Manifold regularized particle filter for articulated human motion tracking. (English) Zbl 1327.93384
Świątek, Jerzy (ed.) et al., Advances in systems science. Proceedings of the international conference on systems science 2013 (ICSS 2013), Wroclaw, Poland, September 10–12, 2013. Cham: Springer (ISBN 978-3-319-01856-0/pbk; 978-3-319-01857-7/ebook). Advances in Intelligent Systems and Computing 240, 283-293 (2014).
Summary: In this paper, a fully Bayesian approach to articulated human motion tracking from video sequences is presented. First, a filtering procedure with a low-dimensional manifold is derived. Next, we propose a general framework for approximating this filtering procedure based on the particle filter technique. The low-dimensional manifold can be treated as a regularizer which restricts the space of all possible distributions to the space of distributions concentrated around the manifold. We refer to our method as Manifold Regularized Particle Filter. The proposed approach is evaluated using real-life benchmark dataset HumanEva.
For the entire collection see [Zbl 1278.00031].
For the entire collection see [Zbl 1278.00031].
MSC:
| 93E11 | Filtering in stochastic control theory |
| 93E10 | Estimation and detection in stochastic control theory |
| 62C10 | Bayesian problems; characterization of Bayes procedures |
Keywords:
articulated motion tracking; manifold regularization; particle filter; generative approach; Gaussian process latent variable modelSoftware:
HumanEvaReferences:
| [1] | Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(1), 44-58 (2006) · doi:10.1109/TPAMI.2006.21 |
| [2] | Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. International Journal of Computer Vision 61(2), 185-205 (2005) · doi:10.1023/B:VISI.0000043757.18370.9c |
| [3] | Kanaujia, A., Sminchisescu, C., Metaxas, D.: Semi-supervised hierarchical models for 3D human pose reconstruction. In: CVPR 2007 Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition (2007) |
| [4] | Lawrence, N.D.: Probabilistic non-linear principal component analysis with gaussian process latent variable models. Journal of Machine Learning Research 6, 1783-1816 (2005) · Zbl 1222.68247 |
| [5] | Lawrence, N.D., Quiñonero-Candela, J.: Local distance preservation in the GP-LVM through back constraints. In: ICML 2006 Proceedings of the 23rd International Conference on Machine Learning, pp. 513-520 (2006) |
| [6] | Li, R., Tian, T., Sclaroff, S., Yang, M.: 3D human motion tracking with a coordinated mixture of factor analyzers. International Journal of Computer Vision 87, 170-190 (2010) · doi:10.1007/s11263-009-0283-4 |
| [7] | Memisevic, R., Sigal, L., Fleet, D.J.: Shared kernel information embedding for discriminative inference. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(4), 778-790 (2012) · doi:10.1109/TPAMI.2011.154 |
| [8] | 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, 90-126 (2006) · doi:10.1016/j.cviu.2006.08.002 |
| [9] | Poppe, R.: Vision-based human motion analysis: An overview. Computer Vision and Image Understanding 108, 4-18 (2007) · doi:10.1016/j.cviu.2006.10.016 |
| [10] | Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006) · Zbl 1177.68165 |
| [11] | Sigal, L., Balan, A.O., Black, M.J.: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. International Journal of Computer Vision 87(1), 4-27 (2010) · doi:10.1007/s11263-009-0273-6 |
| [12] | Sigal, L., Bhatia, S., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: CVPR 2004 Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition (2004) |
| [13] | Taylor, G.W., Sigal, L., Fleet, D.J., Hinton, G.E.: Dynamical binary latent variable models for 3D human pose tracking. In: CVPR 2010 Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (2010) |
| [14] | Tian, T., Li, R., Sclaroff, S.: Tracking human body pose on a learned smooth space. Technical Report 2005-029, Boston University Computer Science Department (2005) |
| [15] | Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR 2011 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (2011) |
| [16] | Wang, J., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(2), 283-298 (2008) · doi:10.1109/TPAMI.2007.1167 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
