作者: Ziyou Wang , Jun Kinugawa , Hongbo Wang , Kosuge Kazahiro
DOI: 10.1109/ICINFA.2014.6932836
关键词:
摘要: A novel human motion estimation method is presented in this paper. The of the estimated by an Unscented Kalman filter (UKF), which a nonlinear dynamic model used to predict trajectory human. This obtained from sample data using Gaussian Process (GP) regression. includes information body segment posture and collected capture system. GP-UKF can extract underlying dynamics data, with future non-linear transition be predicted. experiment results show that proposed has improved accuracy over conventional method.