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
  • [41] MSCA-YOLO: A YOLOv5-based Steel Defect Detection Method Enhanced with Multi-Scale Feature Extraction and Contextual Augmentation
    Wang, Yao
    Liang, Chengxin
    Wang, Xiao
    Liu, Yushan
    JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2024, 68 (04) : 29 - 29
  • [42] Multi-scale feature fusion-based lightweight dual stream transformer for detection of paddy leaf disease
    Kumar, Ajitesh
    Yadav, Dhirendra Prasad
    Kumar, Deepak
    Pant, Manu
    Pant, Gaurav
    ENVIRONMENTAL MONITORING AND ASSESSMENT, 2023, 195 (09)
  • [43] Multi-scale feature fusion-based lightweight dual stream transformer for detection of paddy leaf disease
    Ajitesh Kumar
    Dhirendra Prasad Yadav
    Deepak Kumar
    Manu Pant
    Gaurav Pant
    Environmental Monitoring and Assessment, 2023, 195
  • [44] Experimental Design of Steel Surface Defect Detection Based on MSFE-YOLO-An Improved YOLOV5 Algorithm with Multi-Scale Feature Extraction
    Li, Lin
    Zhang, Ruopeng
    Xie, Tunjun
    He, Yushan
    Zhou, Hao
    Zhang, Yongzhong
    ELECTRONICS, 2024, 13 (18)
  • [45] MAL-YOLO: a lightweight algorithm for target detection in side-scan sonar images based on multi-scale feature fusion and attention mechanism
    Cao, Yu
    Cui, Xiaodong
    Gan, Mingyi
    Wang, Yaxue
    Yang, Fanlin
    Huang, Yi
    INTERNATIONAL JOURNAL OF DIGITAL EARTH, 2024, 17 (01)