Journal of Integrative Agriculture ›› 2025, Vol. 24 ›› Issue (7): 2749-2769.DOI: 10.1016/j.jia.2024.12.017

• • 上一篇    下一篇

GBiDC-PEST： 一种用于多类微小害虫实时检测和移动平台部署的新型轻量级模型

  

  • 收稿日期:2024-07-19 修回日期:2024-12-16 接受日期:2024-10-24 出版日期:2025-07-20 发布日期:2025-06-17

GBiDC-PEST: A novel lightweight model for real-time multiclass tiny pest detection and mobile platform deployment

Weiyue Xu1, 2, Ruxue Yang1, Raghupathy Karthikeyan3, Yinhao Shi1, Qiong Su3#   

  1. 1 Changzhou University, Changzhou 213164, China

    2 Department of Biological and Agricultural Engineering, Texas A&M University, College Station, Texas 77843, United States

    3 Department of Agricultural Sciences, Clemson University, Clemson, South Carolina 29634, United States

  • Received:2024-07-19 Revised:2024-12-16 Accepted:2024-10-24 Online:2025-07-20 Published:2025-06-17
  • About author:Weiyue Xu, Mobile: +86-15051971896, E-mail: wyxu@cczu.edu.cn; #Correspondence Qiong Su, Tel: +1-979-4224883, E-mail: qsu@clemson.edu
  • Supported by:

    Weiyue Xu acknowledges the support of the Natural Science Foundation of Jiangsu Province, China (BK20240977), the China Scholarship Council (201606850024), the National High Technology Research and Development Program of China (2016YFD0701003), and the Postgraduate Research & Practice Innovation Program of Jiangsu Province, China (SJCX23_1488). 

PDF

摘要：

基于深度学习的智能识别算法可解决劳动密集型人工害虫检测问题，但其移动设备上的部署通常受限于高计算需求。本文开发了基于GBiDC-PEST改进轻量级检测算法的移动应用程序，其结合了You Only Look Once （YOLO）系列单阶段架构用于实时检测四种微小害虫（小麦螨，甘蔗蚜虫，小麦蚜虫和水稻飞虱）。改进的GBiDC-PEST模型包括GhostNet（用于轻量级特征提取和主干架构优化），双向特征金字塔网络（BiFPN，用于增强多尺度特征融合），DWConv层（用于减少计算负荷的深度卷积），以及卷积注意力模块（CBAM，用于精确特征聚焦）。GBiDC-PEST使用覆盖多种田间环境的多靶点农业微小害虫数据集（Tpest-3960）进行训练和验证，结果显示：（1）模型尺寸被显著减小（2.8 MB，为原始模型的20%），小于YOLO系列（v5 ~ v10）；（2）检测精度高于YOLOv10n和v10s；（3）检测速度优于v8s、v9c、v10m和v10b；（4）复杂背景下的害虫检测性能获得提高，对小麦螨和水稻飞虱的检测准确率比原始模型增加了4.5-7.5%（Android部署实验）。本研究提出的GBiDC-PEST模型及其移动端部署工作为大田现场的快速识别、定位微小害虫提供了强大技术支撑，为在各种农业环境中有效监测、计数和控制有害生物提供了有价值的参考。

Abstract:

Deep learning-based intelligent recognition algorithms are increasingly recognized for their potential to address the labor-intensive challenge of manual pest detection. However, their deployment on mobile devices has been constrained by high computational demands. Here, we developed GBiDC-PEST, a mobile application that incorporates an improved, lightweight detection algorithm based on the you only look once (YOLO) series single-stage architecture, for real-time detection of four tiny pests (wheat mites, sugarcane aphids, wheat aphids, and rice planthoppers). GBiDC-PEST incorporates several innovative modules, including GhostNet for lightweight feature extraction and architecture optimization by reconstructing the backbone, the Bi-directional Feature Pyramid Network (BiFPN) for enhanced multiscale feature fusion, Depthwise convolution (DWConv) layers to reduce computational load, and the Convolutional Block Attention Module (CBAM) to enable precise feature focus. The newly developed GBiDC-PEST was trained and validated using a multitarget agricultural tiny pest dataset (Tpest-3960) that covered various field environments. GBiDC-PEST (2.8 MB) significantly reduced the model size to only 20% of the original model size, offering a smaller size than the YOLO series (v5 ~ v10), higher detection accuracy than YOLOv10n and v10s, and faster detection speed than v8s, v9c, v10m and v10b. In Android deployment experiments, GBiDC-PEST demonstrated enhanced performance in detecting pests against complex backgrounds, and the accuracy for wheat mites and rice planthoppers was improved by 4.5-7.5% compared with the original model. The GBiDC-PEST optimization algorithm and its mobile deployment proposed in this study offer a robust technical framework for the rapid, onsite identification and localization of tiny pests. This advancement provides valuable insights for effective pest monitoring, counting, and control in various agricultural settings.

Key words: mobile counting , real-time processing , pest detection , tiny object identification , algorithm deployment