A Lightweight Rice Pest Detection Algorithm Using Improved Attention Mechanism and YOLOv8

被引:2
作者
Yin, Jianjun [1 ,2 ]
Huang, Pengfei [1 ,2 ]
Xiao, Deqin [1 ,2 ]
Zhang, Bin [1 ,2 ]
机构
[1] South China Agr Univ, Coll Math & Informat, Guangzhou 510642, Peoples R China
[2] Minist Agr & Rural Affairs, Key Lab Smart Agr Technol Trop South China, Guangzhou 510642, Peoples R China
来源
AGRICULTURE-BASEL | 2024年 / 14卷 / 07期
关键词
pest detection; YOLOv8; attention mechanism; loss metric; lightweight model;
D O I
10.3390/agriculture14071052
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Intelligent pest detection algorithms are capable of effectively detecting and recognizing agricultural pests, providing important recommendations for field pest control. However, existing recognition models have shortcomings such as poor accuracy or a large number of parameters. Therefore, this study proposes a lightweight and accurate rice pest detection algorithm based on improved YOLOv8. Firstly, a Multi-branch Convolutional Block Attention Module (M-CBAM) is constructed in the YOLOv8 network to enhance the feature extraction capability for pest targets, yielding better detection results. Secondly, the Minimum Points Distance Intersection over Union (MPDIoU) is introduced as a bounding box loss metric, enabling faster model convergence and improved detection results. Lastly, lightweight Ghost convolutional modules are utilized to significantly reduce model parameters while maintaining optimal detection performance. The experimental results demonstrate that the proposed method outperforms other detection models, with improvements observed in all evaluation metrics compared to the baseline model. On the test set, this method achieves a detection average precision of 95.8% and an F1-score of 94.6%, with a model parameter of 2.15 M, meeting the requirements of both accuracy and lightweightness. The efficacy of this approach is validated by the experimental findings, which provide specific solutions and technical references for intelligent pest detection.
引用
收藏
页数:17
相关论文
共 50 条
  • [41] Lightweight Helmet Detection Algorithm Using an Improved YOLOv4
    Chen, Junhua
    Deng, Sihao
    Wang, Ping
    Huang, Xueda
    Liu, Yanfei
    SENSORS, 2023, 23 (03)
  • [42] FE-YOLO: A Lightweight Model for Construction Waste Detection Based on Improved YOLOv8 Model
    Yang, Yizhong
    Li, Yexue
    Tao, Maohu
    BUILDINGS, 2024, 14 (09)
  • [43] Attention Mechanism-Based Improved Lightweight Target Detection Algorithm
    Jin Mei
    Li Yihui
    Zhang Liguo
    Ma Zijian
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (04)
  • [44] A Universal Tire Detection Method Based on Improved YOLOv8
    Guo, Chi
    Chen, Mingxia
    Wu, Junjie
    Hu, Haipeng
    Huang, Luobing
    Li, Junjie
    IEEE ACCESS, 2024, 12 : 174770 - 174781
  • [45] Automotive adhesive defect detection based on improved YOLOv8
    Chunjie Wang
    Qibo Sun
    Xiaogang Dong
    Jia Chen
    Signal, Image and Video Processing, 2024, 18 : 2583 - 2595
  • [46] RVDR-YOLOv8: A Weed Target Detection Model Based on Improved YOLOv8
    Ding, Yuanming
    Jiang, Chen
    Song, Lin
    Liu, Fei
    Tao, Yunrui
    ELECTRONICS, 2024, 13 (11)
  • [47] Improved underwater transparent organism detection based on YOLOv8
    Li, Hongtao
    Guo, Fengyue
    Wu, Jihua
    Ren, Peng
    Luo, Cai
    OCEANS 2024 - SINGAPORE, 2024,
  • [48] Automotive adhesive defect detection based on improved YOLOv8
    Wang, Chunjie
    Sun, Qibo
    Dong, Xiaogang
    Chen, Jia
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (03) : 2583 - 2595
  • [49] Leather Defect Detection Based on Improved YOLOv8 Model
    Peng, Zirui
    Zhang, Chen
    Wei, Wei
    APPLIED SCIENCES-BASEL, 2024, 14 (24):
  • [50] Object detection of mural images based on improved YOLOv8
    Wang, Penglei
    Fan, Xin
    Yang, Qimeng
    Tian, Shengwei
    Yu, Long
    MULTIMEDIA SYSTEMS, 2025, 31 (01)