МОДЕЛІ РОЗПОДІЛЕНОГО ГЛИБОКОГО НАВЧАННЯ ДЛЯ ТОЧНОГО ВИЗНАЧЕННЯ БУР’ЯНІВ НА ПОЛЯХ
DOI:
https://doi.org/10.30890/2709-2313.2025-43-01-003Ключові слова:
distributed deep learning, weed detection, federated learning, precision agriculture, computer vision, IoU, F1-scoreАнотація
This paper presents distributed deep learning models for accurate weed detection in agricultural crops such as wheat, soybean, corn, and potato.The study explores federated learning architectures combining ResNet50, U-Net++, Swin Transformer, and YOLOv8Посилання
Olsen, A. et al. DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning. Scientific Reports, 2019.
Bah, M. D. et al. CropWeed Dataset: Open Dataset for Crop and Weed Detection. Agriculture, 2020.
Dos Santos Ferreira, A. et al. Weed Detection in Soybean Crops Using ConvNets. Computers and Electronics in Agriculture, 2019.
Kamilaris, A., Prenafeta-Boldú, F. Deep Learning in Agriculture: A Survey. Computers and Electronics in Agriculture, 2022.
Zhang, L. et al. Multi-Crop Weed Detection with Transfer Learning. Plant Methods, 2024.
Li, X. et al. Federated Learning for Smart Agriculture. IEEE IoT Journal, 2023.
Wang, Y. et al. Distributed Deep Learning for Precision Weed Control. Sensors, 2023.
Zhao, H. et al. Swin Transformer for Crop-Weed Segmentation. Frontiers in Plant Science, 2025.
Опубліковано
Як цитувати
Ліцензія
Авторське право (c) 2025 Автори
Ця робота ліцензується відповідно до Creative Commons Attribution 4.0 International License.
