Scholarlink

<p>The Red Palm Weevil (RPW) is one of the most destructive pests affecting palm trees worldwide, leading to severe agricultural and economic losses. Early detection was essential for effective intervention; however, conventional methods such as pheromone traps and manual inspections frequently failed to identify early stage infestations.To address this challenge, this study developed an automated RPW detection framework using thermal image processing and deep learning.A Convolutional Neural Network(CNN) model was trained to analyze thermal images and detect early signs of infestation.The proposed model achieved a detection accuracy of 98.5%,outperforming traditional machine learning techniques in both precision and response speed. For real-time deployment, the trained CNN was integrated into a Raspberry Pi 4B, enabling a low cost, scalable, and non-invasive monitoring solution suitable for field applications.While the system demonstrated strong performance under controlled conditions, the work also identified key limitations, including the limited penetration depth of thermal imaging and the need for large-scale field validation to ensure robustness under diverse real-world environments.</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

Smart IoT thermal imaging approach for early identification of Red Palm Weevil (RPW) infestation on palms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月6日

查看全文
  • Betty Martin,
  • S. Saranya,
  • Pakalapati Jathin Chowdary

摘要

The Red Palm Weevil (RPW) is one of the most destructive pests affecting palm trees worldwide, leading to severe agricultural and economic losses. Early detection was essential for effective intervention; however, conventional methods such as pheromone traps and manual inspections frequently failed to identify early stage infestations.To address this challenge, this study developed an automated RPW detection framework using thermal image processing and deep learning.A Convolutional Neural Network(CNN) model was trained to analyze thermal images and detect early signs of infestation.The proposed model achieved a detection accuracy of 98.5%,outperforming traditional machine learning techniques in both precision and response speed. For real-time deployment, the trained CNN was integrated into a Raspberry Pi 4B, enabling a low cost, scalable, and non-invasive monitoring solution suitable for field applications.While the system demonstrated strong performance under controlled conditions, the work also identified key limitations, including the limited penetration depth of thermal imaging and the need for large-scale field validation to ensure robustness under diverse real-world environments.