Scholarlink

<p>Real-time tennis action recognition is important for sports video analysis and training review, yet many pose-aware models remain computationally expensive for routine use. This article proposes HL-TAR-YOLO, a lightweight pose-aware YOLO framework for fine-grained tennis stroke recognition. Built on YOLO11-Pose, the framework integrates DualConv for efficient feature extraction, SimAM for parameter-free spatial refinement, DySample for dynamic upsampling, and Slide Loss for adaptive optimization under sample difficulty imbalance. The proposed model was evaluated on TAR-Det, a pose-annotated tennis action dataset introduced in our previous work, and compared with representative lightweight and pose-aware baselines in terms of precision, recall, mAP, parameter count, FLOPs, and inference speed. Experimental results show that HL-TAR-YOLO achieves 95.2% precision, 93.9% recall, 94.3% mAP<sub>0.5</sub>, and 91.0% mAP<sub>0.5:0.95</sub>, while using only 2.6&#xa0;M parameters and 6.9 GFLOPs and running at 122.3 FPS under the reported GPU evaluation setting. Additional CPU inference analysis showed lower single-frame latency than YOLO11s-Pose. These results suggest that HL-TAR-YOLO provides an effective accuracy-efficiency trade-off for resource-constrained tennis stroke analysis, while temporal modeling, external validation, and real-device evaluation remain important directions for future work.</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

A lightweight pose-aware YOLO framework for real-time tennis stroke recognition and training analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月28日

查看全文
  • Bohan Chen,
  • Liangyu Du,
  • Dongwei Peng,
  • Yujin Zhou,
  • Dong He,
  • Weichen Fang,
  • Yanling Cen,
  • Caiying Mou,
  • Jianjun Peng,
  • Li Jin,
  • Xiaowei Peng

摘要

Real-time tennis action recognition is important for sports video analysis and training review, yet many pose-aware models remain computationally expensive for routine use. This article proposes HL-TAR-YOLO, a lightweight pose-aware YOLO framework for fine-grained tennis stroke recognition. Built on YOLO11-Pose, the framework integrates DualConv for efficient feature extraction, SimAM for parameter-free spatial refinement, DySample for dynamic upsampling, and Slide Loss for adaptive optimization under sample difficulty imbalance. The proposed model was evaluated on TAR-Det, a pose-annotated tennis action dataset introduced in our previous work, and compared with representative lightweight and pose-aware baselines in terms of precision, recall, mAP, parameter count, FLOPs, and inference speed. Experimental results show that HL-TAR-YOLO achieves 95.2% precision, 93.9% recall, 94.3% mAP0.5, and 91.0% mAP0.5:0.95, while using only 2.6 M parameters and 6.9 GFLOPs and running at 122.3 FPS under the reported GPU evaluation setting. Additional CPU inference analysis showed lower single-frame latency than YOLO11s-Pose. These results suggest that HL-TAR-YOLO provides an effective accuracy-efficiency trade-off for resource-constrained tennis stroke analysis, while temporal modeling, external validation, and real-device evaluation remain important directions for future work.