Gaussian Process Latent Variable Models For Human Pose Estimation

Carl Henrik EkPhilip H. S. TorrNeil D. Lawrence
Machine Learning for Multimodal Interaction (MLMI 2007), Springer-Verlag 4892:132-143, 2008.

Abstract

We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) \[1\] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.

Cite this Paper


BibTeX
@InProceedings{Ek:pose07, title = {Gaussian Process Latent Variable Models For Human Pose Estimation}, author = {Ek, Carl Henrik and Torr, Philip H. S. and Lawrence, Neil D.}, booktitle = {Machine Learning for Multimodal Interaction (MLMI 2007)}, pages = {132--143}, year = {2008}, editor = {Popescu-Belis, Andrei and Renals, Steve and Bourlard, Hervé}, volume = {4892}, series = {LNCS}, address = {Brno, Czech Republic}, publisher = {Springer-Verlag}, doi = {10.1007/978-3-540-78155-4_12}, url = {http://inverseprobability.com/publications/ek-pose07.html}, abstract = {We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) \[1\] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.} }
Endnote
%0 Conference Paper %T Gaussian Process Latent Variable Models For Human Pose Estimation %A Carl Henrik Ek %A Philip H. S. Torr %A Neil D. Lawrence %B Machine Learning for Multimodal Interaction (MLMI 2007) %C LNCS %D 2008 %E Andrei Popescu-Belis %E Steve Renals %E Hervé Bourlard %F Ek:pose07 %I Springer-Verlag %P 132--143 %R 10.1007/978-3-540-78155-4_12 %U http://inverseprobability.com/publications/ek-pose07.html %V 4892 %X We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) \[1\] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.
RIS
TY - CPAPER TI - Gaussian Process Latent Variable Models For Human Pose Estimation AU - Carl Henrik Ek AU - Philip H. S. Torr AU - Neil D. Lawrence BT - Machine Learning for Multimodal Interaction (MLMI 2007) DA - 2008/01/01 ED - Andrei Popescu-Belis ED - Steve Renals ED - Hervé Bourlard ID - Ek:pose07 PB - Springer-Verlag DP - LNCS VL - 4892 SP - 132 EP - 143 DO - 10.1007/978-3-540-78155-4_12 UR - http://inverseprobability.com/publications/ek-pose07.html AB - We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) \[1\] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type. ER -
APA
Ek, C.H., Torr, P.H.S. & Lawrence, N.D.. (2008). Gaussian Process Latent Variable Models For Human Pose Estimation. Machine Learning for Multimodal Interaction (MLMI 2007), in LNCS 4892:132-143 doi:10.1007/978-3-540-78155-4_12 Available from http://inverseprobability.com/publications/ek-pose07.html.

Related Material