YOLOV5-CBAM-C3TR: an optimized model based on transformer module and attention mechanism for apple leaf disease detection

被引:11
|
作者
Lv, Meng [1 ]
Su, Wen-Hao [1 ]
机构
[1] China Agr Univ, Coll Engn, Beijing, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
deep learning; apple leaf; disease detection; YOLOv5; attention mechanism; transformer encoder;
D O I
10.3389/fpls.2023.1323301
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Apple trees face various challenges during cultivation. Apple leaves, as the key part of the apple tree for photosynthesis, occupy most of the area of the tree. Diseases of the leaves can hinder the healthy growth of trees and cause huge economic losses to fruit growers. The prerequisite for precise control of apple leaf diseases is the timely and accurate detection of different diseases on apple leaves. Traditional methods relying on manual detection have problems such as limited accuracy and slow speed. In this study, both the attention mechanism and the module containing the transformer encoder were innovatively introduced into YOLOV5, resulting in YOLOV5-CBAM-C3TR for apple leaf disease detection. The datasets used in this experiment were uniformly RGB images. To better evaluate the effectiveness of YOLOV5-CBAM-C3TR, the model was compared with different target detection models such as SSD, YOLOV3, YOLOV4, and YOLOV5. The results showed that YOLOV5-CBAM-C3TR achieved mAP@0.5, precision, and recall of 73.4%, 70.9%, and 69.5% for three apple leaf diseases including Alternaria blotch, Grey spot, and Rust. Compared with the original model YOLOV5, the mAP 0.5increased by 8.25% with a small change in the number of parameters. In addition, YOLOV5-CBAM-C3TR can achieve an average accuracy of 92.4% in detecting 208 randomly selected apple leaf disease samples. Notably, YOLOV5-CBAM-C3TR achieved 93.1% and 89.6% accuracy in detecting two very similar diseases including Alternaria Blotch and Grey Spot, respectively. The YOLOV5-CBAM-C3TR model proposed in this paper has been applied to the detection of apple leaf diseases for the first time, and also showed strong recognition ability in identifying similar diseases, which is expected to promote the further development of disease detection technology.
引用
收藏
页数:13
相关论文
共 22 条
  • [1] An Image Object Detection Model Based on Mixed Attention Mechanism Optimized YOLOv5
    Sun, Guangming
    Wang, Shuo
    Xie, Jiangjian
    ELECTRONICS, 2023, 12 (07)
  • [2] TGC-YOLOv5: An Enhanced YOLOv5 Drone Detection Model Based on Transformer, GAM & CA Attention Mechanism
    Zhao, Yuliang
    Ju, Zhongjie
    Sun, Tianang
    Dong, Fanghecong
    Li, Jian
    Yang, Ruige
    Fu, Qiang
    Lian, Chao
    Shan, Peng
    DRONES, 2023, 7 (07)
  • [3] An improved YOLOv5-based apple leaf disease detection method
    Liu, Zhengyan
    Li, Xu
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [4] Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism
    Ma, Li
    Yu, Qiwen
    Yu, Helong
    Zhang, Jian
    AGRONOMY-BASEL, 2023, 13 (02):
  • [5] Yolov5s-CA: An Improved Yolov5 Based on the Attention Mechanism for Mummy Berry Disease Detection
    Obsie, Efrem Yohannes
    Qu, Hongchun
    Zhang, Yong-Jiang
    Annis, Seanna
    Drummond, Francis
    AGRICULTURE-BASEL, 2023, 13 (01):
  • [6] DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism
    Roy, Arunabha M.
    Bhaduri, Jayabrata
    ADVANCED ENGINEERING INFORMATICS, 2023, 56
  • [7] Improved Tomato Leaf Disease Recognition Based on the YOLOv5m with Various Soft Attention Module Combinations
    Lee, Yong-Suk
    Patil, Maheshkumar Prakash
    Kim, Jeong Gyu
    Choi, Seong Seok
    Seo, Yong Bae
    Kim, Gun-Do
    AGRICULTURE-BASEL, 2024, 14 (09):
  • [8] An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
    Xu, Sheng
    Guo, Zhanyu
    Liu, Yuchi
    Fan, Jingwei
    Liu, Xuxu
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT III, 2022, 13531 : 531 - 543
  • [9] A Multi-objective Apple Leaf Disease Detection Algorithm Based on Improved TPH-YOLOV5
    Li, Fengmei
    Zheng, Yuhui
    Liu, Song
    Sun, Fengbo
    Bai, Haoran
    APPLIED FRUIT SCIENCE, 2024, 66 (02) : 399 - 415
  • [10] A Multi-objective Apple Leaf Disease Detection Algorithm Based on Improved TPH-YOLOV5
    Fengmei Li
    Yuhui Zheng
    Song Liu
    Fengbo Sun
    Haoran Bai
    Applied Fruit Science, 2024, 66 : 399 - 415