Body Recognition Sports APP Based on Android System
DOI:
https://doi.org/10.62051/ijcsit.v3n3.45Keywords:
Image recognition, CNN Convolutional neural network, 3D residual model, Human behavior recognition research, AI online guidance functionAbstract
With the enhancement of health awareness, people are more and more inclined to improve the quality of life through exercise, but the wrong way of exercise may lead to muscle strain and other problems. To solve this problem, this study designed a motion aid APP integrated with posture recognition technology, aiming at guiding users to correct movements through real-time feedback. The APP's core function, "AI online guidance," combines computer vision and image recognition technology to capture user movement data through the camera and analyze it using deep learning algorithms to identify and correct the user's movement posture. In this study, we first discuss three main methods of human behavior recognition: based on deep neural networks, based on 3D residual model and based on 3D attention mechanism. The application and structure design of 3D shallow feature extraction module and 3D attention mechanism in human behavior recognition are introduced. Finally, this study describes the functional implementation of the APP, including action analysis, error point identification, improvement suggestion generation, and user interaction design. The results of this study show that the APP can effectively improve the accuracy of users' movements during sports, reduce the risk of sports injuries, increase the interest of sports, and improve users' subjective initiative.
Downloads
References
[1] Li Zhuoran. Posture recognition based on skeleton point marker research [D]. Shenyang university of technology, 2023. The DOI: 10.27322 /, dc nki. Gsgyu. 2023.001254.
[2] Li Jingjing, Huang Zhangjin, Zou Lu. Human motion recognition based on Convolutional networks of motion guidance graphs [J/OL]. Journal of Computer Aided Design and Graphics, 1-10 [2024-07-30]. HTTP: / / http://kns.cnki.net/kcms/detail/11.2925.TP.20240716.1755.002.html
[3] Cui Yanxin. Research on Human behavior Recognition Algorithm based on Deep Learning [D]. Hebei: Hebei Normal University,2023.
[4] An improved method of 3D residual neural network video pedestrian action classification [J]. Journal of Dalian Minzu University,2019,21(3):225-229. (in Chinese) DOI:10.3969/j.issn.1009-315X.2019.03.007.
[5] Li Xusheng. Remote sensing tree species recognition based on 3D residual Convolutional neural network algorithm [D]. Xinjiang: Xinjiang Agricultural University,2020.
[6] Wu Lijun, Li Binbin, Chen Zhicong, et al. Behavior recognition under 3D Multiple attention mechanism [J]. Journal of Fuzhou University (Natural Science Edition),2022,50(1):47-53. DOI:10.7631/issn.1000-2243.20496.
[7] Liu H, Tu J H, Liu M Y. Two-stream 3D convolutional neural network for skeleton-based action recognition[EB/OL]. [2022-08-10]. http://arxiv-org-s.webvpn.wbu.edu.cn:8118/ftp/arxiv/papers/1705/1705.08106.pdf
[8] Kim T S, Reiter A. Interpretable 3D human action analysis with temporal convolutional networks[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Los Alamitos: IEEE Computer Society Press, 2017: 1623-1631.
[9] Wang P C, Li Z Y, Hou Y H, et al. Action recognition based on joint trajectory maps using convolutional neural networks[C] //Proceedings of the 24th ACM International Conference on Multimedia. New York: ACM Press, 2016: 102-106
[10] Wu Jiahui, Zhou Tao, Luo Mingxin, et al. Design and development of Facial expression Recognition system based on C3D CNN [J]. Information & Computer,2022,34(14):104-107. (in Chinese) DOI:10.3969/j.issn.1003-9767.2022.14.032.
[11] Lu Hongtao, Zhang Qinchuan. A review on the application of deep convolutional neural networks in computer vision [J]. Data Acquisition and Processing, 2016, 31 (01): 1-17. DOI:10.16337/ J.1004-9037.2016.01.001.
[12] Yan S J, Xiong Y J, Lin D H. Spatial temporal graph convolutional networks for skeleton-based action recognition[C] //Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2018: Article No.912
[13] Wan Lei, Tong Xin, Sheng Mingwei, et al. Application of Softmax classifier for deep learning image classification [J]. Navigation and Control, 2019, 18 (06): 1-9+47. (in Chinese)
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
