Abstract
This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an explicit probabilistic model from available training data is currently impractical. Instead we exploit methods from texture synthesis that treat images as representing an implicit empirical distribution. These methods replace the problem of representing the probability of a texture pattern with that of searching the training data for similar instances of that pattern. We extend this idea to temporal data representing 3D human motion with a large database of example motions. To make the method useful in practice, we must address the problem of efficient search in a large training set; efficiency is particularly important for tracking. Towards that end, we learn a low dimensional linear model of human motion that is used to structure the example motion database into a binary tree. An approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time. This probabilistic tree search returns a particular sample human motion with probability approximating the true distribution of human motions in the database. This sampling method is suitable for use with particle filtering techniques and is applied to articulated 3D tracking of humans within a Bayesian framework. Successful tracking results are presented, along with examples of synthesizing human motion using the model.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
J. Bar-Joseph, R. El-Yaniv, D. Lischinski, and M. Werman. Texture mixing and texture movie synthesis using statistical learning. IEEE Trans. Visualization and Computer Graphics, 7(2):1120–135, 2001.
J. S. Beis and D. G. Lowe. Shape indexing using nearest-neighbour search in high-dimensional spaces. CVPR, pp. 1000–1006, 1997.
M. Brand. Shadow puppetry. ICCV, vol. 2, pp. 1237–1244, 1999.
M. Brand and A. Hertzmann. Style machines. SIGGRAPH, pp. 183–192, 2000.
A. Bruderlin and T. W. Calvert. Intelligence without representation. Computer Graphics, 23:233–242, 1989.
S. Chenney and D. A. Forsyth. Sampling plausible solutions to multi-body constraint problems. SIGGRAPH, pp. 219–228, 2000.
J. de Bonet. Multiresolution sampling procedure for analysis and synthesis of texture images. SIGGRAPH, pp. 361–368, 1997.
A. A. Efros and W. T. Freeman. Image quilting for texture synthesis and transfer. SIGGRAPH, pp. 341–346, 2001.
A. A. Efros and T. K. Leung. Texture synthesis by non-parametric sampling. ICCV, vol. 2, pp. 1033–1038, 1999.
A. Fitzgibbon. Stochastic rigidity: Image registration for nowhere-static scenes. ICCV, vol. 1, pp. 662–669, 2001
M. Gleicher. Retargeting motion to new characters. SIGGRAPH, pp. 33–42, 1998.
L. Goncalves, E. Di Bernardo, and P. Perona. Reach out and touch space (motion learning). IEEE International Conference on Automatic Face and Gesture Recognition, pp. 234–238, 1998.
N. Gordon. A novel approach to nonlinear/non-gaussian Bayesian state estimation. IEE Proceedings on Radar, Sonar and Navigation, 140(2):107–113, 1993.
P. Harrison. A non-hierarchical procedure for re-synthesis of complex textures. WSCG, 2001.
D. J. Heeger and J. R. Bergen. Pyramid-based texture analysis/synthesis. SIGGRAPH, pp. 229–238, 1995.
A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salisin. Image analogies. SIGGRAPH, pp. 327–240 2001.
D. C. Hogg. Model-based vision: A program to see a walking person. IVC, 1(1):5–20, 1983.
M. Isard and A. Blake. Condensation-conditional density propagation for visual tracking. IJCV, 29(1):5–28, 1998.
M. Isard and A. Blake. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. ECCV, vol. 1, pp. 893–908, 1998.
J. K. Hodgins and N. S. Pollard. Adapting simulated behaviors for new characters. SIGGRAPH, pp. 153–162, 1997.
C. E. Jacobs, A. Finkelstein, and D. H. Salesin. Fast multiresolution image querying. SIGGRAPH, pp. 277–286, 1995.
M. E. Leventon and W. T. Freeman. Bayesian estimation of 3-d human motion from an image sequence. MERL Tech. Rep. TR-98-06, Cambridge, MA, 1998.
J. MacCormick and M. Isard. Partitioned sampling, articulated objects, and interface quality hand tracking. ECCV, vol. 2, pp. 3–19, 2000.
J. McNames. A fast nearest-neighbor algorithm based on a principal axis search tree. PAMI, 23(9):964–976, 2001.
B. Moghaddam and A. Pentland. Probabilistic visual learning for object representation. PAMI, 19(7):696–710, 1997.
L. Molina and A. Hilton. Realistic synthesis of novel human movements from a database of motion capture examples. IEEE Workshop on Human Motion, pp. 137–142, 2000.
H. Murase and S. Nayar. Visual learning and recognition of 3-D objects from appearance. IJCV, 14:5–24, 1995.
S. A. Nene and S. Nayar. A simple algorithm for nearest neighbor search in high dimensions. PAMI, 19:989–1003, 1997.
V. Pavolvić, J. Rehg, T-J. Cham, and K. Murphy. A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV, vol. 1, pp. 94–101, 1999.
K. Popat and R. W. Picard. Cluster-based probability model and its applications to image and texture processing. IEEE Trans. Image Proc., 6(2):268–284, 1997.
Z. Popovic and A. Witkin. Physically Based Motion Transformation. SIGGRAPH, pp. 11–20, 1999.
J. Portilla and E. P. Simoncelli. A parametric texture model based on joint statistics of compex wavelet coefficients. IJCV, 40(1):49–71, 2000.
K. Pullen and C. Bregler. Animating by multi-level sampling. IEEE Computer Animation, pp. 36–42, 2000.
K. Rohr. Towards model-based recognition of human movements in image sequences. CVGIP-Image Understanding, 59(1):94–115, 1994.
A. Schödl, R. Szeliski, D. H. Salesin, and I. Essa. Video textures. SIGGRAPH, pp. 489–498, 2000.
H. Sidenbladh and M. J. Black. Learning image statistics for Bayesian tracking. ICCV, vol. 2, pp. 709–716, 2001.
H. Sidenbladh, M. J. Black, and D. J. Fleet. Stochastic tracking of 3D human figures using 2D image motion. ECCV, vol. 2, pp. 702–718, 2000.
C. Sminchisescu and B. Triggs. Covariance scaled sampling for monocular 3D body tracking. CVPR, vol. 1 pp. 447–454, 2001.
S. Soatto, G. Doretto, Y. Wu. Dynamic Textures. ICCV, pp. 439–446, 2001.
L-Y. Wei and M. Levoy. Fast texture synthesis using tree-structured vector quantization. SIGGRAPH, pp. 479–488, 2000.
C. R. Wren and A. P. Pentland. Dynaman: Recursive modeling of human motion. IVC, to appear.
Y. Yacoob and M. J. Black. Parameterized modeling and recognition of activities in temporal surfaces. CVIU, 73(2):232–247, 1999.
Y. Yacoob and L. Davis. Learned models for estimation of rigid and articulated human motion from stationary or moving camera. IJCV, 36(1):5–30, 2000.
S. C. Zhu, Y. N. Wu, and D. Mumford. Minimax entropy principle and its application to texture modeling. Neural Computation, 9:1627–1660, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sidenbladh, H., Black, M.J., Sigal, L. (2002). Implicit Probabilistic Models of Human Motion for Synthesis and Tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2350. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47969-4_52
Download citation
DOI: https://doi.org/10.1007/3-540-47969-4_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43745-1
Online ISBN: 978-3-540-47969-7
eBook Packages: Springer Book Archive