Normalized Difference Vegetation Index Prediction for Blueberry Plant Health from RGB Images: A Clustering and Deep Learning Approach
AgriEngineering · 16.12.2024 · 6 (4) · 4831-4850
DOI: 10.3390/agriengineering6040276 ↗Kurz gefasst
Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 16.12.2024. Verfasst von A. G. M. Zaman und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Estonian University of Life Sciences, Estonian Research Council.
Abstract (Originalsprache)
In precision agriculture (PA), monitoring individual plant health is crucial for optimizing yields and minimizing resources. The normalized difference vegetation index (NDVI), a widely used health indicator, typically relies on expensive multispectral cameras. This study introduces a method for predicting the NDVI of blueberry plants using RGB images and deep learning, offering a cost-effective alternative. To identify individual plant bushes, K-means and Gaussian Mixture Model (GMM) clustering were applied. RGB images were transformed into the HSL (hue, saturation, lightness) color space, and the hue channel was constrained using percentiles to exclude extreme values while preserving relevant plant hues. Further refinement was achieved through adaptive pixel-to-pixel distance filtering combined with the Davies–Bouldin Index (DBI) to eliminate pixels deviating from the compact cluster structure. This enhanced clustering accuracy and enabled precise NDVI calculations. A convolutional neural network (CNN) was trained and tested to predict NDVI-based health indices. The model achieved strong performance with mean squared losses of 0.0074, 0.0044, and 0.0021 for training, validation, and test datasets, respectively. The test dataset also yielded a mean absolute error of 0.0369 and a mean percentage error of 4.5851. These results demonstrate the NDVI prediction method’s potential for cost-effective, real-time plant health assessment, particularly in agrobotics.
Förderung
- Estonian University of Life Sciences
- Estonian Research Council
Zitieren
APA
Zaman, A. G. M., Roy, K., & Olt, J. (2024). Normalized Difference Vegetation Index Prediction for Blueberry Plant Health from RGB Images: A Clustering and Deep Learning Approach. AgriEngineering, 6(4), 4831-4850. https://doi.org/10.3390/agriengineering6040276
Vancouver
Zaman AGM, Roy K, Olt J. Normalized Difference Vegetation Index Prediction for Blueberry Plant Health from RGB Images: A Clustering and Deep Learning Approach. AgriEngineering. 2024;6(4):4831-4850. doi:10.3390/agriengineering6040276
BibTeX
@article{Zaman2024,
author = {Zaman, A. G. M. and Roy, Kallol and Olt, Jüri},
title = {Normalized Difference Vegetation Index Prediction for Blueberry Plant Health from RGB Images: A Clustering and Deep Learning Approach},
journal = {AgriEngineering},
year = {2024},
volume = {6},
number = {4},
pages = {4831--4850},
doi = {10.3390/agriengineering6040276}
}
EUVIMED