Improving the Accuracy of Agricultural Pest Identification: Application of AEC-YOLOv8n to Large-Scale Pest Datasets

• Published in: Agronomy (Basel) Vol. 14; no. 8; p. 1640
• Main Authors: Wei, Jinfan, Gong, He, Li, Shijun, You, Minghui, Zhu, Hang, Ni, Lingyun, Luo, Lan, Chen, Mengchao, Chao, Hongli, Hu, Jinghuan, Zhu, Caocan, Wang, Heyang, Liu, Jingyi, Nian, Jiaxin, Fan, Wenye, Mu, Ye, Sun, Yu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2024
• Subjects: Accuracy; AFEM_SIE; Agricultural pests; Agricultural production; Agriculture; agronomy; Algorithms; concat_weighting; Crop diseases; Crop production; Crops; data collection; Datasets; Deep learning; EMSFEM; Food security; information exchange; Information processing; IP102; Modules; multiple target recognition; Multisensor fusion; pest identification; Pests; Plant diseases; plant pests; Product quality; Receptive field; Soybeans; Spatial data; species; Target detection; texture; texture and edge information; Weighting

Crop diseases and pests are important factors restricting agricultural production. Traditional pest detection methods are mainly targeted at a single pest species, which is difficult to meet the needs of multi-target identification and rapid response in real scenes. Therefore, this paper improves th...