Scholarlink

<p>To achieve precise localization and counting of abnormal-cut tobacco in complex cigarette manufacturing environments with interference and occlusion, this study proposes an enhanced YOLOv5s-based method using rotated bounding boxes for detection and counting. First, a C3-DEBlock module is developed in the backbone network by integrating the Efficient Multi-scale Attention (EMA) module, the Dynamic Snake Convolution (DSConv), and the C3 structure. This design adaptively adjusts the receptive field to enhance feature extraction capability. Second, a Context Anchor Attention–Bidirectional Feature Pyramid Network (CAA-BiFPN) is incorporated into the neck network. This structure not only reduces computational costs but also captures long-range contextual information, thereby strengthening multi-scale feature fusion. Finally, the Kullback–Leibler divergence (KLD) between the Gaussian distributions is adopted as the regression loss function, enabling dynamic adjustment of parameter gradients based on object characteristics for more accurate bounding box regression. Experimental results demonstrate that the proposed model outperforms mainstream detection models–Faster R-CNN, YOLOv4-tiny, and YOLOv5s–with improvements in mean average precision (mAP) of 14.91, 25.21, and 2.61% points, respectively. Regression analysis based on manual measurements of the length and width of abnormal-cut tobacco shows coefficients of determination of 0.98, 0.985, 0.99, 0.985, 0.995, and 0.98. By accurately localizing abnormal-cut tobacco via rotated bounding boxes, the method significantly mitigates interference from background regions. It provides an online detection solution for precise counting of the abnormal-cut tobacco, supports refined grading control and cutting process optimization, and thereby facilitates the modernization of tobacco processing.</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

Abnormal-cut tobacco detection and phenotypic measurement based on improved YOLOv5s rotating frame

  • 期刊论文

  • 发表日期：

    2026年2月24日

查看全文
  • Jiakang Li,
  • Donghui Hu,
  • Erqiang Zhang,
  • Jie Zhang,
  • Hui Li,
  • Shihuan Chen,
  • Jinsong Du,
  • Dayong Xu

摘要

To achieve precise localization and counting of abnormal-cut tobacco in complex cigarette manufacturing environments with interference and occlusion, this study proposes an enhanced YOLOv5s-based method using rotated bounding boxes for detection and counting. First, a C3-DEBlock module is developed in the backbone network by integrating the Efficient Multi-scale Attention (EMA) module, the Dynamic Snake Convolution (DSConv), and the C3 structure. This design adaptively adjusts the receptive field to enhance feature extraction capability. Second, a Context Anchor Attention–Bidirectional Feature Pyramid Network (CAA-BiFPN) is incorporated into the neck network. This structure not only reduces computational costs but also captures long-range contextual information, thereby strengthening multi-scale feature fusion. Finally, the Kullback–Leibler divergence (KLD) between the Gaussian distributions is adopted as the regression loss function, enabling dynamic adjustment of parameter gradients based on object characteristics for more accurate bounding box regression. Experimental results demonstrate that the proposed model outperforms mainstream detection models–Faster R-CNN, YOLOv4-tiny, and YOLOv5s–with improvements in mean average precision (mAP) of 14.91, 25.21, and 2.61% points, respectively. Regression analysis based on manual measurements of the length and width of abnormal-cut tobacco shows coefficients of determination of 0.98, 0.985, 0.99, 0.985, 0.995, and 0.98. By accurately localizing abnormal-cut tobacco via rotated bounding boxes, the method significantly mitigates interference from background regions. It provides an online detection solution for precise counting of the abnormal-cut tobacco, supports refined grading control and cutting process optimization, and thereby facilitates the modernization of tobacco processing.