Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture
This work addresses efficient weed control for farmers by improving segmentation accuracy and computational efficiency, though it is incremental as it builds on existing hybrid methods.
The paper tackled crop-weed segmentation for precision agriculture by proposing a lightweight transformer-CNN hybrid that processes multispectral imagery, achieving a mean IoU of 78.88% and outperforming RGB-only models by 15.8 percentage points.
Efficient crop-weed segmentation is critical for site-specific weed control in precision agriculture. Conventional CNN-based methods struggle to generalize and rely on RGB imagery, limiting performance under complex field conditions. To address these challenges, we propose a lightweight transformer-CNN hybrid. It processes RGB, Near-Infrared (NIR), and Red-Edge (RE) bands using specialized encoders and dynamic modality integration. Evaluated on the WeedsGalore dataset, the model achieves a segmentation accuracy (mean IoU) of 78.88%, outperforming RGB-only models by 15.8 percentage points. With only 8.7 million parameters, the model offers high accuracy, computational efficiency, and potential for real-time deployment on Unmanned Aerial Vehicles (UAVs) and edge devices, advancing precision weed management.