School of Physical Education and Health Science, Mudanjiang Normal University, Mudanjiang 157011, China.
School of Physical Education and Health Science, Mudanjiang Normal University, Mudanjiang 157011, China.
Prev Med. 2023 Aug;173:107592. doi: 10.1016/j.ypmed.2023.107592. Epub 2023 Jun 26.
The existing sports training methods are mainly aimed at the sports field environment. The traditional sports training is only based on the coaches' visual inspection and combined with their own experience to put forward suggestions, which is relatively inefficient, thus limiting the rise of athletes' sports training level to a certain extent. Based on this background, combining traditional physical education teaching methods with video image processing technology, especially using particle swarm optimization algorithm, can promote the application of human motion recognition technology in physical training. This paper mainly investigates the optimization process of particle swarm optimization algorithm and discusses the development of particle swarm optimization algorithm; Secondly, through video decoding, image noise removal, video enhancement and other methods, complete video image processing and establish the structure of the manikin to achieve the collection of key points of the target, and then collect relevant data with experimental methods The results show that the motion recognition system proposed in this paper can effectively detect the changes of athletes' sampling point path, and can be compared with standard movements, which has a good auxiliary role. With the application of video image processing technology in sports training becoming more and more common, athletes can analyze their training videos in a more intuitive way and find out shortcomings, so as to improve the training effect. This paper studies particle swarm optimization algorithm and applies it to the field of video image processing, which promotes the development of sports action recognition technology based on video processing.
现有的运动训练方法主要针对运动场环境。传统的运动训练仅基于教练的视觉检查，并结合自己的经验提出建议，这相对效率低下，从而在一定程度上限制了运动员运动训练水平的提高。基于此背景，将传统体育教学方法与视频图像处理技术相结合，特别是采用粒子群优化算法，可以促进人体运动识别技术在体育训练中的应用。本文主要研究粒子群优化算法的优化过程，并讨论粒子群优化算法的发展；其次，通过视频解码、图像去噪、视频增强等方法，完成视频图像处理，建立人体模型结构，实现目标关键点的采集，然后采用实验方法采集相关数据。实验结果表明，本文提出的运动识别系统能够有效检测运动员采样点路径的变化，并与标准动作进行对比，具有很好的辅助作用。随着视频图像处理技术在体育训练中的应用越来越普遍，运动员可以更直观地分析自己的训练视频，找出不足之处，从而提高训练效果。本文研究了粒子群优化算法，并将其应用于视频图像处理领域，促进了基于视频处理的体育动作识别技术的发展。
