Abstract
This chapter provides an introduction to models of human pose and motion for use in 3D human pose tracking. We concentrate on probabilistic latent variable models of kinematics, most of which are learned from motion capture data, and on recent physics-based models. We briefly discuss important open problems and future research challenges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Global position and orientation with respect to the world coordinate frame are somewhat arbitrary, and often excluded. Global orientation with respect to gravity, height above the ground, and the change in position with respect to the body-centric coordinate frame should be included.
- 2.
Because the data are joint angles, interpolation is normally accomplished using quaternion spherical interpolation [56]. Naturally, the temporal sampling rate must be sufficiently high that one can interpolate the pose signal with reasonable accuracy.
- 3.
http://staffwww.dcs.shef.ac.uk/people/N.Lawrence/gpsoftware.html is a comprehensive GPLVM code base. GPLVM code is also in the Matlab toolbox for dimensionality reduction available at http://homepage.tudelft.nl/19j49/.
- 4.
The GPLVM has a closed-form mapping from x to y, but there is no closed-form inverse mapping. As a consequence, optimization is required to find the optimal x for a given y.
- 5.
GPDM Code: http://www.dgp.toronto.edu/~jmwang/gpdm/.
- 6.
Code for the coordinated mixture of factor analyzers is included in the Matlab toolbox for dimensionality reduction available at http://homepage.tudelft.nl/19j49/.
- 7.
- 8.
References
Andriluka, M., Roth, S., Schiele, B.: Monocular 3d pose estimation and tracking by detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2010)
Brubaker, M.A., Fleet, D.J.: The kneed walker for human pose tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2008)
Brubaker, M.A., Fleet, D.J., Hertzmann, A.: Physics-based person tracking using the anthropomorphic walker. Int. J. Comput. Vis. 87(1–2), 140–155 (2010)
Brubaker, M.A., Sigal, L., Fleet, D.J.: Estimating contact dynamics. In: IEEE International Conference on Computer Vision, pp. 2389–2396 (2009)
Brubaker, M.A., Sigal, L., Fleet, D.J.: Physics-based human motion modeling for people tracking: A short tutotial. In: Notes from IEEE ICCV Tutorial (2009). (Available from http://www.cs.toronto.edu/~ls/iccv2009tutorial/)
Choo, K., Fleet, D.J.: People tracking using hybrid Monte Carlo filtering. In: IEEE International Conference on Computer Vision, vol. II, pp. 321–328 (2001)
Collins, S.H., Ruina, A.: A bipedal walking robot with efficient and human-like gait. In: International Conference on Robotics and Automation (2005)
Corazza, S., Muendermann, L., Chaudhari, A., Demattio, T., Cobelli, C., Andriacchi, T.: A markerless motion capture system to study musculoskeletal biomechanics: Visual hull and simulated annealing approach. Ann. Biomed. Eng. 34(6), 1019–1029 (2006)
Darby, J., Li, B., Costens, N., Fleet, D.J., Lawrence, N.D.: Backing off: Hierarchical decomposition of activity for 3d novel pose recovery. In: British Machine Vision Conference (2009)
de La Gorce, M., Fleet, D.J., Paragios, N.: Model-based 3d hand pose estimation from monocular video. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1793–1805 (2011)
Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. Int. J. Comput. Vis. 61(2), 185–205 (2005)
Doretto, G., Chiuso, A., Wu, Y.N., Soatto, S.: Dynamic textures. Int. J. Comput. Vis. 51(2), 91–109 (2003)
Doucet, A., Godsill, S., Andrieu, C.: On sequential Monte Carlo sampling methods for Bayesian filtering. Stat. Comput. 10(3), 197–208 (2000)
Elgammal, A.M., Lee, C.-S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 681–688 (2004)
Elgammal, A.M., Lee, C.-S.: Separating style and content on a nonlinear manifold. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 478–485 (2004)
Fox, E.B., Sudderth, E.B., Jordan, M.I., Willsky, A.S.: Nonparametric Bayesian learning of switching linear dynamical systems. In: Advances in Neural Information Processing Systems, pp. 457–464 (2008)
Full, R.J., Koditschek, D.E.: Templates and anchors: Neuromechanical hypotheses of legged locomotion on land. J. Exp. Biol. 202, 3325–3332 (1999)
Gall, J., Rosenhahn, B., Brox, T., Seidel, H.-P.: Optimization and filtering for human motion capture. Int. J. Comput. Vis. 87(1–2), 75–92 (2010)
Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc., F, Radar Signal Process. 140, 107–113 (1993)
Grochow, K., Martin, S.L., Hertzmann, A., Popovic, Z.: Style-based inverse kinematics. ACM Trans. Graph. 23(3), 522–531 (2004)
Hauberg, S., Sommer, S., Pedersen, K.S.: Gaussian-like spatial priors for articulated tracking. In: European Conference on Computer Vision, vol. 1, pp. 425–437 (2010)
