Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Galymzhankyzy, Zeynep, Martinson, Eric
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915299827122176
author Galymzhankyzy, Zeynep
Martinson, Eric
author_facet Galymzhankyzy, Zeynep
Martinson, Eric
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07444
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture
Galymzhankyzy, Zeynep
Martinson, Eric
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
I.4.6
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.
title Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
I.4.6
url https://arxiv.org/abs/2505.07444