Research on Lightweight Rice False Smut Disease Identification Method Based on Improved YOLOv8n Model

被引:1
|
作者
Yang, Lulu [1 ]
Guo, Fuxu [1 ]
Zhang, Hongze [1 ]
Cao, Yingli [1 ,2 ]
Feng, Shuai [1 ,2 ]
机构
[1] Shenyang Agr Univ, Coll Informat & Elect Engn, Shenyang 110866, Peoples R China
[2] Liaoning Key Lab Intelligent Agr Technol, Shenyang 110866, Peoples R China
来源
AGRONOMY-BASEL | 2024年 / 14卷 / 09期
关键词
rice false smut; digital imaging; YOLOv8n; feature fusion; lightweight network; FRUIT;
D O I
10.3390/agronomy14091934
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
In order to detect rice false smut quickly and accurately, a lightweight false smut detection model, YOLOv8n-MBS, was proposed in this study. The model introduces the C2f_MSEC module to replace C2f in the backbone network for better extraction of key features of false smut, enhances the feature fusion capability of the neck network for different sizes of false smut by using a weighted bidirectional feature pyramid network, and designs a group-normalized shared convolution lightweight detection head to reduce the number of parameters in the model head to achieve model lightweight. The experimental results show that YOLOv8n-MBS has an average accuracy of 93.9%, a parameter count of 1.4 M, and a model size of 3.3 MB. Compared with the SSD model, the average accuracy of the model in this study increased by 4%, the number of parameters decreased by 89.8%, and the model size decreased by 86.9%; compared with the YOLO series of YOLOv7-tiny, YOLOv5n, YOLOv5s, and YOLOv8n models, the YOLOv8n-MBS model showed outstanding performance in terms of model accuracy and model performance detection; compared to the latest YOLOv9t and YOLOv10n models, the average model accuracy increased by 2.8% and 2.2%, the number of model parameters decreased by 30% and 39.1%, and the model size decreased by 29.8% and 43.1%, respectively. This method enables more accurate and lighter-weight detection of false smut, which provides the basis for intelligent management of rice blast disease in the field and thus promotes food security.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Research on Improved Lightweight Fish Detection Algorithm Based on Yolov8n
    Zhang, Qingyang
    Chen, Shizhe
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (10)
  • [2] A Lightweight Method for Road Damage Detection Based on Improved YOLOv8n
    Li, Xudong
    Zhang, Yujun
    ENGINEERING LETTERS, 2025, 33 (01) : 114 - 123
  • [3] RDB-YOLOv8n: Insulator defect detection based on improved lightweight YOLOv8n model
    Jiang, Yong
    Wang, Shuai
    Cao, Weifeng
    Liang, Wanyong
    Shi, Jun
    Zhou, Lintao
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (05)
  • [4] Improved YOLOv8n for Lightweight Ship Detection
    Gao, Zhiguang
    Yu, Xiaoyan
    Rong, Xianwei
    Wang, Wenqi
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (10)
  • [5] Fabric Defect Detection Based on Improved Lightweight YOLOv8n
    Ma, Shuangbao
    Liu, Yuna
    Zhang, Yapeng
    APPLIED SCIENCES-BASEL, 2024, 14 (17):
  • [6] A lightweight weed detection model for cotton fields based on an improved YOLOv8n
    Wang, Jun
    Qi, Zhengyuan
    Wang, Yanlong
    Liu, Yanyang
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [7] Maize Seed Damage Identification Method Based on Improved YOLOV8n
    Yang, Songmei
    Wang, Benxu
    Ru, Shaofeng
    Yang, Ranbing
    Wu, Jilong
    AGRONOMY-BASEL, 2025, 15 (03):
  • [8] Research on Bubble Detection Based on Improved YOLOv8n
    Chen, Tingting
    Zeng, Qingzhu
    IEEE ACCESS, 2024, 12 : 9659 - 9668
  • [9] Lightweight Mulberry Fruit Detection Method Based on Improved YOLOv8n for Automated Harvesting
    Qiu, Hong
    Zhang, Qinghui
    Li, Junqiu
    Rong, Jian
    Yang, Zongpeng
    AGRONOMY-BASEL, 2024, 14 (12):
  • [10] Waste drilling fluid flocculation identification method based on improved YOLOv8n
    Wan, Min
    Yang, Xin
    Zhang, Huaibang
    REVIEW OF SCIENTIFIC INSTRUMENTS, 2025, 96 (01):