In the process of crop growth, real-time detection and treatment of leaf diseases is extremely important. To improve detection accuracy and reduce the waste of resources, a you only look once version 8 nano (YOLOv8n) crop leaf disease detection model is proposed. First, we use the wise intersection over union (WIoU) loss function to intelligently focus on the model anchor boxes, accelerating model convergence. Next, to accommodate the size of the target being inspected, the detection heads are replaced to improve model accuracy. Then, we add the multi-head self-attention (MHSA) mechanism to the backbone network, enriching the feature extraction capability of the model for images. At last, we introduce deformable convolutional networks version 2 (DCNv2) in cross stage partial feature fusion (C2f) to improve the model’s ability to accurately localize input image targets. The experimental results show that the YOLOv8n_leaf disease model accuracy is improved by 1.3%, recall rate is improved by 0.4%, mean average precision at IoU threshold 0.5 (mAP0.5) reaches 83.7%, and mean average precision at IoU threshold 0.95 (mAP0.95) reaches 69.7%. The improved YOLOv8 model can provide technical support for crop leaf disease detection.
| [1] |
Zhang H Y. Study on the formation mechanism and avoidance of soybean import dependence risk in China, 2023, Yangzhou, Yangzhou University [D]
|
| [2] |
Liu J, Wang X. Tomato diseases and pests detection based on improved Yolo V3 convolutional neural network. Frontiers in plant science, 2020, 11: 898 J]
|
| [3] |
Rashid J, Khan I, Ali G, et al. . Multi-level deep learning model for potato leaf disease recognition. Electronics, 2021, 10(17): 2064 J]
|
| [4] |
Dai Q, Fan J. An industrial-grade solution for crop disease image detection tasks. Frontiers in plant science, 2022, 13: 921057 J]
|
| [5] |
Li M, Cheng S, Cui J, et al. . High-performance plant pest and disease detection based on model ensemble with inception module and cluster algorithme]. Plants, 2023, 12(1): 200
|
| [6] |
Yang W J, Hu W C, Zhao Y D, et al. . Research on plant disease detection algorithm based on improved YOLOv5. Journal of Chinese agricultural mechanization, 2023, 44(01): 108-115 [J]
|
| [7] |
Liu L, Lin S C, Li X Q, et al. . Leaf disease detection based on improved U-Net network model. Chinese journal of liquid crystals and displays, 2024, 39(08): 1138-1144 J]
|
| [8] |
ZHANG H Y, HUANG L X, CHEN J Q, et al. Strawberry ripeness detection algorithm based on improved YOLOv5s[J/OL]. Journal of Nanjing Agricultural University, 2024: 1–12.
|
| [9] |
Zuo H X, Huang Q C, Yang J H, et al. . Improved YOLOv5s-based detection method for tomato yellow leaf curl virus disease. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(S01): 230-238 [J]
|
| [10] |
Gupta C, Gill N S, Gulia P, et al. . A novel finetuned YOLOv6 transfer learning model for real-time object detection. Journal of real-time image processing, 2023, 20(3): 42 J]
|
| [11] |
XIAO B, NGUYEN M, YAN W Q. Fruit ripeness identification using YOLOv8 model[J]. Multimedia tools and applications, 2023: 1–18.
|
| [12] |
Wang L L, Wang B, Li D X, et al. . Object detection and classification of pleurotus ostreatus using improved YOLOv5. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(17): 163-171 [J]
|
| [13] |
Zhu Q, Zhou D Q, Sheng W F, et al. . Apple surface defect detection method based on DSCS-YOLO. Journal of Nanjing Agricultural University, 2023, 46: 1-10 [J]
|
| [14] |
Sun J, Wu Z Q, Jia Y L, et al. . Detection grape in an orchard using improved YOLOv5s. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(18): 192-200 [J]
|
| [15] |
Hui Q J, Sun J. Study on maize leaf disease recognition model based on multi-scale feature metric meta-learning. Jiangsu agricultural sciences, 2023, 51(09): 199-206 [J]
|
| [16] |
ZHANG Z H, WU Y, JIN Z Q. Detection of gibberella infection rate in whet based on MHSA-YOLOv7[J]. Radio engineering: 54(1): 71–77. (in Chinese)
|
RIGHTS & PERMISSIONS
Tianjin University of Technology
PDF
