您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Monitoring the leaf damage by the rice leafroller with deep learning and ultra-light UAV

文献类型： 外文期刊

作者： Xia, Lang 1 ; Zhang, Ruirui 1 ; Chen, Liping 3 ; Li, Longlong 3 ; Yi, Tongchuan 3 ; Chen, Meixiang 1 ;

作者机构： 1.Beijing Acad Agr & Forestry Sci, Natl Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China

2.Beijing Acad Agr & Forestry Sci, Beijing Key Lab Intelligent Equipment Technol Agr, Beijing, Peoples R China

3.Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing, Peoples R China

4.Natl Ctr Int Res Agr Aerial Applicat Technol, Beijing, Peoples R China

关键词： rice leafroller; deep learning; ultra-light UAV; spatial distribution; downwash flow field

期刊名称：PEST MANAGEMENT SCIENCE （ 影响因子：3.8； 五年影响因子：4.3 ）

ISSN： 1526-498X

年卷期： 2024 年 80 卷 12 期

页码：

收录情况： SCI

摘要： BACKGROUND: Rice leafroller is a serious threat to the production of rice. Monitoring the damage caused by rice leafroller isessential for effective pest management. Owing to limitations in collecting decent quality images and high-performing identi-fication methods to recognize the damage, studies recommending fast and accurate identification of rice leafroller damage arerare. In this study, we employed an ultra-lightweight unmanned aerial vehicle (UAV) to eliminate the influence of the downwashflowfield and obtain very high-resolution images of the damaged areas of the rice leafroller. We used deep learning technologyand the segmentation model, Attention U-Net, to recognize the damaged area by the rice leafroller. Further, a method is pre-sented to count the damaged patches from the segmented area. RESULTS: The result shows that Attention U-Net achieves high performance, with an F1 score of 0.908. Further analysis indicatesthat the deep learning model performs better than the traditional image classification method, Random Forest (RF). The tradi-tional method of RF causes a lot of false alarms around the edge of leaves, and is sensitive to the changes in brightness. Vali-dation based on the ground survey indicates that the UAV and deep learning-based method achieve a reasonable accuracyin identifying damage patches, with a coefficient of determination of 0.879. The spatial distribution of the damage is uneven,and the UAV-based image collecting method provides a dense and accurate method to recognize the damaged area. CONCLUSION: Overall, this study presents a vision to monitor the damage caused by the rice leafroller with ultra-light UAV effi-ciently. It would also contribute to effectively controlling and managing the hazardous rice leafroller.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台