Imaging 21(5), 525–537 (2002)CrossRefMATHGoogle Scholar
  11. 11.
    Zihua, S.: Statistical Shape Modelling: Automatic Shape Model Building. University College London, London (2011)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Femke Danckaers
    • 1
  • Toon Huysmans
    • 1
  • Ann Hallemans
    • 2
    • 4
  • Guido De Bruyne
    • 3
  • Steven Truijen
    • 2
    • 4
  • Jan Sijbers
    • 1
  1. 1.imec - Vision Lab, Department of Physics, Faculty of SciencesUniversity of AntwerpAntwerpBelgium
  2. 2.Multidisciplinary Motor Centre AntwerpUniversity of AntwerpAntwerpBelgium
  3. 3.Department of Product Development, Faculty of Design SciencesUniversity of AntwerpAntwerpBelgium
  4. 4.Department of Rehabilitation Sciences and Physiotherapy, Faculty of Medicine and Health SciencesUniversity of AntwerpAntwerpBelgium

Personalised recommendations