Abstract
In this paper, we suggest to model priors on human motion by means of nonparametric kernel densities. Kernel densities avoid assumptions on the shape of the underlying distribution and let the data speak for themselves. In general, kernel density estimators suffer from the problem known as the curse of dimensionality, i.e., the amount of data required to cover the whole input space grows exponentially with the dimension of this space. In many applications, such as human motion tracking, though, this problem turns out to be less severe, since the relevant data concentrate in a much smaller subspace than the original high-dimensional space. As we demonstrate in this paper, the concentration of human motion data on lower-dimensional manifolds, approves kernel density estimation as a transparent tool that is able to model priors on arbitrary mixtures of human motions. Further, we propose to support the ability of kernel estimators to capture distributions on low-dimensional manifolds by replacing the standard isotropic kernel by an adaptive, anisotropic one.
We thank U. Kersting for providing data from a marker-based system, as well as the German Research Foundation for their financial support.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Akaike, H.: An approximation to the density function. Annals of the Institute of Statistical Mathematics 6, 127–132 (1954)
Brox, T., Rosenhahn, B., Kersting, U., Cremers, D.: Nonparametric density estimation for human pose tracking. In: Franke, K., Müller, K.R., Nickolay, B., Schäfer, R. (eds.) Pattern Recognition. LNCS, vol. 4174, pp. 546–555. Springer, Heidelberg (2006)
CMU. Carnegie-Mellon Motion Capture Database. http://mocap.cs.cmu.edu
Cremers, D., Kohlberger, T., Schnörr, C.: Shape statistics in kernel space for variational image segmentation. Pattern Recognition 36(9), 1929–1943 (2003)
Grochow, K., Martin, S.L., Hertzmann, A., Popović, Z.: Style-based inverse kinematics. ACM Transactions on Graphics (Proc. SIGGRAPH) 23, 522–531 (2004)
Herda, L., Urtasun, R., Fua, P.: Implicit surface joint limits to constrain video-based motion capture. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3022, pp. 405–418. Springer, Heidelberg (2004)
Howe, N., Leventon, M., Freeman, W.: Bayesian reconstruction of 3D human motion from single-camera video. In: Proc. Neural Information Processing Systems, pp. 820–826 (2000)
Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Computation 3, 79–87 (1991)
Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104(2), 90–126 (2006)
Parzen, E.: On the estimation of a probability density function and the mode. Annals of Mathematical Statistics 33, 1065–1076 (1962)
Rosales, R., Sclaroff, S.: Learning body pose via specialized maps. In: Proc. Neural Information Processing Systems (2001)
Rosenblatt, F.: Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics 27, 832–837 (1956)
Rosenhahn, B., Brox, T., Weickert, J.: Three-dimensional shape knowledge for joint image segmentation and pose tracking. International Journal of Computer Vision 73(3), 243–262 (2007)
Sain, S.R.: Multivariate locally adaptive density estimation. Computational Statistics & Data Analysis 39(2), 165–186 (2002)
Scott, D.: Multivariate Density Estimation. Wiley, Chichester (1992)
Sidenbladh, H., Black, M.J., Sigal, L.: Implicit probabilistic models of human motion for synthesis and tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 784–800. Springer, Heidelberg (2002)
Sminchisescu, C., Jepson, A.: Generative modeling for continuous non-linearly embedded visual inference. In: Proc.International Conference on Machine Learning (2004)
Sminchisescu, C., Kanaujia, A., Metaxas, D.: Learning joint top-down and bottom-up processes for 3D visual inference. In: Proc. International Conference on Computer Vision and Pattern Recognition, pp. 1743–1752 (2006)
Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. International Journal of Robotics Research 22(6), 371–391 (2003)
Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with Gaussian process dynamical models. In: Proc. International Conference on Computer Vision and Pattern Recognition, pp. 238–245. IEEE Computer Society Press, Los Alamitos (2006)
Vincent, P., Bengio, Y.: Manifold parzen windows. In: Proc. Neural Information Processing Systems, vol. 15, pp. 825–832 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brox, T., Rosenhahn, B., Cremers, D., Seidel, HP. (2007). Nonparametric Density Estimation with Adaptive, Anisotropic Kernels for Human Motion Tracking. In: Elgammal, A., Rosenhahn, B., Klette, R. (eds) Human Motion – Understanding, Modeling, Capture and Animation. HuMo 2007. Lecture Notes in Computer Science, vol 4814. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75703-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-75703-0_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75702-3
Online ISBN: 978-3-540-75703-0
eBook Packages: Computer ScienceComputer Science (R0)