Scholarlink

<p>To address the poor real-time detection of potato damage during harvesting and the high computational complexity of the model, this paper proposed a lightweight detection algorithm based on the YOLOv8 framework—Light-YOLOv8. The algorithm achieved lightweight detection by integrating EfficientNet-B0 composite scaling strategy to optimize model parameters and integrating the MBConv network module to reduce the backbone network’s weight. By combining the lightweight network Slim-neck with the CARAFE upsampling operator, the SNC neck network was designed and constructed, to reduce the weight and enhance its ability to process detailed information. Additionally, Light-YOLOv8 employed the PReLU activation function to optimize network performance. Experimental results demonstrated that Light-YOLOv8 achieved a mean average precision (mAP@50–95) of 95.23%, significantly reduced model parameters (only 1.88&#xa0;M) and floating-point operations (as low as 5.5G), and reduced the inference speed for a single image to 12 ms per image, with a model memory footprint of only 3.93&#xa0;MB. In edge computing device deployment, Light-YOLOv8 balances speed and accuracy effectively compared to other models, providing technical support for real-time potato damage detection.</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 real-time potato damage detection method based on improved YOLOv8

  • 期刊论文

  • 发表日期：

    2025年5月27日

查看全文
  • Zheng Ma,
  • Ning Zhang,
  • Shuai Wang,
  • Yaoming Li,
  • Yu Pan,
  • Jiaqi Zhang,
  • Chang Liu,
  • Hongyan Gao

摘要

To address the poor real-time detection of potato damage during harvesting and the high computational complexity of the model, this paper proposed a lightweight detection algorithm based on the YOLOv8 framework—Light-YOLOv8. The algorithm achieved lightweight detection by integrating EfficientNet-B0 composite scaling strategy to optimize model parameters and integrating the MBConv network module to reduce the backbone network’s weight. By combining the lightweight network Slim-neck with the CARAFE upsampling operator, the SNC neck network was designed and constructed, to reduce the weight and enhance its ability to process detailed information. Additionally, Light-YOLOv8 employed the PReLU activation function to optimize network performance. Experimental results demonstrated that Light-YOLOv8 achieved a mean average precision (mAP@50–95) of 95.23%, significantly reduced model parameters (only 1.88 M) and floating-point operations (as low as 5.5G), and reduced the inference speed for a single image to 12 ms per image, with a model memory footprint of only 3.93 MB. In edge computing device deployment, Light-YOLOv8 balances speed and accuracy effectively compared to other models, providing technical support for real-time potato damage detection.