Digital Expression and Evaluation of Standing Stake Based on Human Pose Estimation

NAVIGATE

Table of Contents

STATISTICS

Viewed1414

Downloads1128

Digital Expression and Evaluation of Standing Stake Based on Human Pose Estimation

[HTML] PDF下载 (1128)

[1]WAN Hong,JIA Shangkun,CUI Enze,et al.Digital Expression and Evaluation of Standing Stake Based on Human Pose Estimation[J].Journal of Zhengzhou University (Engineering Science),2022,43(04):8-15.[doi:10.13705/j.issn.1671-6833.2022.04.023]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 43卷 Number of periods: 2022 04 Page number: 8-15 Column: Public date: 2022-07-03

Title:: Digital Expression and Evaluation of Standing Stake Based on Human Pose Estimation

Author(s):: WAN Hong1; 2; JIA Shangkun1; 2; CUI Enze1; 2; ZHANG Junming1; 2; 1.School of Electrical Engineering,Zhengzhou University,Zhengzhou 450001,China;
2.Henan Key Laboratory of Brain Science and Brain Computer Interface Technology,Zhengzhou University,Zhengzhou 450001,China

Keywords:: standing stake; OpenPose; characteristic parameters; evaluation index; auxiliary training

CLC:: TP391

DOI:: 10.13705/j.issn.1671-6833.2022.04.023

Abstract:: Standing stake seems simple but actually profound.In order to interpret the internal law of standing stake process and assist students in standing stake training,combined with experiments and data analysis,based on the human pose estimation technology,the dynamic characteristic parameters of standing stake process were extracted,and the digital expression and evaluation system of standing stake posture was constructed.Firstly,the human pose estimation algorithm OpenPose was used to extract the human keypoints from the video of standing stake.Secondly,the key characteristic parameters of digital expression were determined according to the essentials of standing stake.Then,the dynamic time warping algorithm and discriminant analysis method were used to calculate the evaluation indexes of each characteristic parameter.Finally,based on the long-term standing stake data,the coefficient of variation method was used to assign different weights to each evaluation index,to discuss the importance of each characteristic parameter and to comprehensively evaluate standing stake performance.The specific implementation included:designing an experiment to collect standing stake video from the front and side,six Tai Chi professional experts and twenty-two students participated in this research,and the students were divided into experimental and control groups.Through the analysis of standing stake parameters of the expert group,it was found that standing stake was actually a dynamic process,and the experimental data expressed the dynamic characteristic parameters of different parts from the front and side.At the same time,the long-term standing stake data of students in the experimental group was tracked for eight months.Through the comparative evaluation with the expert data,it revealed that the trunk,thigh,knee and hip were the more important body parts in standing stake process.In addition,after digital evaluation and guidance,standing stake quality of students in the experimental group was significantly improved,which could verify the effectiveness of digital expression and evaluation system for auxiliary training.

References:: [1] 蔡建平, 淮湛欣. 太极拳运动考评软件的设计与实现[ J] . 软件, 2012, 33(3) : 60-63.
CAI J P, HUAI Z X. Design & implementation of Taiji motion appraisal system [ J ] . Software, 2012, 33 (3) : 60-63.
[2] HASHIMOTO H, NAKAJIMA M, KAWATA S, et al. Skill level evaluation of Taijiquan based on 3D body motion analysis[C] / / 2014 IEEE International Conference on Industrial Technology. Piscataway: IEEE, 2014: 712-717.
[3] 漆才杰, 戴国斌. 太极( 定步) 推手动作识别系统的设计与研制[ J] . 武汉体育学院学报, 2015, 49 (8) : 52-56. QI C J, DAI G B. Design and development of Taichi pushing hands ( with fixed-foot stance ) movements recognition system[ J] . Journal of Wuhan institute of physical education, 2015, 49(8) : 52-56.
[4] 薛智宏, 张利英, 程振华, 等. 基于 Kinect 的原地太极拳辅助训练系统 [ J ] . 河北科技大学学报, 2017, 38(2) : 183-189.
XUE Z H, ZHANG L Y, CHENG Z H, et al. Research of Tai-Chi-Chuan auxiliary training system based on Kinect [ J] . Journal of Hebei university of science and technology, 2017, 38(2) : 183-189.
[5] TOMPSON J J, JAIN A, LECUN Y, et al. Joint training of a convolutional network and a graphical model for human pose estimation[EB / OL] . (2014- 09- 17) [2021-11-08] . https: / / arxiv. org / abs/ 1406. 2984.
[6] NING G H, ZHANG Z, HE Z Q. Knowledge-guided deep fractal neural networks for human pose estimation [ J ] . IEEE transactions on multimedia, 2018, 20 (5) : 1246-1259.
[7] 陈梦婷, 王兴刚, 刘文予. 基于密集深度插值的 3D 人体姿态估计方法[ J] . 郑州大学学报( 工学版) , 2021, 42(3) : 26-32.
CHEN M T, WANG X G, LIU W Y. Dense depth interpolation for 3D human pose estimation[ J] . Journal of Zhengzhou university ( engineering science) , 2021, 42(3) : 26-32.
[8] CAO Z, HIDALGO G, SIMON T, et al. OpenPose: realtime multi-person 2D pose estimation using part affinity fields[J]. IEEE transactions on pattern analysis and machine intelligence, 2021, 43(1): 172-186.
[9] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [ EB / OL] . (2015-04 - 10) [ 2021 - 11 - 08] . https: / / arxiv. org / abs/ 1409. 1556.
[10] KHAN A, HARIS M, NADEEM S S, et al. Virtual self defense trainer-analyzing and scoring user pose [ C] / / 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications. Piscataway: IEEE, 2020: 1-5.
[11] YADAV S K, SINGH A, GUPTA A, et al. Real-time Yoga recognition using deep learning[ J] . Neural computing and applications, 2019, 31(12) : 9349-9361.
[12] THAR M C, WINN K Z N, FUNABIKI N. A proposal of Yoga pose assessment method using pose detection for self-learning [ C ] / / 2019 International Conference on Advanced Information Technologies ( ICAIT) . Piscataway: IEEE, 2019: 137-142.
[13] 唐心宇, 宋爱国. 人体姿态估计及在康复训练情景交互中的应用[ J] . 仪器仪表学报, 2018, 39( 11) : 195-203.
TANG X Y, SONG A G. Human pose estimation and its implementation in scenario interaction system of rehabilitation training [ J] . Chinese journal of scientific instrument, 2018, 39(11) : 195-203.
[14] TAKEDA I, YAMADA A, ONODERA H. Artificial Intelligence-assisted motion capture for medical applications: a comparative study between markerless and passive marker motion capture[ J] . Computer methods in biomechanics and biomedical engineering, 2021, 24 (8) : 864-873.
[15] GIORGINO T. Computing and visualizing dynamic time warping alignments in R: the dtw package [ J] . Journal of statistical software, 2009, 31(7) : 1-24.
[16] YU X Q, XIONG S P. A dynamic time warping based algorithm to evaluate Kinect-enabled home-based physical rehabilitation exercises for older people[ J] . Sensors, 2019, 19(13) : 2882.
[17] 张勇, 党兰学. 线性判别分析特征提取稀疏表示人脸识别方法[ J] . 郑州大学学报 ( 工学版) , 2015, 36(2) : 94-98.
ZHANG Y, DANG L X. Sparse representation-based face recognition method by LDA feature extraction[ J] . Journal of Zhengzhou university ( engineering science) , 2015, 36(2) : 94-98

Similar References:

Memo

Last Update: 2022-07-03