Abstract
This paper presents a novel method to reconstruct 3D body surface model of human figure from 2D uncalibrated monocular video. Unlike other works on body reconstruction from monocular video where either the source video are strictly selected or the skeleton proportions are assumed available beforehand, the proposed system automatically recovers the skeleton proportions and rebuild the 3D human body shape in NURBS format without pose estimation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
REFERENCES
Z. Chen and H.J. Lee, Knowledge-Guided Visual Perception of 3-D Human Gait from a Single Image Sequence, IEEE Trans. On Systems, Man, and Cybernetics, 22(2), 1992.
A. Hilton and T. Gentils, Popup People: Capturing Human Models to Populate Virtual Worlds, SIGGRAPH, UK (1998).
I.A. Kakadiaris and D. Metaxas, 3D Human Body Model Acquisition from Multiple Views, in Proceedings of ICCV’95, pages 618–623, Boston, MA, June 1995.
W. Lee, J. Gu, and N.M. Thalmann, Generating Animatable 3D Virtual Humans from Photographs, Eurographics, 2000.
F. Remondino and A. Roditakis, Human figure Reconstruction and Modeling from Single Image or Monocular Video Sequence, The 4th International Conference on 3-D Digital Imaging and Modeling (3DIM), Banff, Canada (2003).
A. Sappa, N. Aifanti, S. Malassiotis, and M.G. Strintzis, Monocular 3D Human Body Reconstruction Towards Depth Augmentation of Television Sequences, ICIP 2003.
J. Starck and A. Hilton, Model-Based Multiple View Reconstruction of People, ICCV 2003.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer
About this chapter
Cite this chapter
Peng, E., Li, L. (2006). 3D HUMAN MODEL ACQUISITION FROM UNCALIBRATED MONOCULAR VIDEO. In: Wojciechowski, K., Smolka, B., Palus, H., Kozera, R., Skarbek, W., Noakes, L. (eds) Computer Vision and Graphics. Computational Imaging and Vision, vol 32. Springer, Dordrecht. https://doi.org/10.1007/1-4020-4179-9_148
Download citation
DOI: https://doi.org/10.1007/1-4020-4179-9_148
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-4178-5
Online ISBN: 978-1-4020-4179-2
eBook Packages: Computer ScienceComputer Science (R0)