Unsupervised hierarchical modeling of locomotion styles

ABSTRACT

This paper describes an unsupervised learning technique for modeling human locomotion styles, such as distinct related activities (e.g. running and striding) or variations of the same motion performed by different subjects. Modeling motion styles requires identifying the common structure in the motions and detecting style-specific characteristics. We propose an algorithm that learns a hierarchical model of styles from unlabeled motion capture data by exploiting the cyclic property of human locomotion. We assume that sequences with the same style contain locomotion cycles generated by noisy, temporally warped versions of a single latent cycle. We model these style-specific latent cycles as random variables drawn from a common "parent" cycle distribution, representing the structure shared by all motions. Given these hierarchical priors, the algorithm learns, in a completely unsupervised fashion, temporally aligned latent cycle distributions, each modeling a specific locomotion style, and computes for each example the style label posterior distribution, the segmentation into cycles, and the temporal warping with respect to the latent cycles. We demonstrate the flexibility of the model on several application problems such as style clustering, animation, style blending, and filling in of missing data.

REFERENCES

• 1: Matthew Brand , Aaron Hertzmann, Style machines, Proceedings of the 27th annual conference on Computer graphics and interactive techniques, p.183-192, July 2000 [doi>10.1145/344779.344865]
• 2: Chiappa, S., Kober, J., & Peters, J. (2009). Using bayesian dynamical systems for motion template libraries. In Adv. in Neural Inform. Proc. Systems 21, 297--304.
• 3: Elgammal, A. M., & Lee, C.-S. (2004). Separating style and content on a nonlinear manifold. Proc. of Comp. Vision Pattern Recogn. (pp. 478--485).
• 4: Keith Grochow , Steven L. Martin , Aaron Hertzmann , Zoran Popović, Style-based inverse kinematics, ACM Transactions on Graphics (TOG), v.23 n.3, August 2004
• 5: Michael I. Jordan , Zoubin Ghahramani , Tommi S. Jaakkola , Lawrence K. Saul, An Introduction to Variational Methods for Graphical Models, Machine Learning, v.37 n.2, p.183-233, Nov.1.1999 [doi>10.1023/A:1007665907178]
• 6: Lucas Kovar , Michael Gleicher , Frédéric Pighin, Motion graphs, ACM Transactions on Graphics (TOG), v.21 n.3, July 2002
• 7: Yan Li , Tianshu Wang , Heung-Yeung Shum, Motion texture: a two-level statistical model for character motion synthesis, ACM Transactions on Graphics (TOG), v.21 n.3, July 2002
• 8: Listgarten, J., Neal, R. M., Roweis, S. T., & Emili, A. (2005). Multiple alignment of continuous time series. In Adv. in Neural Inform. Proc. Systems 17, 817--824.
• 9: Listgarten, J., Neal, R. M., Roweis, S. T., Puckrin, R., & Cutler, S. (2007). Bayesian detection of infrequent differences in sets of time series with shared structure. In Adv. in Neural Inform. Proc. Systems 19, 905--912.
• 10: C. Karen Liu , Aaron Hertzmann , Zoran Popović, Learning physics-based motion style with nonlinear inverse optimization, ACM Transactions on Graphics (TOG), v.24 n.3, July 2005
• 11: Ormoneit, D., Black, M., Hastie, T., & Kjellströöm, H. (2005). Representing cyclic human motion using functional analysis. Image and Vision Comp., 1264--1276.
• 12: Lawrence R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Readings in speech recognition, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1990
• 13: Charles Rose , Michael F. Cohen , Bobby Bodenheimer, Verbs and Adverbs: Multidimensional Motion Interpolation, IEEE Computer Graphics and Applications, v.18 n.5, p.32-40, September 1998 [doi>10.1109/38.708559]
• 14: Taylor, G. W., Hinton, G. E., & Roweis, S. T. (2007). Modeling human motion using binary latent variables. In Adv. in Neural Inform. Proc. Systems 19, 1345--1352.
• 15: Torresani, L., Hackney, P., & Bregler, C. (2007). Learning motion style synthesis from perceptual observations. In Adv. in Neural Inform. Proc. Systems 19, 1393--1400.
• 16: Raquel Urtasun , David J. Fleet , Andreas Geiger , Jovan Popović , Trevor J. Darrell , Neil D. Lawrence, Topologically-constrained latent variable models, Proceedings of the 25th international conference on Machine learning, p.1080-1087, July 05-09, 2008, Helsinki, Finland [doi>10.1145/1390156.1390292]
• 17: Jack M. Wang , David J. Fleet , Aaron Hertzmann, Multifactor Gaussian process models for style-content separation, Proceedings of the 24th international conference on Machine learning, p.975-982, June 20-24, 2007, Corvalis, Oregon [doi>10.1145/1273496.1273619]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics
          Subjects: Manipulators; Kinematics and dynamics
  I.6 SIMULATION AND MODELING
      I.6.4 Model Validation and Analysis
      I.6.5 Model Development
          Subjects: Modeling methodologies

General Terms:
Algorithms, Design, Performance, Theory