Back
Representing cyclic human motion using functional analysis
We present a robust automatic method for modeling cyclic 3D human motion such as walking using motion-capture data. The pose of the body is represented by a time-series of joint angles which are automatically segmented into a sequence of motion cycles. The mean and the principal components of these cycles are computed using a new algorithm that enforces smooth transitions between the cycles by operating in the Fourier domain. Key to this method is its ability to automatically deal with noise and missing data. A learned walking model is then exploited for Bayesian tracking of 3D human motion.
@article{Ormoneit:IVC:2005, title = {Representing cyclic human motion using functional analysis}, journal = {Image and Vision Computing}, abstract = {We present a robust automatic method for modeling cyclic 3D human motion such as walking using motion-capture data. The pose of the body is represented by a time-series of joint angles which are automatically segmented into a sequence of motion cycles. The mean and the principal components of these cycles are computed using a new algorithm that enforces smooth transitions between the cycles by operating in the Fourier domain. Key to this method is its ability to automatically deal with noise and missing data. A learned walking model is then exploited for Bayesian tracking of 3D human motion.}, volume = {23}, number = {14}, pages = {1264--1276}, month = dec, year = {2005}, slug = {ormoneit-ivc-2005}, author = {Ormoneit, D. and Black, M. J. and Hastie, T. and Kjellstr{\"o}m, H.}, month_numeric = {12} }
More information