Human Motion Recognition Method Using Hybrid CNN-HMM

被引：0

作者：

Zhang Z. ^{[1
,2
]}

Zhang S. ^{[1
]}

Zhao Z. ^{[1
,2
]}

Liu Y. ^{[1
,2
]}

Kan Y. ^{[1
]}

Tu Z. ^{[2
]}

机构：

[1] School of Mechanical Engineering, Anhui Polytechnic University, Wuhu

[2] Wuhu Ceprei Robot Technoligy Research Co., Ltd., Wuhu

来源：

Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | 2022年 / 51卷 / 03期

关键词：

Convolutional neural networks; Hidden Markov model; Human motion recognition; Pattern recognition and intelligent system; Perception neuron;

D O I：

10.12178/1001-0548.2021326

中图分类号：

学科分类号：

摘要：

Aiming at the problems of poor detection accuracy of current human motion recognition algorithms and the diversity of experimental scenes, a new human motion recognition method based on hybrid convolutional neural network-hidden Markov model (CNN-HMM) is proposed. In order to verify the effectiveness of the method, we establish three sets of human rehabilitation training motion models including one standard motion posture and five non-standard motion postures for leg-lifting, squat and hip bridge, respectively. The experimental data are obtained by the wearable inertial motion capture system, Perception Neuron 2.0 (PN2.0). Finally, the performance of the proposed method is evaluated in terms of accuracy, sensitivity and specificity. Three groups of the experimental results show that the proposed method can distinguish the six different motion gestures with a high average recognition rate of 97.00%, which is 5.78% higher than the single CNN method. Copyright ©2022 Journal of University of Electronic Science and Technology of China. All rights reserved.

引用

页码：444 / 451

页数：7

共 23 条

[1] LI N, CHENG X, GUO H, Et al., Recognizing human interactions by genetic algorithm-based random forest spatio-temporal correlation, Pattern Analysis & Applications, 19, 1, pp. 267-282, (2016)
[2] ZHANG X., Application of human motion recognition utilizing deep learning and smart wearable device in sports, International Journal of System Assurance Engineering and Management, 12, 4, pp. 835-843, (2021)
[3] PAN Z G, LI C., Robust basketball sports recognition by leveraging motion block estimation, Signal Processing: Image Communication, 83, (2020)
[4] XING M M, WEI G H, LIU J, Et al., A review on multi-modal human motion representation recognition and its application in orthopedic rehabilitation training, Journal of Biomedical Engineering, 37, 1, pp. 180-184, (2020)
[5] JI S, XU W, YANG M, Et al., 3D convolutional neural networks for human action recognition, IEEE Transactions on Pattern Analysis & Machine Intelligence, 35, 1, pp. 221-231, (2013)
[6] HABIB M, FARIS M, QADDOURA R, Et al., Toward an automatic quality assessment of voice-based telemedicine consultations: A deep learning approach, Sensors, 21, 9, pp. 1-26, (2021)
[7] HAN K, HUANG Z F., Falling behavior recognition method based on dynamic characteristics of human body posture, Journal of Hunan University (Natural Sciences), 47, 12, pp. 69-76, (2020)
[8] HU Q S, ZHANG L, DING J, Et al., Data encoding and CNN accurate recognition of human body motion, Journal of University of Electronic Science and Technology of China, 49, 3, pp. 473-480, (2020)
[9] JIANG L B, ZHOU X L, CHE L., Few-shot learning for human motion recognition based on carrier-free UWB radar, Acta Electronica Sinica, 48, 3, pp. 602-615, (2020)
[10] KHAN M A, JAVED K, SABA T., Human action recognition using fusion of multiview and deep features: An application to video surveillance, Multimedia Tools and Applications, (2020)

← 1 2 3 →