[1]万红,贾上坤,崔恩泽,等.基于人体姿态估计的站桩数字化表达与评估[J].郑州大学学报(工学版),2022,43(04):8-15.
 [J].Journal of Zhengzhou University (Engineering Science),2022,43(04):8-15.
点击复制

基于人体姿态估计的站桩数字化表达与评估()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年04期
页码:
8-15
栏目:
出版日期:
2022-07-03

文章信息/Info

作者:
万红贾上坤崔恩泽张俊明
文献标志码:
A
摘要:
站桩看似简单实则深奥 为解读站桩过程的内在规律 , 辅助学员站桩训练 , 结合实验和数据分 , 基于人体姿态估计技术 , 提取站桩过程的动态特征参数 , 构建站桩姿态数字化表达与评估体系 ,利用 OpenPose 人体姿态估计算法从站桩视频中提取人体关键点;其次,根据站桩要领确定数字化表达的关键特征参数;接着采用动态时间规整算法和判别分析法分别计算各特征参数的评估指标;最后, 基于长期站桩数据,使用变异系数法赋予各评估指标不同的权重,探讨各特征参数的重要性并对站桩效 能进行综合评估具体实施包括:设计一个从正面和侧面采集站桩视频的实验,6 名太极拳专家和 22 名学员参与这项研究,学员被分为实验组和对照组通过对专家组站桩参数的分析发现,站桩实则是一个动态过程,实验数据从正面侧面表达了不同部位的动态特征参数;同时跟踪实验组学员 8 个月的长期站桩数据,通过与专家数据的对比评估发现,躯干大腿膝关节和髋关节是站桩过程中更重要的身体部此外,经过数字化评估指导后,实验组学员的站桩质量得到明显提升,验证了数字化表达与评估体系对于辅助训练的有效性
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 con- structed. 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 anal- ysis 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 eval- uate 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 participa- ted 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 e- valuation and guidance, standing stake quality of students in the experimental group was significantly im- proved, which could verify the effectiveness of digital expression and evaluation system for auxiliary training.

更新日期/Last Update: 2022-07-03