Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation

Estimating 3D pose from monocular images is a highly ambiguous problem. Physical constraints can be exploited to restrict the space of feasible configurations. In this paper we propose an approach to constraining the prediction of a discriminative predictor. We first show that the mean prediction of a Gaussian process implicitly satisfies linear constraints if those constraints are satisfied by the training examples. We then show how, by performing a change of variables, a GP can be forced to satisfy quadratic constraints. As evidenced by the experiments, our method outperforms state-of-the-art approaches on the tasks of rigid and non-rigid pose estimation.

[1]  Trevor Darrell,et al.  Fast pose estimation with parameter-sensitive hashing , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2]  Ankur Agarwal,et al.  3D human pose from silhouettes by relevance vector regression , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3]  Carl E. Rasmussen,et al.  Warped Gaussian Processes , 2003, NIPS.

[4]  Timothy C. Coburn,et al.  Geostatistics for Natural Resources Evaluation , 2000, Technometrics.

[5]  Adrien Bartoli,et al.  Monocular Template-based Reconstruction of Inextensible Surfaces , 2011, International Journal of Computer Vision.

[6]  Cristian Sminchisescu,et al.  Kinematic jump processes for monocular 3D human tracking , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Neil D. Lawrence,et al.  Sparse Convolved Gaussian Processes for Multi-output Regression , 2008, NIPS.

[8]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[9]  Edwin V. Bonilla,et al.  Multi-task Gaussian Process Prediction , 2007, NIPS.

[10]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Yuncai Liu,et al.  Monocular Template-Based Tracking of Inextensible Deformable Surfaces under L2-Norm , 2009, ACCV.

[12]  David J. Fleet,et al.  Priors for people tracking from small training sets , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Philip H. S. Torr,et al.  Randomized trees for human pose detection , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Pascal Fua,et al.  Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture , 2004, ECCV.

[15]  Trevor Darrell,et al.  Sparse probabilistic regression for activity-independent human pose inference , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[17]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[18]  Raquel Urtasun,et al.  Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[20]  Pascal Fua,et al.  Local deformation models for monocular 3D shape recovery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[22]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[23]  Vincent Lepetit,et al.  Accurate Non-Iterative O(n) Solution to the PnP Problem , 2007, 2007 IEEE 11th International Conference on Computer Vision.