Research of Nonlinear Time Series Prediction Method for Motion Capture

Authors

Tianyu Huang, Beijing Institute of Technology, Beijing 100081, China;
Yunying Guo, Beijing Institute of Technology, Beijing 100081, China;

Abstract

Abstract: In this paper, we study the nonlinear time series prediction method for action capture. A prediction method based on the capture data is studied and implemented by analyzing human motion data to solve the data loss and correction problem caused by sensor failure. Based on this research purpose, the simulation experiment assumes that a sensor in the sequence of actions fails, then uses eight kinds of machine learning methods, and evaluates them with six indexes. The prediction results of different methods are compared and the predicted motions are visualized. Through the experiments, data prediction accuracy by random forest, decision tree, nearest neighbor (KNN) method can reach more than 90%. Thus, the nonlinear time series prediction method for motion capture can accurately reconstruct the action.

Recommended Citation

Huang, Tianyu and Guo, Yunying (2019) "Research of Nonlinear Time Series Prediction Method for Motion Capture," Journal of System Simulation: Vol. 30: Iss. 7, Article 47.
DOI: 10.16182/j.issn1004731x.joss.201807047
Available at: https://dc-china-simulation.researchcommons.org/journal/vol30/iss7/47

First Page

2808

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201807047

Last Page

2815

CLC

TP391.72

Recommended Citation

Tianyu Huang, Yunying Guo. Research of Nonlinear Time Series Prediction Method for Motion Capture[J]. Journal of System Simulation, 2018, 30(7): 2808-2815.

DOI

10.16182/j.issn1004731x.joss.201807047