Herda, L., Urtasun, R., Fua, P.: Hierarchical implicit surface joint limits for human body tracking. Comput. Vis. Image Underst. 99(2), 189–209 (2005)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. Technical Report UTML TR 2010-003, Department of Computer Science, University of Toronto (2010)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Hou, S., Galata, A., Caillette, F., Thacker, N.A., Bromiley, P.A.: Real-time body tracking using a Gaussian process latent variable model. In: IEEE International Conference on Computer Vision (2007)
Howe, N.R., Leventon, M.E., Freeman, W.T.: Bayesian reconstruction of 3d human motion from single-camera video. In: Advances in Neural Information Processing Systems, pp. 820–826 (1999)
Hyndman, M., Jepson, A.D., Fleet, D.J.: Higher-order autoregressive models for dynamic textures. In: British Machine Vision Conference (2007)
Isard, M., Blake, A.: CONDENSATION – Conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)
Kakadiaris, L., Metaxas, D.: Model-based estimation of 3D human motion. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1453–1459 (2000)
Kong, A., Liu, J.S., Wong, W.H.: Sequential imputations and Bayesian missing data problems. J. Am. Stat. Assoc. 89(425), 278–288 (1994)
Kuo, A.D.: A simple model of bipedal walking predicts the preferred speed–step length relationship. J. Biomech. Eng. 123(3), 264–269 (2001)
Lawrence, N.D.: Probabilistic non-linear principal component analysis with Gaussian process latent variable models. J. Mach. Learn. Res. 6, 1783–1816 (2005)
Lawrence, N.D., Moore, A.J.: Hierarchical Gaussian process latent variable models. In: International Conference on Machine Learning, pp. 481–488 (2007)
Lawrence, N.D., Quiñonero-Candela, J.: Local distance preservation in the gp-lvm through back constraints. In: International Conference on Machine Learning, pp. 513–520 (2006)
Li, R.: Simultaneous learning of non-linear manifold and dynamical models for high-dimensional time series. PhD thesis, Boston University (2009)
Li, R., Tian, T.-P., Sclaroff, S., Yang, M.-H.: 3d human motion tracking with a coordinated mixture of factor analyzers. Int. J. Comput. Vis. 87(1–2), 170–190 (2010)
Li, R., Yang, M.-H., Sclaroff, S., Tian, T.-P.: Monocular tracking of 3d human motion with a coordinated mixture of factor analyzers. In: European Conference on Computer Vision, vol. 2, pp. 137–150 (2006)
Liu, C.K., Hertzmann, A., Popović, Z.: Learning physics-based motion style with nonlinear inverse optimization. ACM Trans. Graph. 24(3), 1071–1081 (2005)
Lu, Z., Carreira-Perpiñán, M.Á., Sminchisescu, C.: People tracking with the Laplacian eigenmaps latent variable model. In: Advances in Neural Information Processing Systems, pp. 1705–1712 (2007)
MacKay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)
McGeer, T.: Dynamics and control of bipedal locomotion. J. Theor. Biol. 163, 277–314 (1993)
Metaxas, D., Terzopoulos, D.: Shape and nonrigid motion estimation through physics-based synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 15(6), 580–591 (1993)
North, B., Blake, A., Isard, M., Rittscher, J.: Learning and classification of complex dynamics. IEEE Trans. Pattern Anal. Mach. Intell. 22(9), 1016–1034 (2000)
Oh, S.M., Rehg, J.M., Balch, T.R., Dellaert, F.: Learning and inferring motion patterns using parametric segmental switching linear dynamic systems. Int. J. Comput. Vis. 77(1–3), 103–124 (2008)
Pan, W., Torresani, L.: Unsupervised hierarchical modeling of locomotion styles. In: International Conference on Machine Learning, p. 99 (2009)
Pavlovic, V., Rehg, J.M., MacCormick, J.: Learning switching linear models of human motion. In: Advances in Neural Information Processing Systems, pp. 981–987 (2000)
Poon, E., Fleet, D.J.: Hybrid Monte Carlo filtering: Edge-based people tracking. In: Workshop on Motion and Video Computing, pp. 151–158 (2002)
Quiñonero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939–1959 (2005)
Raskin, L.M., Rivlin, E., Rudzsky, M.: Using Gaussian process annealing particle filter for 3d human tracking. EURASIP J. Adv. Sig. Proc. (2008)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Robertson, D.G.E., Caldwell, G.E., Hamill, J., Kamen, G., Whittlesey, S.N.: Research Methods in Biomechanics. Human Kinetics, Champaign (2004)
Rose, C., Cohen, M.F., Bodenheimer, B.: Verbs and adverbs: Multidimensional motion interpolation. IEEE Comput. Graph. Appl. 18(5), 32–40 (1998)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(550), 2323–2326 (2000)
Roweis, S.T., Saul, L.K., Hinton, G.E.: Global coordination of local linear models. In: Advances in Neural Information Processing Systems, pp. 889–896 (2001)
