A Federated Learning-Based Object Detection System with Edge–Cloud Collaboration

Authors

  • Yunsheng Wang School of Electronic Information Engineering, Inner Mongolia University
  • Xiangning Chen School of Electronic Information Engineering, Inner Mongolia University
  • Shubin Wang School of Electronic Information Engineering, Inner Mongolia University

Keywords:

Federated Learning, Cloud-Edge Collaboration, YOLOv11

Abstract

With the development of smart agriculture, field object detection has become a key component in improving management efficiency. This paper proposes and implements a cloud-edge collaborative federated learning system for object detection, using a field weed dataset as a case study. The system employs a federated learning framework to enable parallel training across multiple edge devices and integrates the YOLOv11 model to perform collaborative training on several Jetson Nano devices. To enhance global model performance and convergence speed, only model parameters that meet predefined accuracy thresholds and pass a target filtering mechanism are uploaded to the cloud for aggregation. On the client side, a PyQt5-based graphical user interface is developed to support inference on images, videos, and real-time camera feeds.In the experimental evaluation, we compared federated training across multiple edge devices with centralized training on a single device. The results show that federated learning outperforms centralized training across several key performance metrics. Specifically, precision improved from 77.89% to 82.17%, recall increased from 72.25% to 73.56%, and mean average precision (mAP) rose from 77.82% to 81.45%. These findings demonstrate that federated learning can significantly enhance model accuracy and generalization while keeping data localized.

References

Redmon J, Farhadi A. YOLOv4: Optimal Speed and Accuracy of Object Detection [EB/OL]. arXiv:2004.10934.

Yang H, Liu M, Wu X, et al. FedVision: An Online Visual Object Detection Platform Powered by Federated Learning [C]//AAAI 2021.

Zhou Y, Wu T, et al. FedDet: A Federated Learning Framework for Object Detection [C]//NeurIPS FL Workshop, 2021.

Li T, Sahu A K, Talwalkar A, Smith V. Federated Learning: Challenges, Methods, and Future Directions[J]. IEEE Signal Processing Magazine, 2020.

Kairouz P, et al. Advances and Open Problems in Federated Learning[J]. Foundations and Trends® in Machine Learning, 2021.

Chen M, Yang J, et al. A Survey on Federated Learning in Edge Computing: Research Problems and Solutions[J]. IEEE Network, 2021.

Aidil Saputra Kirsan, Kosuke Takano, Sallie Trixie Zebada Mansurina.EksPy: A new Python framework for developing graphical user interface based PyQt5[J]. International Journal of Electrical and Computer Engineering (IJECE), 2024, 14(1): 520–531. DOI: 10.11591/ijece.v14i1.pp520-531.

Zheng, Y., Zhou, G., & Lu, B. Rebar Cross-section Detection Based on Improved YOLOv5s Algorithm[J]. Innovation & Technology Advances, 2023, 1(1): 1–6. https://doi.org/10.61187/ita.v1i1.1

Zhao, X., Zhang, L., & Hu, Z. Smart warehouse track identification based on Res2Net-YOLACT+HSV[J]. Innovation & Technology Advances, 2023, 1(1): 7–11. https://doi.org/10.61187/ita.v1i1.2

Downloads

Published

2025-09-30

How to Cite

Wang, Y., Chen, X., & Wang, S. (2025). A Federated Learning-Based Object Detection System with Edge–Cloud Collaboration. Journal of Theory and Practice in Engineering and Technology, 2(5), 10–18. Retrieved from https://woodyinternational.com/index.php/jtpet/article/view/298