Scholarlink

<p>Accurate localization of strawberries is essential for improving the performance of strawberry-harvesting robots. To address the needs of intelligent strawberry picking in terms of target detection and picking point positioning, this study proposes YOLOv8-SP (YOLOv8-Strawberry and Picking Points), an improved model capable of simultaneously identifying strawberries and detecting their picking points. The model introduces a novel lightweight module named C2f-Star-ELA (CSE), which replaces the Bottleneck in the original C2f module with StarNet blocks and incorporates an ELA attention mechanism. This enhancement improves accuracy while reducing computational cost. Furthermore, the original PAN structure is replaced with a Cross-Scale Feature Fusion Module (CCFM) to strengthen feature integration. Experimental results demonstrate that YOLOv8-SP achieves a strawberry detection accuracy of 94.1%, which is 5.4% higher than the baseline YOLOv8 model. The average error for picking point localization is 24.17 pixels. The overall parameter count of the model is reduced by 39.6%, and computational complexity is decreased by 32.1%. When deployed on an actual strawberry-picking robot, the model achieves a field picking accuracy of 87.72%. In summary, YOLOv8-SP offers high detection performance, low model complexity, and strong robustness, making it suitable for practical strawberry harvesting applications.</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

Lightweight model for simultaneous detection of strawberries maturity and picking points based on improved YOLOv8

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • Zhiqing Tao,
  • Ke Li,
  • Yuan Rao,
  • Wei Li,
  • Jun Zhu

摘要

Accurate localization of strawberries is essential for improving the performance of strawberry-harvesting robots. To address the needs of intelligent strawberry picking in terms of target detection and picking point positioning, this study proposes YOLOv8-SP (YOLOv8-Strawberry and Picking Points), an improved model capable of simultaneously identifying strawberries and detecting their picking points. The model introduces a novel lightweight module named C2f-Star-ELA (CSE), which replaces the Bottleneck in the original C2f module with StarNet blocks and incorporates an ELA attention mechanism. This enhancement improves accuracy while reducing computational cost. Furthermore, the original PAN structure is replaced with a Cross-Scale Feature Fusion Module (CCFM) to strengthen feature integration. Experimental results demonstrate that YOLOv8-SP achieves a strawberry detection accuracy of 94.1%, which is 5.4% higher than the baseline YOLOv8 model. The average error for picking point localization is 24.17 pixels. The overall parameter count of the model is reduced by 39.6%, and computational complexity is decreased by 32.1%. When deployed on an actual strawberry-picking robot, the model achieves a field picking accuracy of 87.72%. In summary, YOLOv8-SP offers high detection performance, low model complexity, and strong robustness, making it suitable for practical strawberry harvesting applications.