Nonlinear Synchronization for Automatic Learning of 3D Pose Variability in Human Motion Sequences

A dense matching algorithm that solves the problem of synchronizing prerecorded human motion sequences, which show different speeds and accelerations, is proposed. The approach is based on minimization of MRF energy and solves the problem by using Dynamic Programming. Additionally, an optimal sequence is automatically selected from the input dataset to be a time-scale pattern for all other sequences. The paper utilizes an action specific model which automatically learns the variability of 3D human postures observed in a set of training sequences. The model is trained using the public CMU motion capture dataset for the walking action, and a mean walking performance is automatically learnt. Additionally, statistics about the observed variability of the postures and motion direction are also computed at each time step. The synchronized motion sequences are used to learn a model of human motion for action recognition and full-body tracking purposes.

[1]  Xavier Varona,et al.  Action Spaces for Efficient Bayesian Tracking of Human Motion , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[2]  Atsushi Nakazawa,et al.  Matching and blending human motions temporal scaleable dynamic programming , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[3]  Vladimir M. Zatsiorsky.  Kinematics of human motion , 1998 .

[4]  Michael J. Black,et al.  Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Joseph B. Kruskall,et al.  The Symmetric Time-Warping Problem : From Continuous to Discrete , 1983 .

[6]  Xavier Varona,et al.  Posture Constraints for Bayesian Human Motion Tracking , 2006, AMDO.

[7]  Thomas B. Moeslund,et al.  A Survey of Computer Vision-Based Human Motion Capture , 2001, Comput. Vis. Image Underst..

[8]  John W. Fisher,et al.  Approximate Dynamic Programming for Communication-Constrained Sensor Network Management , 2007, IEEE Transactions on Signal Processing.

[9]  Stephen J. McKenna,et al.  Adaptive Learning of Statistical Appearance Models for 3D Human Tracking , 2002, BMVC.

[10]  Tieniu Tan,et al.  Recent developments in human motion analysis , 2003, Pattern Recognit..

[11]  Pankaj K. Agarwal,et al.  Faster Algorithms for Optimal Multiple Sequence Alignment Based on Pairwise Comparisons , 2006, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

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

[13]  Eamonn J. Keogh,et al.  Derivative Dynamic Time Warping , 2001, SDM.

[14]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[15]  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.

[16]  Xavier Varona,et al.  Analysis of Human Walking Based on aSpaces , 2004, AMDO.

[17]  F. Xavier Roca,et al.  3D Action Modeling and Reconstruction for 2D Human Body Tracking , 2005, ICAPR.

[18]  Minglun Gong,et al.  Real-Time Stereo Matching Using Orthogonal Reliability-Based Dynamic Programming , 2007, IEEE Transactions on Image Processing.