Research on Automatic Tracking of Marking Points in Sports Image Sequences Based on Machine Learning
DOI:
https://doi.org/10.54097/hset.v1i.489Keywords:
machine learning, sports images, image sequence, landmark tracking, shadow removalAbstract
The article aims at dynamically fusing sports images to obtain the constraint items of the edge highlight model. At the same time, we combine the RGB feature decomposition technology to extract the feature mark point features. The article combines the steady-state matching technology to complete the automatic tracking of the landmark points of the sports image sequence. Preliminary application results show that this method has low requirements on the experimental environment, strong robustness, and high recognition rate. It can not only be used for human motion analysis, but also has great application potential for automatic tracking of moving targets in other free backgrounds.
Downloads
References
Yang Qiuju, Zhou Penghui. Automatic segmentation of auroral images based on machine learning. Chinese Journal of Geophysics, vol. 63, pp.15-20, January 2020.
Sun Dong, Song Yang, Cen Xuanzhen, et al. Research Progress of Unmarked Recognition of Sports Action Based on Computer Vision. Journal of Shanghai Institute of Physical Education, vol. 45, pp.16-22, September 2021.
Wei Tong, Zhou Yinhe. Blind track image positioning based on machine learning recognition and labeled watershed segmentation. Optics and Precision Engineering, vol. 15, pp.10-19, January 2019.
Huang Xiaolong. Research on Feature Detail Recognition of Astronomical Photoelectric Images Based on Machine Learning. Automation and Instrumentation, vol. 4, pp.4-11, June 2020.
Lu Laibing, Bruce Lee. The clustering and evolution of artificial intelligence technology in the field of international sports. Journal of Shandong Institute of Physical Education, vol. 36, pp. 12-19, March 2020.
Li Jing, Fan Wenliang, Lei Ziqiao, et al. Recognition of Parkinson's patients based on machine learning model of magnetic resonance diffusion tensor imaging. Chinese Medical Equipment, vol. 36, pp.45-47, October 2021.
Ye Chunming, Zhao Shengwen, Yang Xiuhong, et al. Analysis and prediction of young athletes' ability to respond to the new crown pneumonia epidemic based on machine learning. Journal of Physical Education, vol. 27, pp. 68-70, March 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
