Recover Human Pose from Monocular Image Under Weak Perspective Projection

  • Minglei Tong
  • Yuncai Liu
  • Thomas S. Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3766)

Abstract

In this paper we construct a novel human body model using convolution surface with articulated kinematic skeleton. The human body’s pose and shape in a monocular image can be estimated from convolution curve through nonlinear optimization. The contribution of the paper is in three folds: Firstly, human model based convolution surface with articulated skeletons is presented and its shape is deformable when changing polynomial parameters and radius parameters. Secondly, we give convolution surface and curve correspondence theorem under weak perspective projection, which provide a bridge between the 3D pose and 2D contour. Thirdly, we model the human body’s silhouette with convolution curve in order to estimate joint’s parameters from monocular images. Evalution of the method is performed on a sequence of video frames about a walking man.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bloomenthal, J., Shoemake, K.: Convolution surface. Computer Graphics 25(4), 251–256 (1991)CrossRefGoogle Scholar
  2. 2.
    DeCarlo, D., Metaxas, D.: Blended Deformable models. PAMI 18(4), 443–448 (1996)Google Scholar
  3. 3.
    Jin, X., Tai, C.-L.: Convolution Surfaces for Line Skeletons with Polynomial Weight Distributions. Journal of Graphics Tools ACM Press 6(3), 17–28 (2001)MATHGoogle Scholar
  4. 4.
    Tai, C.-L., Zhang, H., Fong, C.-K.: Prototype Modeling from Sketched Silhouettes based on Convolution Surfaces. Computer Graphics Forum 23(1) (2004)Google Scholar
  5. 5.
    Moeslund, T.B., Granum, E.: A Survey of Computer Vision-Based Human Motion Capture. Int. Journal of Computer Vision and Image Under-standing 81(3), 231–268 (2001)MATHCrossRefGoogle Scholar
  6. 6.
    Aggarwal, J.K., Cai, Q., Liao, W., Sabatay, B.: Non-rigid Motion Analysis: Articulated and Elastic Motion. Int. Journal of Computer Vision and Image Understanding 70(2), 142–156 (1998)CrossRefGoogle Scholar
  7. 7.
    Gavrila, D.M.: The visual analysis of human movement: a survey. Computer Vision and Image Understanding 73(1), 82–98 (1999)MATHCrossRefGoogle Scholar
  8. 8.
    Shoji, K., Mito, A., Toyama, F.: Pose estimation of a 2-D articulated objects from its silhouette. In: Proc. 15th Int. Conf. On Pattern Recognition, vol. 3, pp. 713–717 (2000)Google Scholar
  9. 9.
    Ju, S.X., Black, M.J., Yacoob, Y.: Cardboard people: a parameterized model of articulated image motion. In: Proc. 2nd Int. Conf. On Automatic Face and Gesture Recognition, pp. 38–44 (1996)Google Scholar
  10. 10.
    Gavrila, D., Davis, L.: 3-D model-based tracking of human in action: a multi-view approach. In: CVPR San Francisco, pp. 73–80 (1996)Google Scholar
  11. 11.
    Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: CVPR, pp. 8–15 (1998)Google Scholar
  12. 12.
    Bregler, C., Aaron, H., Biermann, H.: Recovering Non-Rigid 3D Shape from Image Streams. In: CVPR, vol. 2 (2000)Google Scholar
  13. 13.
    Sand, P., McMillan, L., Popovic, J.: Continuous Capture of Skin Deformation. In: SIGGRAPH (2003)Google Scholar
  14. 14.
    Plankers, R., Fua, P.: Articulated soft objects for multi-view shape and motion capture. PAMI 25(10) (2003)Google Scholar
  15. 15.
    Sminchisescu, C., Telea, A.: Human pose estimation from silhouettes. a consistent approach using distance level sets. In: WSCG International Conference on Computer Graphics, Visualization and Computer Vision (2002)Google Scholar
  16. 16.
    Sherstyuk, A.: Kernel functions in convolution surfaces: A comparative analysis. The Visual Computer 15(4), 171–182 (1999)MATHCrossRefGoogle Scholar
  17. 17.
    Moré, J.J., Sorensen, D.C.: Computing a Trust Region Step. SIAM Journal on Scientific and Statistical Computing 3, 553–572 (1983)CrossRefGoogle Scholar
  18. 18.
    Steihaug, T.: The Conjugate Gradient Method and Trust Regions in Large Scale Optimization. SIAM Journal on Numerical Analysis 20, 626–637 (1983)MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Tolani, D., Goswami, A., Badler, N.: Real-Time Inverse Kinematics Techniques for Anthropometric Limbs. Graphical Models 62, 338–353 (2000)CrossRefGoogle Scholar
  20. 20.
    Zhang, X., Liu, Y., Huang, T.S.: Motion Estimation of Articulated Objects from Perspective View. In: Perales, F.J., Hancock, E.R. (eds.) AMDO 2002. LNCS, vol. 2492, pp. 165–176. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  21. 21.
    Yang, Y., Levine, M.: The Background Primal Sketch: An Approach for Tracking Moving Objects. Machine Vision and Applications 5, 17–34 (1992)CrossRefGoogle Scholar
  22. 22.
    Kuno, Y., Watanabe, T., Shimosakoda, Y., Nakagawa, S.: Automated Detection of Human for Visual Surveillance System. In: Proc. Int’l Conf. Pattern Recognition, pp. 865–869 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Minglei Tong
    • 1
  • Yuncai Liu
    • 1
  • Thomas S. Huang
    • 2
  1. 1.Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong UniversityP.R. China
  2. 2.Beckman institueUniversity of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations