DOI QR코드

DOI QR Code

Silhouette-based Motion Estimation for Movement Education of Young Children

유아의 동작 교육을 위한 실루엣 기반 동작 추정

  • 신영숙 (조선대학교 정보통신공학과) ;
  • 김혜정 (덕성여자대학교 아동게임연구센터) ;
  • 이정욱 (덕성여자대학교 아동게임연구센터) ;
  • 이경미 (덕성여자대학교 아동게임연구센터)
  • Published : 2008.04.28

Abstract

Movements are a critical ability to young children's whole development, including physical, social/emotional, and cognitive development. This paper proposes the method to estimate movements suitable for young children's body conditions. The proposed method extracts a silhouette in each frame of videos that are obtained by deploying two video cameras by compensating illuminations, removing background and conducting morphology operations. And we extract silhouette feature values: an area, the ratio of length to width, the lowest foot position, and 7 Hu moments. Also, the area and movements of sub-area are used as local features. For motion estimation, we used probability propagation of the features extracted from the front and side frames. The proposed estimation algorithm is demonstrated for seven movements, walking, jumping, hopping, bending, stretching, balancing, and turning.

Keywords

Silhouette;Motion Estimation;Density Propagation;Movement Education

References

  1. M. Brand and A. Hertzmann, "Style machines," in Proc. of SIGGRAPH, pp.183-192, 2000.
  2. C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas, "Discriminative density propagation for 3D human motion estimation," in Proc. of CVPR, Vol.I, pp.390-397, 2005. https://doi.org/10.1109/CVPR.2005.132
  3. J. Deutscher, A. Blake, and I. Reid, "Articulated body motion capture by annealed particle filtering," in Proc. of CVPR, Vol.II, pp.126-133, 2000. https://doi.org/10.1109/CVPR.2000.854758
  4. G. Hager and P. Belhumeur, "Efficient region tracking with parametric models of geometry and illumination," IEEE transactions on PAMI, Vol.20, No.10, pp.1025-1039, 1999. https://doi.org/10.1109/34.722606
  5. N. Howe, M. Leventon, and W. Freeman, "Bayesian reconstruction of 3D human motion from single camera video," in Proc. of NIPS, Vol.12, pp.820-826, MIT Press, 1999.
  6. I. Pitas, Digital image processing algorithms and applications, Wiley-interscience, pp.352-356, 2000.
  7. S. Roth, L. Sigal, and M. J. Black, "Gibbs likelihoods for Bayesian tracking," in Proc. of CVPR, Vol.I, pp.886-893, 2004. https://doi.org/10.1109/CVPR.2004.1315125
  8. A. Schodl, R. Szeliski, D. H. Salesin, and I. Essa, "Video textures," in Proc. of SIGGRAPH, pp.489-498, 2000.
  9. H. Sidenbladh, M.J. Black, and L. Sigal, "Implicit probabilistic models of human motion for synthesis and tracking," in Proc. of the ECCV, Vol.I, pp.784-800, 2000.
  10. H. Sidenbladh and M. J. Black, "Learning image statistics for Bayesian tracking," in Proc. of ICCV, Vol. II, pp.709-716, 2001.
  11. R. Laban, "Modern educational dance," Macdonald and Evans Ltd. London, 1963.
  12. 구성희, 유치원 교육 활동 지도 자료'에 나타난 동작 관련 활동 분석, 이화여대 석사논문, 2002.
  13. 오연주, 이경실, 김현지, 박경애, 유아 동작 교육의 이론과 실제, 창지사, 2000.
  14. R. Kehl and L. J. Van Gool, "Real-time pointing gesture recognition for an immersive environment," in Proc. of AFGR, pp.577-582, 2004.
  15. A. Mittal, L. Zhao, and L. S. Davis, "Human body pose estimation using silhouette shape analysis," in Proc. of AVSS, pp.263-270, 2003.
  16. L. Ren, G. Shakhnarovich, J. K. Hodgins, H. Pfister, and P. A. Viola, "Learning silhouette features for control of human motion," ACM Graph, Vol.24, No.4, pp.1303-1331, 2005. https://doi.org/10.1145/1095878.1095882
  17. B. Rosenhahn, U. G. Kersting, A. W. Smith, J. K. Gurney, T. Brox, and R. Klette, "A system for marker-less human motion estimation," in Proc. of DAGM, LNCS, 3663, pp.230-237, 2005.
  18. K.. M. Lee and Y. M. Lee, "Tracking multi-person robust to illumination changes and occlusions," in Proc. of ICAT, pp.429-432, 2004.