LSTM-Based Lower Limbs Motion Reconstruction Using Low-Dimensional Input of Inertial Motion Capture System

doi:10.1109/JSEN.2019.2959639

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	LSTM-Based Lower Limbs Motion Reconstruction Using Low-Dimensional Input of Inertial Motion Capture System
	Tong, Lina 2; Liu, Rongkai 2; Peng, Liang 1
刊名	IEEE SENSORS JOURNAL
	2020-04-01
卷号	20 期号:7 页码:3667-3677
关键词	Motion reconstruction LSTM neural networks inertial motion capture dimension reduction sensor configuration
ISSN号	1530-437X
DOI	10.1109/JSEN.2019.2959639
通讯作者	Peng, Liang(liang.peng@ia.ac.cn)
英文摘要	Motion capture system has been widely used in virtual reality and rehabilitation area. This study proposed a data-driven method using low-dimensional input of inertial motion capture system to reconstruct human lower-limb motions. The long short-term memory (LSTM) neural network was used and an ensemble LSTM architecture was involved to improve reconstruction performance. Besides, the selection of optimal sensor configuration scheme and time-step parameters of LSTM network was discussed in detail. The reconstruction experiment shows that the method could get the lowest reconstruction joint angle root mean square (RMS) errors of 4.031 degrees on separated motion dataset, and 5.105 degrees on completely new dataset of synthetic motions using ensemble LSTM model with 18 base learner and three sensors units. The computational consumption test shows that the single and ensemble LSTM model spend 0.15ms and 0.91ms respectively to predict next frame. These findings demonstrate that the proposed method is effective and efficient for motions reconstruction of lower limbs.
资助项目	National Natural Science Foundation of China[61603386] ; National Natural Science Foundation of China[61720106012] ; National Natural Science Foundation of China[U1613228] ; Beijing Municipal Natural Science Foundation[Z170003]
WOS关键词	SENSORS
WOS研究方向	Engineering ; Instruments & Instrumentation ; Physics
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000524351800032
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38919]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Peng, Liang
作者单位	1.Chinese Acad Sci, Inst Automat, SKLMCCS, Beijing 100190, Peoples R China 2.China Univ Min & Technol Beijing, Elect Engn & Automat Dept, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Tong, Lina,Liu, Rongkai,Peng, Liang. LSTM-Based Lower Limbs Motion Reconstruction Using Low-Dimensional Input of Inertial Motion Capture System[J]. IEEE SENSORS JOURNAL,2020,20(7):3667-3677.
APA	Tong, Lina,Liu, Rongkai,&Peng, Liang.(2020).LSTM-Based Lower Limbs Motion Reconstruction Using Low-Dimensional Input of Inertial Motion Capture System.IEEE SENSORS JOURNAL,20(7),3667-3677.
MLA	Tong, Lina,et al."LSTM-Based Lower Limbs Motion Reconstruction Using Low-Dimensional Input of Inertial Motion Capture System".IEEE SENSORS JOURNAL 20.7(2020):3667-3677.