Sports training posture recognition method based on Kinect body sensor and internet of things technology
Abstract
Most of the routine sports training posture recognition uses the principle of image processing method, which has strong limitations, and there is a problem of data loss in the recognition process. The recognition error is large, which reduces the accuracy of the recognition results. Based on this, a new method of sports training posture recognition is proposed by introducing Kinect body sensor and Internet of Things technology. First, the mathematical description method is used to model the human body in three dimensions to represent the continuous posture changes of the trainer. Secondly, Kinect somatosensory sensor and the Internet of Things technology collect the sports training action information of trainers, track and capture the movement of limbs and the whole body, and extract the sports training behavior characteristics of the recognized people. On this basis, the recognition algorithm of sports training posture is designed to achieve the goal of sports training posture recognition. The experimental results show that after the application of the new method, the recognition error of sports training posture is small and the recognition accuracy is high.
References
1. Liu J, Tsujinaga S, Chai S, Sun H, Tateyama T, Iwamoto Y. Single Image Depth Map Estimation for Improving Posture Recognition. IEEE sensors journal 2021; 21(23):26997-27004.
2. Jiang H, Tsai S B. An Empirical Study on Sports Combination Training Action Recognition Based on SMO Algorithm Optimization Model and Artificial Intelligence. Mathematical Problems in Engineering 2021; 2021:1-11.
3. Li C, Cui J. Intelligent Sports Training System Based on Artificial Intelligence and Big Data. Mobile Information Systems 2021; 2021(1):1-11.
4. Wu M, Du D, Li Y, Bai W, Liu W. Multi-cascade Perceptual Human Posture Recognition Enhancement Network. IEEE Access 2021; 9: 64256-64266.
5. Xu Y. A Sports Training Video Classification Model Based on Deep Learning. Scientific Programming 2021; 2021(5):1-11.
6. Envelope M, Rlpdm B, Vfdlj B. Gesture recognition of wrist motion based on wearables sensors. Procedia Computer Science 2022; 210:181-188.
7. Li J, Ray S, Rajanna V, Hammond H. Evaluating the Performance of Machine Learning Algorithms in Gaze Gesture Recognition Systems. IEEE Access 2022; 10:1020-1035.
8. Xia Z, Xing J, Wang C, Li X. Gesture Recognition Algorithm of Human Motion Target Based on Deep Neural Network. Mobile Information Systems 2021; 2021(3):1-12.
9. Tu M. Gesture Detection and Recognition Based on Pyramid Frequency Feature Fusion Module and Multiscale Attention in Human-Computer Interaction. Mathematical Problems in Engineering 2021; 2021(7):1-10.
10. Fronteddu G, Porcu S, Floris A, Atzori L. A dynamic hand gesture recognition dataset for human-computer interfaces. Computer Networks 2022; 205:108781.
11. Yu Z, Zhao J, Wang Y, He L, Wang S. Surface EMG-Based Instantaneous Hand Gesture Recognition Using Convolutional Neural Network with the Transfer Learning Method. Sensors 2021; 21(7):2540.
12. Nallabolu P, Li Z, Hong H, Li C. Human Presence Sensing and Gesture Recognition for Smart Home Applications with Moving and Stationary Clutter Suppression Using a 60-GHz Digital Beamforming FMCW Radar. IEEE Access 2021; 9: 72857-72866.
13. Silva B, Melo D, Pombo N, Xu L. Internet of Things Assisted Monitoring based on a Ultrasound-based Gesture Recognition Contactless System. IEEE Access 2021; 9:90185-90194.
14. Peng Y, Wang J, Pang K, Liu L, Meng J, Li B. A Physiology-Based Flexible Strap Sensor for Gesture Recognition by Sensing Tendon Deformation. IEEE Sensors Journal 2021; 21(7):9449-9456.
15. Chmurski M, Zubert M, Bierzynski K, Santra A. Analysis of Edge-Optimized Deep Learning Classifiers for Radar-Based Gesture Recognition. IEEE Access 2021; 99:74406-74421.
16. Singh D K. 3D-CNN based Dynamic Gesture Recognition for Indian Sign Language Modeling. Procedia Computer Science 2021; 189:76-83.
17. Qiang B, Zhai Y, Zhou M, Yang X, Peng B, Wang Y. SqueezeNet and Fusion Network-Based Accurate Fast Fully Convolutional Network for Hand Detection and Gesture Recognition. IEEE Access 2021; 9:77661-77674.
18. Sun Y, Xiong H, Tan D K P, Han T X, Du R, Yang X. Moving Target Localization and Activity/Gesture Recognition for Indoor Radio Frequency Sensing Applications. IEEE sensors journal 2021; 21(21):24318-24326.
19. Ninos A, Hasch J, Alvarez M E P, Zwick T. Synthetic Radar Dataset Generator for Macro-Gesture Recognition. IEEE Access 2021; 9:76576-76584.
20. Zhang W, Wang J, Lan F. Dynamic Hand Gesture Recognition Based on Short-Term Sampling Neural Networks. IEEE/CAA Journal of Automatica Sinica 2021; 8(1):110-120.
21. Magrofuoco N, Roselli P, Vanderdonckt J. Two-dimensional Stroke Gesture Recognition: A Survey. ACM Computing Surveys 2021; 54(7):1-36.
22. Zeng X, Wu C, Ye W B. User-Definable Dynamic Hand Gesture Recognition Based on Doppler Radar and Few-Shot Learning. IEEE sensors journal 2021; 21(20):23224-23233.
23. Guo L, Lu Z, Yao L. Human-Machine Interaction Sensing Technology Based on Hand Gesture Recognition: A Review. IEEE transactions on human-machine systems 2021; 51(4):300-309.
24. Yu Z, Zhou B, Wan J, Wang P, Chen H, Liu X. Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition. IEEE Transactions on Image Processing 2021; 30:5626-5640.
25. Yang X, Zhu Y, Chen J. Intelligent Recognition of Multi Pose Face Images Based on Distance Constrained Optimization. Computer Simulation 2022;39(1):200-203.
Copyright (c) 2024 Jie Rong, Huijuan Dong, Lei Wang, Hongxia Sun
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
