Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process, hence multiple solutions exist. It is desirable to restrict the solution space to a smaller subset of feasible solutions. The space of feasible solutions may not admit a closed form description. The proposed framework seeks to learn an approximation over such a space. Using Gaussian Process Latent Variable Modelling. The scaled conjugate gradient method is used to find the best matching pose in the learned space. The formulation allows easy incorporation of various constraints for more accurate pose estimation. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The proposed approach performs better than the latter approach in terms of estimation accuracy with synthetic data and qualitatively better results with real video of humans performing gestures.

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

[2]  Rama Chellappa,et al.  View independent human body pose estimation from a single perspective image , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, SIGGRAPH 2004.

[4]  Neil D. Lawrence,et al.  Fast Sparse Gaussian Process Methods: The Informative Vector Machine , 2002, NIPS.

[5]  Mun Wai Lee,et al.  Proposal maps driven MCMC for estimating human body pose in static images , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[6]  Ioannis A. Kakadiaris,et al.  Estimating Anthropometry and Pose from a Single Uncalibrated Image , 2001, Comput. Vis. Image Underst..

[7]  Camillo J. Taylor,et al.  Reconstruction of articulated objects from point correspondences in a single uncalibrated image , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  Camillo J. Taylor,et al.  Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image , 2000, Comput. Vis. Image Underst..

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

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

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

[12]  Rómer Rosales,et al.  Specialized mappings and the estimation of human body pose from a single image , 2000, Proceedings Workshop on Human Motion.

[13]  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..

[14]  Stan Sclaroff,et al.  Database Indexing Methods for 3D Hand Pose Estimation , 2003, Gesture Workshop.

[15]  Christopher K. I. Williams.  Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond , 1999, Learning in Graphical Models.

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

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