您好,欢迎访问重庆市农业科学院 机构知识库!

Efficient and accurate identification of maize rust disease using deep learning model

文献类型: 外文期刊

作者: Wang, Pei 1 ; Tan, Jiajia 1 ; Yang, Yuheng 2 ; Zhang, Tong 2 ; Wu, Pengxin 1 ; Tang, Xinglong 4 ; Li, Hui 1 ; He, Xiongkui 5 ; Chen, Xinping 2 ;

作者机构: 1.Southwest Univ, Coll Engn & Technol, Key Lab Agr Equipment Hilly & Mt Areas, Chongqing, Peoples R China

2.Southwest Univ, Interdisciplinary Res Ctr Agr Green Dev Yangtze Ri, Chongqing, Peoples R China

3.Southwest Univ, Coll Plant Protect, Chongqing, Peoples R China

4.Chongqing Acad Agr Sci, Inst Agr Machinery, Chongqing, Peoples R China

5.China Agr Univ, Coll Sci, Ctr Chem Applicat Technol, Beijing, Peoples R China

关键词: maize; southern rust; common rust; SimAM; small target detection

期刊名称:FRONTIERS IN PLANT SCIENCE ( 影响因子:4.8; 五年影响因子:5.7 )

ISSN: 1664-462X

年卷期: 2025 年 15 卷

页码:

收录情况: SCI

摘要: Common corn rust and southern corn rust, two typical maize diseases during growth stages, require accurate differentiation to understand their occurrence patterns and pathogenic risks. To address this, a specialized Maize-Rust model integrating a SimAM module in the YOLOv8s backbone and a BiFPN for scale fusion, along with a DWConv for streamlined detection, was developed. The model achieved an accuracy of 94.6%, average accuracy of 91.6%, recall rate of 85.4%, and F1 value of 0.823, outperforming Faster-RCNN and SSD models by 16.35% and 12.49% in classification accuracy, respectively, and detecting a single rust image at 16.18 frames per second. Deployed on mobile phones, the model enables real-time data collection and analysis, supporting effective detection and management of large-scale outbreaks of rust in the field.

  • 相关文献
作者其他论文 更多>>