连续康复训练动作分割与评估

doi:10.16183/j.cnki.jsjtu.2021.458

上海交通大学学报 ›› 2023, Vol. 57 ›› Issue (5): 533-544.doi: 10.16183/j.cnki.jsjtu.2021.458

所属专题：《上海交通大学学报》2023年“生物医学工程”专题

连续康复训练动作分割与评估

胡铭轩¹, 乔钧², 张执南¹()

1.上海交通大学机械与动力工程学院, 上海 200240
2.上海市长宁区精神卫生中心康复科, 上海 200335

收稿日期:2021-11-16 修回日期:2022-01-23 接受日期:2022-02-14 出版日期:2023-05-28 发布日期:2023-06-02
通讯作者: 张执南 E-mail:zhinanz@sjtu.edu.cn.
作者简介:胡铭轩(1997-),硕士生,从事医工交叉研究.
基金资助:
医工交叉研究基金(YG2019QNA11)

Segmentation and Evaluation of Continuous Rehabilitation Exercises

HU Mingxuan¹, QIAO Jun², ZHANG Zhinan¹()

1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. Department of Rehabilitation, Shanghai Changning Mental Health Center, Shanghai 200335, China

Received:2021-11-16 Revised:2022-01-23 Accepted:2022-02-14 Online:2023-05-28 Published:2023-06-02
Contact: ZHANG Zhinan E-mail:zhinanz@sjtu.edu.cn.

摘要/Abstract

摘要：

为提高对康复训练动作反馈的准确性和客观性以及康复患者在康复训练中的积极性和自律性,建立一种能够处理人体连续康复训练动作数据的动作评估方法.首先,提出一种基于高斯混合模型的动作分割方法,从同一动作的连续重复运动序列中提取单次动作数据.其次,根据相关先验知识,提出结合显著运动特征动态时间规整距离评估与高斯混合模型似然评估的多特征融合动作评估方法,从康复训练动作的整体动作与局部关节信息两方面进行动作评估.结果表明:动作分割方法能够很好地分割连续重复动作的运动数据,在数据集上分割动作的正确率达到95%以上;多特征融合动作评估方法有效地提高健康样本与康复患者样本之间动作评估的区分度,使得健康样本动作分数在0~1的评分范围内主要分布在0.93~0.94的得分区间,患者样本则主要分布在0.81~0.89的得分区间.

关键词: 动作评估, 动作分割, 高斯混合模型, 动态时间规整算法

Abstract:

To provide an accurate and objective feedback on rehabilitation training movements and to improve the motivation of rehabilitation patients in rehabilitation training, a motion evaluation method capable of processing continuous human rehabilitation training movement data is proposed. First, a motion segmentation method based on the Gaussian mixture model (GMM) is developed to extract single motion repetition from continuous repetitive motion sequences of the same motion. Then, based on relevant a priori knowledge, a multi-feature fusion motion evaluation method combining significant motion feature dynamic time warping (DTW) distance evluation and Gaussian mixture model likelihood evaluation is proposed to perform motion evaluation in both the overall motion feature and local joint information of rehabilitation exercises. The results show that the motion segmentation method can segment the motion data of continuous repetitive motions well, and the correct rate of segmented motions on the dataset reaches more than 95%. The multi-feature fusion motion evaluation method effectively improves the differentiation of motion evaluation between healthy samples and rehabilitation patient samples, so that the motion scores of healthy samples are mainly distributed in the range of 0.93—0.94 on a scale of 0—1, while the motion scores of patient samples are mainly distributed in the range of 0.81—0.89.

Key words: motion evaluation, motion segmentation, Gaussian mixture model (GMM), dynamic time warping (DTW)

中图分类号:

R496

胡铭轩, 乔钧, 张执南. 连续康复训练动作分割与评估[J]. 上海交通大学学报, 2023, 57(5): 533-544.

