Scholarlink

<p>Tea bud picking points detection is crucial for automating tea harvesting. However, existing detection algorithms still suffer from excessive parameter sizes and suboptimal accuracy. In addition, in natural environments, the variability in tea bud morphology and spatial distribution complicates detection. To address these challenges, this paper proposes a lightweight and high-precision deep learning method for tea bud picking point detection, based on the Real-Time DEtection Transformer (RT-DETR). The FasterNet block module is introduced to optimize the backbone of proposed network, significantly reducing computational complexity and parameters. Additionally, a novel Cross-Resolution Attention Fusion is employed, which adaptively combines fine-grained and coarse-grained features, enabling the integration of local and global information and improving robustness in complex environments. An improved loss function is also proposed, directing the model’s attention to hard samples and mitigating false negatives and positives. Experimental results show that our method outperforms the original RT-DETR, improving mean accuracy by 4.6%, increasing the F1 score by 4.9%, reducing parameters by 7.5%, and decreasing computational complexity by 5.9 GFLOPs. Moreover, the model achieves a detection rate of 106.42 frames per second (FPS), satisfying the criteria for real-time performance. The proposed method effectively enhances detection accuracy while reducing computational complexity, offering an efficient and deployable solution for intelligent tea harvesting.</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 RT-DETR for tea-picking points detection

  • 期刊论文

  • 发表日期：

    2026年2月13日

查看全文
  • Yaohai Lin,
  • Zipeng You,
  • Youzhuang Lin,
  • Wanhan Wu,
  • Changcai Yang,
  • Shuilian Gao

摘要

Tea bud picking points detection is crucial for automating tea harvesting. However, existing detection algorithms still suffer from excessive parameter sizes and suboptimal accuracy. In addition, in natural environments, the variability in tea bud morphology and spatial distribution complicates detection. To address these challenges, this paper proposes a lightweight and high-precision deep learning method for tea bud picking point detection, based on the Real-Time DEtection Transformer (RT-DETR). The FasterNet block module is introduced to optimize the backbone of proposed network, significantly reducing computational complexity and parameters. Additionally, a novel Cross-Resolution Attention Fusion is employed, which adaptively combines fine-grained and coarse-grained features, enabling the integration of local and global information and improving robustness in complex environments. An improved loss function is also proposed, directing the model’s attention to hard samples and mitigating false negatives and positives. Experimental results show that our method outperforms the original RT-DETR, improving mean accuracy by 4.6%, increasing the F1 score by 4.9%, reducing parameters by 7.5%, and decreasing computational complexity by 5.9 GFLOPs. Moreover, the model achieves a detection rate of 106.42 frames per second (FPS), satisfying the criteria for real-time performance. The proposed method effectively enhances detection accuracy while reducing computational complexity, offering an efficient and deployable solution for intelligent tea harvesting.