Modeling the product manifold of posture and motion

Long-term human motion is composed of an ensemble of different activities with varying complexity. This makes it challenging to develop models to accurately estimate human motion. In this paper, we exploit the dependencies that exist between posture and motion for long-term human motion estimation. We propose to model the nonlinear motion manifold as a collection of local linear models, noting that given a particular posture, the variation in motion for that posture can be well-approximated by a linear model. A collection of local linear models is easy to fit and also has the expressiveness to encode several activities in any arbitrary order. Furthermore, to account for the varying complexity of different activities, each local linear model can have a different dimensionality. A collection of local linear models, thus, avoids the limitation of global models that require a uniform dimensionality for the latent motion manifold. This model allows us to linearly regularize motion estimation algorithms over the nonlinear human motion manifold. Our results demonstrate that a collection of local linear models provides an effective representation for the motion manifold when compared to other global models such as the bilinear model [18] and the Principal Component Analysis [14].

[1]  Joshua B. Tenenbaum,et al.  Separating Style and Content with Bilinear Models , 2000, Neural Computation.

[2]  Matthew Brand,et al.  Charting a Manifold , 2002, NIPS.

[3]  Andrew Blake,et al.  Articulated body motion capture by annealed particle filtering , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[5]  Ahmed M. Elgammal,et al.  Modeling View and Posture Manifolds for Tracking , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Christopher M. Bishop,et al.  Mixtures of Probabilistic Principal Component Analyzers , 1999, Neural Computation.

[7]  Nikos A. Vlassis,et al.  Non-linear CCA and PCA by Alignment of Local Models , 2003, NIPS.

[8]  Geoffrey E. Hinton,et al.  Global Coordination of Local Linear Models , 2001, NIPS.

[9]  David J. Fleet,et al.  Gaussian Process Dynamical Models , 2005, NIPS.

[10]  B. Triggs,et al.  Tracking Articulated Motion with Piecewise Learned Dynamical Models , 2004 .

[11]  Nanda Kambhatla,et al.  Dimension Reduction by Local Principal Component Analysis , 1997, Neural Computation.

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

[13]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data , 2003, NIPS.

[14]  K. Schittkowski,et al.  NONLINEAR PROGRAMMING , 2022 .

[15]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[16]  Chiraz Ben Abdelkader.  Motion-Based Recognition of People in EigenGait Space , 2002 .

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

[18]  Dimitri P. Bertsekas,et al.  Nonlinear Programming , 1997 .

[19]  Hiroshi Murase,et al.  Moving object recognition in eigenspace representation: gait analysis and lip reading , 1996, Pattern Recognit. Lett..

[20]  Adrian Hilton,et al.  Realistic synthesis of novel human movements from a database of motion capture examples , 2000, Proceedings Workshop on Human Motion.

[21]  Daniel Martin.  Manifold Theory: An Introduction for Mathematical Physicists , 1991 .

[22]  Takeo Kanade,et al.  Linear motion estimation for systems of articulated planes , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.