HU Mingxuan, QIAO Jun, ZHANG Zhinan. Segmentation and Evaluation of Continuous Rehabilitation Exercises[J]. Journal of Shanghai Jiao Tong University, 2023, 57(5): 533-544.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

表1

表2

图9

表3

图10

图11

参考文献 21

[1]	崔迪. 虚拟环境下远程自适应康复训练系统与评估模型研究[D]. 宁波: 中国科学院大学(中国科学院宁波材料技术与工程研究所), 2017.
	CUI Di. Research on adaptability and evaluation model of remote rehabilitation training system in virtual environment[D]. Ningbo: Ningbo Institute of Material Technology, Chinese Academy of Sciences, 2017.
[2]	LUNENBURGER L, WELLNER M, BANZ R, et al. Virtual Performance-Enhancing Reality (ViPER) for robot-assisted gait training[C]//2006 International Workshop on Virtual Rehabilitation. New York, USA: IEEE, 2006: 174-177.
[3]	耿松松. 中国残疾人康复现状与问题研究[D]. 兰州: 兰州大学, 2013.
	GENG Songsong. Rehabilitation and problems on disabled in China[D]. Lanzhou: Lanzhou University, 2013.
[4]	KOMATIREDDY R, CHOKSHI A, BASNETT J, et al. Quality and quantity of rehabilitation exercises delivered by a 3-D motion controlled camera: A pilot study[J]. International Journal of Physical Medicine & Rehabilitation, 2014, 2(4): 214.
[5]	JOHANSSON B B. Current trends in stroke rehabilitation. A review with focus on brain plasticity[J]. Acta Neurologica Scandinavica, 2011, 123(3): 147-159. doi: 10.1111/j.1600-0404.2010.01417.x pmid: 20726844
[6]	TEYHEN D S, SHAFFER S W, LORENSON C L, et al. The functional movement screen: A reliability study[J]. The Journal of Orthopaedic & Sports Physical Therapy, 2012, 42(6): 530-540.
[7]	DEAKIN A, HILL H, POMEROY V M. Rough guide to the Fugl-Meyer assessment: Upper limb section[J]. Physiotherapy, 2003, 89(12): 751-763. doi: 10.1016/S0031-9406(05)60502-0 URL
[8]	ZHANG Z, FANG Q, GU X D. Objective assessment of upper-limb mobility for poststroke rehabilitation[J]. IEEE Transactions on Bio-medical Engineering, 2016, 63(4): 859-868. doi: 10.1109/TBME.2015.2477095 pmid: 26357394
[9]	汤翾, 黄襄念, 周杉. 基于Kinect的肩周炎康复训练动作识别系统研究[J]. 现代计算机(专业版), 2014(23): 53-55.
	TANG Xuan, HUANG Xiangnian, ZHOU Shan. Research on the frozen rehabilitation training action recognition system based on kinect[J]. Modern Computer, 2014(23): 53-55.
[10]	杨文璐, 王杰, 夏斌, 等. 基于Kinect的下肢体康复动作评估系统[J]. 传感器与微系统, 2017, 36(1): 91-94.
	YANG Wenlu, WANG Jie, XIA Bin, et al. Assessment system of lower limb rehabilitation action based on Kinect[J]. Transducer & Microsystem Technologies, 2017, 36(1): 91-94.
[11]	吴齐云, 战荫伟, 邵阳. 基于DTW和K-means的动作匹配和评估[J]. 电子技术应用, 2016, 42(8): 141-143.
	WU Qiyun, ZHAN Yinwei, SHAO Yang. Human motion matching and evaluation based on STDTW and K-means[J]. Application of Electronic Technique, 2016, 42(8): 141-143.
[12]	HOUMANFAR R, KARG M, KULIĆ D. Movement analysis of rehabilitation exercises: Distance metrics for measuring patient progress[J]. IEEE Systems Journal, 2016, 10(3): 1014-1025. doi: 10.1109/JSYST.2014.2327792 URL
[13]	SU C J, CHIANG C Y, HUANG J Y. Kinect-enabled home-based rehabilitation system using Dynamic Time Warping and fuzzy logic[J]. Applied Soft Computing, 2014, 22: 652-666. doi: 10.1016/j.asoc.2014.04.020 URL
[14]	CAPECCI M, CERAVOLO M G, FERRACUTI F, et al. A Hidden Semi-Markov Model based approach for rehabilitation exercise assessment[J]. Journal of Biomedical Informatics, 2018, 78: 1-11. doi: S1532-0464(17)30282-4 pmid: 29277330
[15]	LIAO Y L, VAKANSKI A, XIAN M. A deep learning framework for assessing physical rehabilitation exercises[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2020, 28(2): 468-477.
[16]	AR I, AKGUL Y S. A computerized recognition system for the home-based physiotherapy exercises using an RGBD camera[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: A Publication of the IEEE Engineering in Medicine & Biology Society, 2014, 22(6): 1160-1171.
[17]	闫航, 陈刚, 崔莉亚, 等. 基于单目视觉的在线人体康复动作识别[J]. 计算机应用与软件, 2021, 38(2): 171-178.
	YAN Hang, CHEN Gang, CUI Liya, et al. Online human rehabilitation action recognition based on monocular vision[J]. Computer Applications & Software, 2021, 38(2): 171-178.
[18]	LIN J F S, KULIĆ D. Online segmentation of human motion for automated rehabilitation exercise analysis[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: A Publication of the IEEE Engineering in Medicine & Biology Society, 2014, 22(1): 168-180.
[19]	李航. 统计学习方法[M]. 第2版. 北京: 清华大学出版社, 2019.
	LI Hang. Statistical learning methods[M]. 2nd ed. Beijing: Tsinghua University Press, 2019.
[20]	HODA M, HODA Y, HAGE A, et al. Cloud-based rehabilitation and recovery prediction system for stroke patients[J]. Cluster Computing, 2015, 18(2): 803-815. doi: 10.1007/s10586-015-0448-6 URL
[21]	VAKANSKI A, JUN H P, PAUL D, et al. A data set of human body movements for physical rehabilitation exercises[J]. Data, 2018, 3(1): 2. doi: 10.3390/data3010002 URL

