Gaussian process motion graph models for smooth transitions among multiple actions

We propose a unified model for human motion prior with multiple actions. Our model is generated from sample pose sequences of the multiple actions, each of which is recorded from real human motion. The sample sequences are connected to each other by synthesizing a variety of possible transitions among the different actions. For kinematically-realistic transitions, our model integrates nonlinear probabilistic latent modeling of the samples and interpolation-based synthesis of the transition paths. While naive interpolation makes unexpected poses, our model rejects them (1) by searching for smooth and short transition paths by employing the good properties of the observation and latent spaces and (2) by avoiding using samples that unexpectedly synthesize the nonsmooth interpolation. The effectiveness of the model is demonstrated with real data and its application to human pose tracking.

[1]  Nancy S. Pollard,et al.  Responsive characters from motion fragments , 2007, SIGGRAPH 2007.

[2]  Lucas Kovar,et al.  Motion graphs , 2002, SIGGRAPH Classes.

[3]  Jessica K. Hodgins,et al.  Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces , 2004, SIGGRAPH 2004.

[4]  Sethu Vijayakumar,et al.  Latent spaces for dynamic movement primitives , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[5]  Trevor Darrell,et al.  Rank priors for continuous non-linear dimensionality reduction , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Human Pose Estimation , 2007, MLMI.

[7]  David J. Fleet,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Gaussian Process Dynamical Model , 2007 .

[8]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, ACM Trans. Graph..

[9]  Alla Safonova,et al.  Achieving good connectivity in motion graphs , 2008, SCA '08.

[10]  Masatsugu Kidode,et al.  Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[11]  Tieniu Tan,et al.  People tracking based on motion model and motion constraints with automatic initialization , 2004, Pattern Recognit..

[12]  David J. Fleet,et al.  Multifactor Gaussian process models for style-content separation , 2007, ICML '07.

[13]  Rajesh P. N. Rao,et al.  Learning Shared Latent Structure for Image Synthesis and Robotic Imitation , 2005, NIPS.

[14]  Xu Zhao,et al.  Tracking 3D Human Motion in Compact Base Space , 2007, 2007 IEEE Workshop on Applications of Computer Vision (WACV '07).

[15]  Wojciech Matusik,et al.  Articulated mesh animation from multi-view silhouettes , 2008, ACM Trans. Graph..

[16]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[17]  Ankur Agarwal,et al.  Tracking Articulated Motion Using a Mixture of Autoregressive Models , 2004, ECCV.

[18]  Joaquin Quiñonero Candela,et al.  Local distance preservation in the GP-LVM through back constraints , 2006, ICML.

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

[20]  David J. Fleet,et al.  Temporal motion models for monocular and multiview 3D human body tracking , 2006, Comput. Vis. Image Underst..

[21]  Odest Chadwicke Jenkins,et al.  Physical simulation for probabilistic motion tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Michael J. Black,et al.  Implicit Probabilistic Models of Human Motion for Synthesis and Tracking , 2002, ECCV.

[23]  A. Elgammal,et al.  Inferring 3D body pose from silhouettes using activity manifold learning , 2004, CVPR 2004.

[24]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[25]  Matthew Brand,et al.  Shadow puppetry , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[26]  Neil A. Thacker,et al.  Real-time Body Tracking Using a Gaussian Process Latent Variable Model , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[27]  Neil D. Lawrence,et al.  Hierarchical Gaussian process latent variable models , 2007, ICML '07.

[28]  F. Sebastian Grassia,et al.  Practical Parameterization of Rotations Using the Exponential Map , 1998, J. Graphics, GPU, & Game Tools.

[29]  David J. Fleet,et al.  Topologically-constrained latent variable models , 2008, ICML '08.

[30]  Neil D. Lawrence,et al.  Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models , 2005, J. Mach. Learn. Res..

[31]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[32]  Jixu Chen,et al.  Switching Gaussian Process Dynamic Models for simultaneous composite motion tracking and recognition , 2009, CVPR.

[33]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.