Scholarlink

<p>Video analysis of soccer matches is vital for enhancing training methodologies and performance assessment. However, accurately tracking players and detecting the ball in real-time poses significant challenges due to occlusion, rapid movements, and variable lighting conditions. In this study, we introduce SoccerEDMF, an Enhanced Dual-Model Framework specifically designed for precise player tracking and ball detection in soccer broadcasts. By employing separate modules optimized for each task, our system leverages unique jersey color patterns for player identification and applies interpolation techniques to predict ball positions during occlusions. Experimental results on custom datasets demonstrate that SoccerEDMF outperforms state-of-the-art methods, achieving a mean average precision of 97.7% for player detection and 65.3% for ball detection. Here, we show that our framework not only enhances detection accuracy but also provides robust visualizations of player movements and ball trajectories, offering valuable insights for coaches and analysts. The proposed system thus represents a significant advancement in real-time soccer video analysis. Our code is available at <a href="https://github.com/JianglangKang/SoccerEDMF">https://github.com/JianglangKang/SoccerEDMF</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced dual-model framework for precision player tracking and ball detection in soccer videos

  • 期刊论文

  • 发表日期：

    2025年8月5日

查看全文
  • Meng Yang,
  • Jianglang Kang,
  • Hongyu Li,
  • Chao Yang,
  • Xiang Suo,
  • Weiliang Meng,
  • Zhen Li,
  • Lijuan Mao,
  • Jun Qi

摘要

Video analysis of soccer matches is vital for enhancing training methodologies and performance assessment. However, accurately tracking players and detecting the ball in real-time poses significant challenges due to occlusion, rapid movements, and variable lighting conditions. In this study, we introduce SoccerEDMF, an Enhanced Dual-Model Framework specifically designed for precise player tracking and ball detection in soccer broadcasts. By employing separate modules optimized for each task, our system leverages unique jersey color patterns for player identification and applies interpolation techniques to predict ball positions during occlusions. Experimental results on custom datasets demonstrate that SoccerEDMF outperforms state-of-the-art methods, achieving a mean average precision of 97.7% for player detection and 65.3% for ball detection. Here, we show that our framework not only enhances detection accuracy but also provides robust visualizations of player movements and ball trajectories, offering valuable insights for coaches and analysts. The proposed system thus represents a significant advancement in real-time soccer video analysis. Our code is available at https://github.com/JianglangKang/SoccerEDMF.