Pine wilt disease detection algorithm based on improved YOLOv5

被引:2
|
作者
Du, Zengjie [1 ,2 ,3 ]
Wu, Sifei [1 ,2 ,3 ]
Wen, Qingqing [4 ]
Zheng, Xinyu [1 ,2 ,3 ]
Lin, Shangqin [1 ,2 ,3 ]
Wu, Dasheng [1 ,2 ,3 ]
机构
[1] Zhejiang A&F Univ, Coll Math & Comp Sci, Hangzhou, Peoples R China
[2] Key Lab State Forestry & Grassland Adm Forestry Se, Hangzhou, Peoples R China
[3] Key Lab Forestry Intelligent Monitoring & Informat, Hangzhou, Peoples R China
[4] Wucheng Nanshan Prov Nat Reserve Management Ctr Zh, Jinhua, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
pine wilt disease; unmanned aerial vehicle; deep learning; YOLOv5; SimAM-ASFF; NEMATODE; TREES;
D O I
10.3389/fpls.2024.1302361
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Pine wilt disease (PWD) poses a significant threat to forests due to its high infectivity and lethality. The absence of an effective treatment underscores the importance of timely detection and isolation of infected trees for effective prevention and control. While deep learning techniques combined unmanned aerial vehicle (UAV) remote sensing images offer promise for accurate identification of diseased pine trees in their natural environments, they often demand extensive prior professional knowledge and struggle with efficiency. This paper proposes a detection model YOLOv5L-s-SimAM-ASFF, which achieves remarkable precision, maintains a lightweight structure, and facilitates real-time detection of diseased pine trees in UAV RGB images under natural conditions. This is achieved through the integration of the ShuffleNetV2 network, a simple parameter-free attention module known as SimAM, and adaptively spatial feature fusion (ASFF). The model boasts a mean average precision (mAP) of 95.64% and a recall rate of 91.28% in detecting pine wilt diseased trees, while operating at an impressive 95.70 frames per second (FPS). Furthermore, it significantly reduces model size and parameter count compared to the original YOLOv5-Lite. These findings indicate that the proposed model YOLOv5L-s-SimAM-ASFF is most suitable for real-time, high-accuracy, and lightweight detection of PWD-infected trees. This capability is crucial for precise localization and quantification of infected trees, thereby providing valuable guidance for effective management and eradication efforts.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Exploring the potential of visual tracking and counting for trees infected with pine wilt disease based on improved YOLOv5 and StrongSORT algorithm
    Ye, Xinquan
    Pan, Jie
    Shao, Fan
    Liu, Gaosheng
    Lin, Jiayi
    Xu, Dongxiao
    Liu, Jia
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 218
  • [2] Improved YOLOv5 Detection Algorithm of Road Disease Image
    Yang, Jie
    Jia, Xinyu
    Guo, Xiaoyan
    Zang, Chuanyan
    Zhao, Haiyan
    Sun, Jiacheng
    Xu, Yan
    [J]. 2023 IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023, 2023, : 193 - 198
  • [3] Vehicle And Pedestrian Detection Algorithm Based on Improved YOLOv5
    Sun, Jiuhan
    Wang, Zhifeng
    [J]. IAENG International Journal of Computer Science, 2023, 50 (04)
  • [4] Improved Small Object Detection Algorithm Based on YOLOv5
    Xu, Bo
    Gao, Bin
    Li, Yunhu
    [J]. IEEE Intelligent Systems, 2024, 39 (05) : 57 - 65
  • [5] Fabric defect detection algorithm based on improved YOLOv5
    Li, Feng
    Xiao, Kang
    Hu, Zhengpeng
    Zhang, Guozheng
    [J]. VISUAL COMPUTER, 2024, 40 (04): : 2309 - 2324
  • [6] Research on improved algorithm for helmet detection based on YOLOv5
    Shan, Chun
    Liu, Hongming
    Yu, Yu
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)
  • [7] Ship Target Detection Algorithm Based on Improved YOLOv5
    Zhou, Junchi
    Jiang, Ping
    Zou, Airu
    Chen, Xinglin
    Hu, Wenwu
    [J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2021, 9 (08)
  • [8] An Improved Distraction Behavior Detection Algorithm Based on YOLOv5
    Zhou, Keke
    Zheng, Guoqiang
    Zhai, Huihui
    Lv, Xiangshuai
    Zhang, Weizhen
    [J]. Computers, Materials and Continua, 2024, 81 (02): : 2571 - 2585
  • [9] Underwater Target Detection Algorithm Based on Improved YOLOv5
    Lei, Fei
    Tang, Feifei
    Li, Shuhan
    [J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2022, 10 (03)
  • [10] Research on improved algorithm for helmet detection based on YOLOv5
    Chun Shan
    HongMing Liu
    Yu Yu
    [J]. Scientific Reports, 13