Grape leaf disease detection based on attention mechanisms

作     者：Wenjuan Guo Quan Feng Xiangzhou Li Sen Yang Junqi Yang 

作者机构：College of Mechanical and Electrical EngineeringGansu Agricultural UniversityLanzhou 730070China School of Cyber SecurityGansu University of Political Science and LawLanzhou 730070China 

出 版 物：《International Journal of Agricultural and Biological Engineering》 (国际农业与生物工程学报（英文）)

年 卷 期：2022年第15卷第5期

页      面：205-212页

核心收录：

学科分类：0401[教育学-教育学] 04[教育学] 

基　　金：financially supported by the National Natural Science Foundation of China(Grant No.31971792) the Industrialization Support Project from the Education Department of Gansu Province(Grant No.2021CYZC-57) Youth Science and Technology Foundation of Gansu Province(Grant No.21JR7RA572) School Level Youth Project of Gansu University of Political Science and Law(Grant No.GZF2019XQNLW08) Gansu Education Department Innovation Fund project(Grant No.2022B-144) 

主　　题：disease detection Faster R-CNN YOLOx SSD attention mechanism 

摘      要：Prevention and control of grape diseases is the key measure to ensure grape *** order to improve the precision of grape leaf disease detection,in this study,Squeeze-and-Excitation Networks(SE),Efficient Channel Attention(ECA),and Convolutional Block Attention Module(CBAM)attention mechanisms were introduced into Faster Region-based Convolutional Neural Networks(R-CNN),YOLOx,and single shot multibox detector(SSD),to enhance important features and weaken unrelated features and ensure the real-time performance of the model in improving its detection *** study showed that Faster R-CNN,YOLOx,and SSD models based on different attention mechanisms effectively enhanced the detection precision and operation speed of the models by slightly enhancing *** models among the three types of models were selected for comparison,and results showed that Faster R-CNN+SE had lower detection precision,YOLOx+ECA required the least parameters with the highest detection precision,and SSD+SE showed optimal real-time performance with relatively high detection *** study solved the problem of difficulty in grape leaf disease detection and provided a reference for the analysis of grape diseases and symptoms in automated agricultural production.