Learning and Tracking Cyclic Human Motion

We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segmenting these data automatically into "cycles". Then the mean and the principal components of the cycles are computed using a new algorithm that accounts for missing information and enforces smooth transitions between cycles. The learned temporal model provides a prior probability distribution over human motions that can be used in a Bayesian framework for tracking human subjects in complex monocular video sequences and recovering their 3D motion.

[1]  Steven M. Seitz,et al.  Affine invariant detection of periodic motion , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  A ne Invariant Detection of Periodic Motion , 1994 .

[3]  James W. Davis,et al.  An appearance-based representation of action , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[4]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[5]  W. Freeman,et al.  Bayesian Estimation of 3-D Human Motion , 1998 .

[6]  Michael J. Black,et al.  Parameterized modeling and recognition of activities in temporal surfaces , 1999 .

[7]  James M. Rehg,et al.  A multiple hypothesis approach to figure tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  Michael J. Black,et al.  Parameterized Modeling and Recognition of Activities , 1999, Comput. Vis. Image Underst..

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

[10]  Trevor Hastie,et al.  Learning and Tracking Human Motion Using Functional Analysis , 2000 .

[11]  Trevor Hastie,et al.  Imputing Missing Data for Gene Expression Arrays , 2001 .