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

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion

文献类型： 外文期刊

作者： Feng, Xuguang 1 ; Zhao, Chunjiang 2 ; Wang, Chunshan 1 ; Wu, Huarui 2 ; Miao, Yisheng 2 ; Zhang, Jingjian 5 ;

作者机构： 1.Hebei Agr Univ, Sch Informat Sci & Technol, Baoding, Peoples R China

2.Natl Engn Res Ctr Informat Technol Agr, Beijing, Peoples R China

3.Minist Agr & Rural Affairs Peoples Republ China, Agr Key Lab Digital Village, Beijing, Peoples R China

4.Hebei Key Lab Agr Big Data, Baoding, Peoples R China

5.Cangzhou Acad Agr & Forestry Sci, Cangzhou, Peoples R China

关键词： cross-modal fusion; transformer; few-shot; complex background; disease identification

期刊名称：FRONTIERS IN PLANT SCIENCE （ 影响因子：6.627； 五年影响因子：7.255 ）

ISSN： 1664-462X

年卷期： 2022 年 13 卷

页码：

收录情况： SCI

摘要： In view of the differences in appearance and the complex backgrounds of crop diseases, automatic identification of field diseases is an extremely challenging topic in smart agriculture. To address this challenge, a popular approach is to design a Deep Convolutional Neural Network (DCNN) model that extracts visual disease features in the images and then identifies the diseases based on the extracted features. This approach performs well under simple background conditions, but has low accuracy and poor robustness under complex backgrounds. In this paper, an end-to-end disease identification model composed of a disease-spot region detector and a disease classifier (YOLOv5s + BiCMT) was proposed. Specifically, the YOLOv5s network was used to detect the disease-spot regions so as to provide a regional attention mechanism to facilitate the disease identification task of the classifier. For the classifier, a Bidirectional Cross-Modal Transformer (BiCMT) model combining the image and text modal information was constructed, which utilizes the correlation and complementarity between the features of the two modalities to achieve the fusion and recognition of disease features. Meanwhile, the problem of inconsistent lengths among different modal data sequences was solved. Eventually, the YOLOv5s + BiCMT model achieved the optimal results on a small dataset. Its Accuracy, Precision, Sensitivity, and Specificity reached 99.23, 97.37, 97.54, and 99.54%, respectively. This paper proves that the bidirectional cross-modal feature fusion by combining disease images and texts is an effective method to identify vegetable diseases in field environments.

  • 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