Gaussian process latent variable models for human pose estimation
2007 (English)In: MACHINE LEARNING FOR MULTIMODAL INTERACTION / [ed] Belis, AP; Renals, S; Bourlard, H, 2007, 132-143 p.Conference paper (Refereed)
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)  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.
Place, publisher, year, edition, pages
2007. 132-143 p.
, Lecture Notes in Computer Science, ISSN 0302-9743
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-50657ISI: 000253834900012OAI: oai:DiVA.org:kth-50657DiVA: diva2:462376
4th International Workshop on Machine Learning for Multimodal Interaction. Brno, CZECH REPUBLIC. JUN 28-30, 2007
QC 201112082011-12-072011-12-072011-12-08Bibliographically approved