Abstract
Within a discriminative framework for human pose estimation, modeling the mapping from feature space to pose space is challenging as we are required to handle the multimodal conditional distribution in a high-dimensional space. However, to build the mapping, current techniques usually involve a large set of training samples in the learning process but are limited in their capability to deal with multimodality. In this work, we propose a novel online sparse Gaussian Process (GP) regression model combining both temporal and spatial information. We exploit the fact that for a given test input, its output is mainly determined by the training samples potentially residing in its neighbor domain in the input-output unified space. This leads to a local mixture GP experts system, where the GP experts are defined in the local neighborhoods with the variational covariance function adapting to the specific regions. For the nonlinear human motion series, we integrate the temporal and spatial experts into a seamless system to handle multimodality. All the local experts are defined online within very small neighborhoods, so learning and inference are extremely efficient. We conduct extensive experiments on the real HumanEva database to verify the efficacy of the proposed model, obtaining significant improvement against the previous models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Moeslund, T., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. CVIU 104(2-3), 90–126 (2006)
Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Discriminative density propagation for 3d human motion estimation. In: CVPR (2005)
Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. PAMI 28(1), 44–58 (2006)
Elgammal, A., Lee, C.: Inferring 3D body pose from silhouettes using activity manifold learning. In: CVPR (2004)
Ning, H., Wei, X., Gong, Y., Huang, T.: Discriminative learning of visual words for 3D human pose estimation. In: CVPR (2008)
Bissacco, A., Yang, M.H., Soatto, S.: Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In: CVPR (2007)
Zhao, X., Ning, H., Liu, Y., Huang, T.: Discriminative estimation of 3D human pose using Gaussian processes. In: ICPR (2008)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV (2003)
Tomasi, C., Petrov, S., Sastry, A.: 3d tracking= classification+ interpolation. In: ICCV (2003)
Agarwal, A., Triggs, B.: 3D human pose from silhouettes by relevance vector regression. In: CVPR (2004)
Rasmussen, C., Williams, C.: Gaussian processes for machine learning (2006)
Urtasun, R., Darrell, T.: Local probabilistic regression for activity-independent human pose inference. In: CVPR (2008)
Urtasun, R., Fleet, D., Hertzmann, A., Fua, P.: Priors for people tracking from small training sets. In: ICCV (2005)
Quiñonero-Candela, J., Rasmussen, C.: A unifying view of sparse approximate Gaussian process regression. JMLR 6, 1939–1959 (2005)
Lawrence, N., Seeger, M., Herbrich, R.: Fast sparse Gaussian process methods: The informative vector machine. In: NIPS (2003)
Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: NIPS (2006)
Rasmussen, C., Ghahramani, Z.: Infinite mixtures of Gaussian process experts. In: NIPS (2002)
Tresp, V.: Mixtures of Gaussian processes. In: NIPS (2000)
Meeds, E., Osindero, S.: An alternative infinite mixture of Gaussian process experts. In: NIPS (2001)
Jacobs, R., Jordan, M., Nowlan, S., Hinton, G.: Adaptive mixtures of local experts. Neural Computation 3(1), 79–87 (1991)
Sigal, L., Black, M.: Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion. Tech.Report CS-06-08, Brown University (2006)
Csato, L., Opper, M.: Sparse on-line Gaussian processes. Neural Computation 14(3), 641–668 (2002)
Smola, A., Bartlett, P.: Sparse greedy Gaussian process regression. In: NIPS (2001)
Seeger, M., Williams, C., Lawrence, N.: Fast forward selection to speed up sparse Gaussian process regression. In: Proc. of the Ninth Int’l Workshop on AI and Statistics (2003)
Keerthi, S., Chu, W.: A matching pursuit approach to sparse Gaussian process regression. In: NIPS (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhao, X., Fu, Y., Liu, Y. (2010). Temporal-Spatial Local Gaussian Process Experts for Human Pose Estimation. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5994. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12307-8_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-12307-8_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12306-1
Online ISBN: 978-3-642-12307-8
eBook Packages: Computer ScienceComputer Science (R0)