YOLO-FMDI: A Lightweight YOLOv8 Focusing on a Multi-Scale Feature Diffusion Interaction Neck for Tomato Pest and Disease Detection

被引:5
|
作者
Sun, Hao [1 ,2 ]
Nicholaus, Isack Thomas [2 ]
Fu, Rui [1 ]
Kang, Dae-Ki [2 ]
机构
[1] Weifang Univ Sci & Technol, Shandong Facil Hort Bioengn Res Ctr, Weifang 262700, Peoples R China
[2] Dongseo Univ, Dept Comp Engn, 47 Jurye Ro, Busan 47011, South Korea
基金
新加坡国家研究基金会;
关键词
object detection; deep learning; YOLOv8; FMDI; MFN; UIB; tomato pests and diseases;
D O I
10.3390/electronics13152974
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
At the present stage, the field of detecting vegetable pests and diseases is in dire need of the integration of computer vision technologies. However, the deployment of efficient and lightweight object-detection models on edge devices in vegetable cultivation environments is a key issue. To address the limitations of current target-detection models, we propose a novel lightweight object-detection model based on YOLOv8n while maintaining high accuracy. In this paper, (1) we propose a new neck structure, Focus Multi-scale Feature Diffusion Interaction (FMDI), and inject it into the YOLOv8n architecture, which performs multi-scale fusion across hierarchical features and improves the accuracy of pest target detection. (2) We propose a new efficient Multi-core Focused Network (MFN) for extracting features of different scales and capturing local contextual information, which optimizes the processing power of feature information. (3) We incorporate the novel and efficient Universal Inverted Bottleneck (UIB) block to replace the original bottleneck block, which effectively simplifies the structure of the block and achieves the lightweight model. Finally, the performance of YOLO-FMDI is evaluated through a large number of ablation and comparison experiments. Notably, compared with the original YOLOv8n, our model reduces the parameters, GFLOPs, and model size by 18.2%, 6.1%, and 15.9%, respectively, improving the mean average precision (mAP50) by 1.2%. These findings emphasize the excellent performance of our proposed model for tomato pest and disease detection, which provides a lightweight and high-precision solution for vegetable cultivation applications.
引用
收藏
页数:12
相关论文
共 45 条
  • [31] Lightweight Underwater Object Detection Based on YOLO v4 and Multi-Scale Attentional Feature Fusion
    Zhang, Minghua
    Xu, Shubo
    Song, Wei
    He, Qi
    Wei, Quanmiao
    REMOTE SENSING, 2021, 13 (22)
  • [32] YOLO-MIF: Improved YOLOv8 with Multi-Information fusion for object detection in Gray-Scale images
    Wan, Dahang
    Lu, Rongsheng
    Hu, Bingtao
    Yin, Jiajie
    Shen, Siyuan
    Xu, Ting
    Lang, Xianli
    ADVANCED ENGINEERING INFORMATICS, 2024, 62
  • [33] Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion
    Wang, Yong
    Zhang, Panxing
    Tian, Shuang
    FRONTIERS IN PLANT SCIENCE, 2024, 15
  • [34] Light-YOLO: a lightweight detection algorithm based on multi-scale feature enhancement for infrared small ship target
    Tang, Ji
    Hu, Xiao-Min
    Jeon, Sang-Woon
    Chen, Wei-Neng
    COMPLEX & INTELLIGENT SYSTEMS, 2025, 11 (02)
  • [35] DAMI-YOLOv8l: A multi-scale detection framework for light-trapping insect pest monitoring
    Chen, Xiao
    Yang, Xinting
    Hu, Huan
    Li, Tianjun
    Zhou, Zijie
    Li, Wenyong
    ECOLOGICAL INFORMATICS, 2025, 86
  • [36] Optimizing tomato detection and counting in smart greenhouses: A lightweight YOLOv8 model incorporating high- and low-frequency feature transformer structures
    Tian, Zhimin
    Hao, Huijuan
    Dai, Guowei
    Li, Yajuan
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2024,
  • [37] YOLOv8-AFA: A photovoltaic module fault detection method based on multi-scale feature fusion
    Chen, Wei
    Lu, Jinyu
    Pei, Tingting
    Yuan, Guojing
    ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2025, 47 (01) : 657 - 676
  • [38] CRGF-YOLO: An Optimized Multi-Scale Feature Fusion Model Based on YOLOv5 for Detection of Steel Surface Defects
    Yu, Tao
    Luo, Xu
    Li, Qiang
    Li, Lei
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2024, 17 (01)
  • [39] Dense Buddha head object detection and counting YOLOv8 network based on multi-scale attention and data augmentation fusion
    Li, Yang
    Wang, Yalun
    Sui, Dong
    Guo, Maozu
    NPJ HERITAGE SCIENCE, 2025, 13 (01):
  • [40] Defect detection in automotive glass based on modified YOLOv5 with multi-scale feature fusion and dual lightweight strategy
    Chen, Zhe
    Huang, Shihao
    Lv, Hui
    Luo, Zhixue
    Liu, Jinhao
    VISUAL COMPUTER, 2024, 40 (11): : 8099 - 8112