Home // GEOProcessing 2025, The Seventeenth International Conference on Advanced Geographic Information Systems, Applications, and Services // View article


Optimizing Picual Olive Variety Recognition through Deep Learning and Hyperspectral Imaging in Precision Agriculture

Authors:
Alba Gómez Liébana
Ruth María Córdoba Ortega
Juan José Cubillas Mercado
Lidia Ortega Alvarado

Keywords: Hyperspectral Imaging (HSI); Deep Learning (DL); Convolutional Neural Networks (CNN); Precision Agriculture; Olive Variety Classification; UAV-based Imaging; Spectral-Spatial Analysis; Arbequina; Picual.

Abstract:
The automated classification of olive varieties plays a crucial role in Precision Agriculture, enabling optimized resource allocation, improved irrigation strategies, and enhanced olive oil quality. This study explores the integration of Hyperspectral Imaging (HSI) and Deep Learning (DL) to classify olive varieties, focusing on Picual. Utilizing drone-acquired hyperspectral data, a Convolutional Neural Network (CNN) was employed to analyze leaf reflectance and extract spectral-spatial features with high accuracy. The Unmanned Aerial Vehicle (UAV)-based HSI system captures high-resolution spectral data, allowing for the detection of subtle differences in reflectance patterns that are imperceptible to traditional sensors. The study demonstrates that the proposed deep learning approach achieves an accuracy of approximately 90% in classifying olive varieties, significantly outperforming traditional machine learning methods. These findings highlight the potential of hyperspectral deep learning in agricultural applications, paving the way for scalable, efficient, and sustainable orchard management.

Pages: 11 to 16

Copyright: Copyright (c) IARIA, 2025

Publication date: May 18, 2025

Published in: conference

ISSN: 2308-393X

ISBN: 978-1-68558-269-2

Location: Nice, France

Dates: from May 18, 2025 to May 22, 2025