Utilizing convolutional neural networks (CNN) and U-Net architecture for precise crop and weed segmentation in agricultural imagery: A deep learning approach

Mughair Aslam BHATTI, M. S. SYAM, Huafeng CHEN, Yurong HU, Wai Keung LI, Zeeshan ZEESHAN, Yasser A. ALI, Nadia SARHAN

Research output: Contribution to journalArticlespeer-review

Abstract

This study presents the implementation and evaluation of a convolutional neural network (CNN) based image segmentation model using the U-Net architecture for forest image segmentation. The proposed algorithm starts by preprocessing the datasets of satellite images and corresponding masks from a repository source. Data preprocessing involves resizing, normalizing, and splitting the images and masks into training and testing datasets. The U-Net model architecture, comprising encoder and decoder parts with skip connections, is defined and compiled with binary cross-entropy loss and Adam optimizer. Training includes early stopping and checkpoint saving mechanisms to prevent overfitting and retain the best model weights. Evaluation metrics such as Intersection over Union (IoU), Dice coefficient, pixel accuracy, precision, recall, specificity, and F1-score are computed to assess the model's performance. Visualization of results includes comparing predicted segmentation masks with ground truth masks for qualitative analysis. The study emphasizes the importance of training data size in achieving accurate segmentation models and highlights the potential of U-Net architecture for forest image segmentation tasks. Copyright © 2024 Elsevier B.V.

Original languageEnglish
Article number100465
JournalBig Data Research
Volume36
Early online dateMay 2024
DOIs
Publication statusPublished - May 2024

Citation

Bhatti, M. A., Syam, M. S., Chen, H., Hu, Y., Li, W. K., Zeeshan, Z., Ali, Y. A., & Sarhan, N. (2024). Utilizing convolutional neural networks (CNN) and U-Net architecture for precise crop and weed segmentation in agricultural imagery: A deep learning approach. Big Data Research, 36, Article 100465. https://doi.org/10.1016/j.bdr.2024.100465