论文信息 - Learning Statistical Models of Human Motion

Learning Statistical Models of Human Motion

Non-linear statistical models of deformation provide methods to learn a priori shape and deformation for an object or class of objects by example. This paper extends these models of deformation to that of motion by augmenting the discrete representation of piecewise nonlinear principle component analysis of shape with a markov chain which represents the temporal dynamics of the model. In this manner, mean trajectories can be learnt and reproduced for either the simulation of movement or for object tracking. This paper demonstrates the use of these techniques in learning human motion from capture data.

R. Bowden

[1] Stephen M. Omohundro,et al. Surface Learning with Applications to Lipreading , 1993, NIPS.

[2] Timothy F. Cootes,et al. A Non-linear Generalisation of PDMs using Polynomial Regression , 1994, BMVC.

[3] David C. Hogg,et al. Automated Pivot Location for the Cartesian-Polar Hybrid Point Distribution Model , 1995, BMVC.

[4] David C. Hogg,et al. An Adaptive Eigenshape Model , 1995, BMVC.

[5] Timothy F. Cootes,et al. Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[6] M Sarhadi,et al. Cluster Based non-linear Principle Component Analysis , 1997 .

[7] Timothy F. Cootes,et al. Non-linear point distribution modelling using a multi-layer perceptron , 1995, Image Vis. Comput..

[8] Christopher J. Taylor,et al. Automatic Construction of Eigenshape Models by Genetic Algorithm , 1997, IPMI.

[9] David C. Hogg,et al. Improving Specificity in PDMs using a Hierarchical Approach , 1997, BMVC.

[10] Richard Bowden,et al. Learning Non-linear Models of Shape and Motion , 1999 .

[11] Timothy F. Cootes,et al. A mixture model for representing shape variation , 1999, Image Vis. Comput..

[12] Mansoor Sarhadi,et al. Building Temporal Models for Gesture Recognition , 2000, BMVC.

[13] Mansoor Sarhadi,et al. Non-linear statistical models for the 3D reconstruction of human pose and motion from monocular image sequences , 2000, Image Vis. Comput..