GAE-YOLO: a lightweight multimodal detection framework for tomato smart agriculture with edge computing
Frontiers in Plant Science · 19.11.2025 · 16
DOI: 10.3389/fpls.2025.1712432 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 19.11.2025. Verfasst von Xiaoke Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Basic Medical Sciences, Shandong Second Medical University, Weifang, Shandong, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The advancement of smart agriculture has witnessed increasing applications of computer vision in crop monitoring and management. However, existing approaches remain challenged by high computational complexity, limited real-time capability, and poor multi-task coordination in tomato cultivation scenarios.
Methods
To address these limitations, an intelligent tomato management system is proposed based on the Ghost-based Adaptive Efficient You Only Look Once (GAE-YOLO) algorithm. The lightweight architecture of the GAE-YOLO framework is achieved through the replacement of standard convolutional layers with Ghost Convolution (GhostConv) modules, while detection accuracy is significantly improved by the integration of both AReLU activation functions and Effective Intersection over Union (E-IoU) loss optimization. The system, implemented on a Jetson TX2 embedded platform, also incorporates ZED stereo vision for 3D localization and a PyQt6-based visualization platform.
Results
When implemented on Jetson TX2, the system achieving 93.5% mean Average Precision at 50% intersection over union (mAP@50) at 10.2 frames per second (FPS), which can be optimized to 27 FPS by employing TensorRT acceleration and 720p resolution for scenarios demanding higher throughput. Furthermore, it establishes standardized assessment systems for tomato maturity and yield prediction, and offers integrated modules for disease diagnosis and agricultural large language model consultation.
Discussion
This work establishes a new paradigm for edge computing in agriculture while providing critical technical support for smart farming development.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Basic Medical Sciences, Shandong Second Medical University, Weifang, Shandong, China.
- Weifang Key Laboratory of Collaborative Innovation of Intelligent Diagnosis and Treatment and Molecular Diseases, School of Basic Medical Sciences, Shandong Second Medical University, Weifang, Shandong, China.
- School of Public Health, Shandong Second Medical University, Weifang, Shandong, China.
Zitieren
APA
Liu, X., Teng, W., Yu, H., Yao, Z., Wang, C., Peng, Y., Han, X., & Liu, J. (2025). GAE-YOLO: a lightweight multimodal detection framework for tomato smart agriculture with edge computing. Frontiers in Plant Science, 16. https://doi.org/10.3389/fpls.2025.1712432
Vancouver
Liu X, Teng W, Yu H, Yao Z, Wang C, Peng Y, et al. GAE-YOLO: a lightweight multimodal detection framework for tomato smart agriculture with edge computing. Frontiers in Plant Science. 2025;16. doi:10.3389/fpls.2025.1712432
BibTeX
@article{Liu2025,
author = {Liu, Xiaoke and Teng, Wenjie and Yu, Haoran and Yao, Zhuoyi and Wang, Chengzhen and Peng, Yuzhong and Han, Xiaoqing and Liu, Jianming},
title = {GAE-YOLO: a lightweight multimodal detection framework for tomato smart agriculture with edge computing},
journal = {Frontiers in Plant Science},
year = {2025},
volume = {16},
doi = {10.3389/fpls.2025.1712432}
}
EUVIMED