|
|||||
|
|
Representing cyclic human motion using functional analysis |
|
| Authors: | Dirk Ormoneit Michael J Black Trevor Hastie Hedvig Kjellstrm |
| Affiliation: | aMarshall Wace LLP, 1/11 John Adam Street, London WC2N 6HT, UK bDepartment of Computer Science, Brown University, 115 Waterman Street, Box 1910, Providence, RI 02912, USA cDepartment of Statistics, Stanford University, Stanford, CA 94305, USA dDepartment of IR Systems, Swedish Defence Research Agency, SE-164 90 Stockholm, Sweden |
| 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. |
| Keywords: | Human motion Functional data analysis Missing data Singular value decomposition Principal component analysis Motion capture Tracking |
| 本文献已被 ScienceDirect 等数据库收录！ | |