Research on Human Pose Capture Based on the Deep Learning Algorithm
A method based on the deep learning algorithm is proposed to accurately capture the posture of the human body. It is one of the important means to improve athletes’ competitive level in modern sports to accurately analyze the posture of sports training by technical means. Aiming at the application d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Control Science and Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/7215500 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832565743088041984 |
|---|---|
| author | Wenbin Xie Xueyun Gu Xiuming Li Luqi Zheng Guodong Li Haisheng Lu Huakang Li |
| author_facet | Wenbin Xie Xueyun Gu Xiuming Li Luqi Zheng Guodong Li Haisheng Lu Huakang Li |
| author_sort | Wenbin Xie |
| collection | DOAJ |
| description | A method based on the deep learning algorithm is proposed to accurately capture the posture of the human body. It is one of the important means to improve athletes’ competitive level in modern sports to accurately analyze the posture of sports training by technical means. Aiming at the application demand of using artificial intelligence technology to accurately analyze and predict the motion training posture, a motion posture analysis and prediction system based on deep learning is designed in this paper. Based on the Arduino embedded development board and equipped with multiple IMU sensors, the scheme established a system to collect accurate human movement data such as speed and acceleration by using stepper motors and obtained accurate human movement data. The experimental results show that these models have been trained with H3.6 m data sets. The sampling frequency was reduced to 25 Hz, and the joint angles were converted into exponential graphs. When the time window covers approximately 1 660 ms, the loop network will be initialized to 40 frames, equivalent to 1 600 ms. For each action, a separate pretrained recursive model is used. It is proved that the method based on deep learning can reduce the prediction error of fine-tuning specific movements and effectively classify and predict the movements not included in the original training data. |
| format | Article |
| id | doaj-art-c270ef6738cc43c48b0c167698183218 |
| institution | Kabale University |
| issn | 1687-5257 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Control Science and Engineering |
| spelling | doaj-art-c270ef6738cc43c48b0c1676981832182025-02-03T01:06:46ZengWileyJournal of Control Science and Engineering1687-52572022-01-01202210.1155/2022/7215500Research on Human Pose Capture Based on the Deep Learning AlgorithmWenbin Xie0Xueyun Gu1Xiuming Li2Luqi Zheng3Guodong Li4Haisheng Lu5Huakang Li6Beibu Gulf UniversityBeibu Gulf UniversityGuangxi Research Institute of Mechanical IndustryBeibu Gulf UniversityBeibu Gulf UniversityBeibu Gulf UniversityBeibu Gulf UniversityA method based on the deep learning algorithm is proposed to accurately capture the posture of the human body. It is one of the important means to improve athletes’ competitive level in modern sports to accurately analyze the posture of sports training by technical means. Aiming at the application demand of using artificial intelligence technology to accurately analyze and predict the motion training posture, a motion posture analysis and prediction system based on deep learning is designed in this paper. Based on the Arduino embedded development board and equipped with multiple IMU sensors, the scheme established a system to collect accurate human movement data such as speed and acceleration by using stepper motors and obtained accurate human movement data. The experimental results show that these models have been trained with H3.6 m data sets. The sampling frequency was reduced to 25 Hz, and the joint angles were converted into exponential graphs. When the time window covers approximately 1 660 ms, the loop network will be initialized to 40 frames, equivalent to 1 600 ms. For each action, a separate pretrained recursive model is used. It is proved that the method based on deep learning can reduce the prediction error of fine-tuning specific movements and effectively classify and predict the movements not included in the original training data.http://dx.doi.org/10.1155/2022/7215500 |
| spellingShingle | Wenbin Xie Xueyun Gu Xiuming Li Luqi Zheng Guodong Li Haisheng Lu Huakang Li Research on Human Pose Capture Based on the Deep Learning Algorithm Journal of Control Science and Engineering |
| title | Research on Human Pose Capture Based on the Deep Learning Algorithm |
| title_full | Research on Human Pose Capture Based on the Deep Learning Algorithm |
| title_fullStr | Research on Human Pose Capture Based on the Deep Learning Algorithm |
| title_full_unstemmed | Research on Human Pose Capture Based on the Deep Learning Algorithm |
| title_short | Research on Human Pose Capture Based on the Deep Learning Algorithm |
| title_sort | research on human pose capture based on the deep learning algorithm |
| url | http://dx.doi.org/10.1155/2022/7215500 |
| work_keys_str_mv | AT wenbinxie researchonhumanposecapturebasedonthedeeplearningalgorithm AT xueyungu researchonhumanposecapturebasedonthedeeplearningalgorithm AT xiumingli researchonhumanposecapturebasedonthedeeplearningalgorithm AT luqizheng researchonhumanposecapturebasedonthedeeplearningalgorithm AT guodongli researchonhumanposecapturebasedonthedeeplearningalgorithm AT haishenglu researchonhumanposecapturebasedonthedeeplearningalgorithm AT huakangli researchonhumanposecapturebasedonthedeeplearningalgorithm |