Shoemake, K.: Animating rotation with quaternion curves. In: ACM Transactions on Graphics, pp. 245–254 (1985)
Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic tracking of 3d human figures using 2d image motion. In: European Conference on Computer Vision, vol. 2, pp. 702–718 (2000)
Sigal, L., Balan, A.O., Black, M.J.: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87(1–2), 4–27 (2010)
Sigal, L., Fleet, D.J., Troje, N., Livne, M.: Human attributes from 3d pose tracking. In: European Conference on Computer Vision (2010)
Sminchisescu, C., Jepson, A.: Generative modeling for continuous non-linearly embedded visual inference. In: International Conference on Machine Learning, pp. 759–766 (2004)
Sminchisescu, C., Triggs, B.: Kinematic jump processes for monocular 3D human tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 69–76, Madison (2003)
Taylor, G.W., Hinton, G.E.: Factored conditional restricted Boltzmann machines for modeling motion style. In: International Conference on Machine Learning (2009)
Taylor, G.W., Hinton, G.E., Roweis, S.T.: Modeling human motion using binary latent variables. In: Advances in Neural Information Processing Systems, pp. 1345–1352 (2006)
Taylor, G.W., Sigal, L., Fleet, D.J., Hinton, G.E.: Dynamical binary latent variable models for 3d human pose tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 631–638 (2010)
Tenenbaum, J.B., Freeman, W.T.: Separating style and content with bilinear models. Neural Comput. 12(6), 1247–1283 (2000)
Troje, N.: Decomposing biological motion: A framework for analysis and synthesis of human gait patterns. J. Vis. 2(5), 371–387 (2002)
Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with Gaussian process dynamical models. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 238–245 (2006)
Urtasun, R., Fleet, D.J., Hertzmann, A., Fua, P.: Priors for people tracking from small training sets. In: IEEE International Conference on Computer Vision, vol. 1, pp. 403–410 (2005)
Urtasun, R., Fleet, D.J., Fua, P.: Motion models for 3D people tracking. Comput. Vis. Image Underst. 104(2–3), 157–177 (2006)
Urtasun, R., Fleet, D.J., Geiger, A., Popovic, J., Darrell, T., Lawrence, N.D.: Topologically-constrained latent variable models. In: International Conference on Machine Learning, pp. 1080–1087 (2008)
Van Overschee, P., De Moor, B.: N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems. Automatica 30(1), 75–93 (1994)
Vasilescu, M.A.O.: Human motion signatures: Analysis, synthesis, recognition. In: International Conference on Pattern Recognition, vol. III, pp. 456–460 (2002)
Verbeek, J.J.: Learning nonlinear image manifolds by global alignment of local linear models. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1236–1250 (2006)
Wachter, S., Nagel, H.H.: Tracking persons in monocular image sequences. Comput. Vis. Image Underst. 74(3), 174–192 (1999)
Wang, J.M.: Locomotion synthesis methods for humanoid characters. PhD thesis, University of Toronto (2010)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Multifactor Gaussian process models for style-content separation. In: International Conference on Machine Learning, pp. 975–982 (2007)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 283–298 (2008)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Optimizing walking controllers. ACM Trans. Graph. 28(5) (2009)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Optimizing walking controllers for uncertain inputs and environments. ACM Trans. Graph. 29(4) (2010)
Wren, C.R., Pentland, A.: Dynamic models of human motion. In: International Conference on Automatic Face and Gesture Recognition, pp. 22–27 (1998)
Yin, K., Loken, K., van de Panne, M.: Simbicon: Simple biped locomotion control. ACM Trans. Graph. 26(3) (2007)
Acknowledgements
Many thanks to research colleagues with whom I have worked on modeling human motion: Michael Black, Marcus Brubaker, Aaron Hertzmann, Geoff Hinton, Hedvig Kjellström. Neil Lawrence, Roland Memisevic, Leonid Sigal, Graham Taylor, Niko Troje, Raquel Urtasun, and Jack Wang. We gratefully acknowledge generous financial support from NSERC Canada and the Canadian Institute for Advanced Research (CIfAR).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag London Limited
About this chapter
Cite this chapter
Fleet, D.J. (2011). Motion Models for People Tracking. In: Moeslund, T., Hilton, A., Krüger, V., Sigal, L. (eds) Visual Analysis of Humans. Springer, London. https://doi.org/10.1007/978-0-85729-997-0_10
Download citation
DOI: https://doi.org/10.1007/978-0-85729-997-0_10
Publisher Name: Springer, London
Print ISBN: 978-0-85729-996-3
Online ISBN: 978-0-85729-997-0
eBook Packages: Computer ScienceComputer Science (R0)