比较对象	欧氏距离	马氏距离	DTW 距离	GMM 似然	多特征融合 (本文方法)
不同实验对象	0.335	0.144	0.345	0.357	0.425
同一实验对象	0.523	0.379	0.529	0.584	0.609

样本类型	GMM似然评估		显著特征DTW距离评估		多特征融合评估(本文方法)
样本类型	评分区间	平均值	评分区间	平均值	评分区间	平均值
健康样本	[0.925, 0.941]	0.933	[0.935, 0.949]	0.940	[0.930, 0.944]	0.937
患者样本	[0.854, 0.908]	0.874	[0.774, 0.889]	0.827	[0.817, 0.892]	0.851

连续康复训练动作分割与评估

Segmentation and Evaluation of Continuous Rehabilitation Exercises

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 21

相关文章 3

编辑推荐

Metrics

本文评价

[1]	张文安, 高伟展, 刘安东. 基于动态运动原语和自适应控制的机器人技能学习[J]. 上海交通大学学报, 2023, 57(3): 354-365.
[2]	贾晓立，江晓波，蒋三新，刘佩林. 利用结构特征的语音压缩感知重建算法[J]. 上海交通大学学报（自然版）, 2017, 51(9): 1111-1116.
[3]	余昊a，孙锬锋a,b，蒋兴浩a,b. 基于光流块统计特征的视频异常行为检测算法[J]. 上海交通大学学报（自然版）, 2015, 49(08): 1199-1204.

样本类型	样本总数	正确分割数	错误分割数
健康样本	100	97	3
患者样本	100	94	6