Abstract
This paper presents a novel method for reconstructing 3D human body pose from monocular image sequences based on top-down learning. Human body pose is represented by a linear combination of prototypes of 2D silhouette images and their corresponding 3D body models in terms of the position of a predetermined set of joints. With a 2D silhouette image, we can estimate optimal coefficients for a linear combination of prototypes of the 2D silhouette images by solving least square minimization. The 3D body model of the input silhouette image is obtained by applying the estimated coefficients to the corresponding 3D body model of prototypes. In the learning stage, the proposed method is hierarchically constructed by classifying the training data into several clusters recursively. Also, in the reconstructing stage, the proposed method hierarchically reconstructs 3D human body pose with a silhouette image or a silhouette history image. We use a silhouette history image and a blurring silhouette image as the spatio-temporal features for reducing noise due to extraction of silhouette image and for extending the search area of current body pose to related body pose. The experimental results show that our method can be efficient and effective for reconstructing 3D human body pose.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ahmad, M., Lee, S.-W.: 3D Human Body Modeling for Gesture Recognition. Technical report CAVR-TR-2004-12, Center for Artificial Vision Research, Korea University (2004)
Bobick, A.F., Davis, J.: The Representation and Recognition of Action Using Temporal Templates. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(3), 257–267 (2001)
Bowden, R., Mitchell, T.A., Sarhadi, M.: Non-linear Statistical Models for 3D Reconstruction of Human Pose and Motion from Monocular Image Sequences. Image and Vision Computing 18(9), 729–737 (2000)
Heap, T., Hogg, D.: Improving Specificity in PDMs Using a Hierarchical Approach. In: Proc. of 8th British Machine Vision Conference, Colchester, UK, September 1997, pp. 590–599 (1997)
Howe, N., Leventon, M., Freeman, M.: Bayesian Reconstruction 3D Human Motion from Single-Camera Video. In: Advances in Neural Information Processing System, vol. 12, pp. 820–826 (2000)
Mori, G., et al.: Recovering Human Body Configurations: Combining Segmentation and Recognition. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA (July 2004)
Mori, G., Malik, J.: Estimating Human Body Configurations using Shape Context Matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Ong, E.J., Gong, S.: A Dynamic Human Model Using Hybrid 2D-3D Representations in Hierarchical PCA Space. In: Proc. of 10th British Machine Vision Conference, Nottingham, UK, September 1999, pp. 33–42 (1999)
Rosales, R., Sclaroff, S.: Specialized Mapping and the Estimation of Human Body Pose from a Single Image. In: Proc. of IEEE Workshop on Human Motion, Texas, USA, December 2000, pp. 19–24 (2000)
Song, Y., Feng, X., Perona, P.: Towards Detection of Human Motion. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, South Carolina, USA, June 2000, pp. 810–817 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, HD., Park, SK., Lee, SW. (2005). Reconstruction of 3D Human Body Pose Based on Top-Down Learning. In: Huang, DS., Zhang, XP., Huang, GB. (eds) Advances in Intelligent Computing. ICIC 2005. Lecture Notes in Computer Science, vol 3644. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11538059_63
Download citation
DOI: https://doi.org/10.1007/11538059_63
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28226-6
Online ISBN: 978-3-540-31902-3
eBook Packages: Computer ScienceComputer Science (R0)