A human motion estimation method based on GP-UKF

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.

参考文章(17)
Christopher K I Williams, Carl Edward Rasmussen, Gaussian Processes for Machine Learning ,(2005)
Renato Grasso, Pascal Prévost, Yuri P Ivanenko, Alain Berthoz, Eye-head coordination for the steering of locomotion in humans: an anticipatory synergy Neuroscience Letters. ,vol. 253, pp. 115- 118 ,(1998) , 10.1016/S0304-3940(98)00625-9
D. Kelly, F. Boland, Motion Model Selection in Tracking Humans irish signals and systems conference. pp. 363- 368 ,(2006) , 10.1049/CP:20060464
M. Hollands, K. Sorensen, A. Patla, Effects of head immobilization on the coordination and control of head and body reorientation and translation during steering Experimental Brain Research. ,vol. 140, pp. 223- 233 ,(2001) , 10.1007/S002210100811
Simon J. Julier, Jeffrey K. Uhlmann, New extension of the Kalman filter to nonlinear systems Signal processing, sensor fusion, and target recognition. Conference. ,vol. 3068, pp. 182- 193 ,(1997) , 10.1117/12.280797
David Ellis, Eric Sommerlade, Ian Reid, Modelling pedestrian trajectory patterns with Gaussian processes international conference on computer vision. pp. 1229- 1234 ,(2009) , 10.1109/ICCVW.2009.5457470
Hongbo Wang, Kazuhiro Kosuge, Attractor design and prediction-based adaption for a robot waltz dancer in physical human-robot interaction world congress on intelligent control and automation. pp. 3810- 3815 ,(2012) , 10.1109/WCICA.2012.6359108
Roderick Murray-Smith, Agathe Girard, Carl Edward Rasmussen, Joaquin Quiñonero Candela, Gaussian Process Priors with Uncertain Inputs Application to Multiple-Step Ahead Time Series Forecasting neural information processing systems. ,vol. 15, pp. 545- 552 ,(2002)
Jonathan Ko, Daniel J. Klein, Dieter Fox, Dirk Haehnel, GP-UKF: Unscented kalman filters with Gaussian process prediction and observation models intelligent robots and systems. pp. 1901- 1907 ,(2007) , 10.1109/IROS.2007.4399284