Bibliographic citations
Flores, D., (2021). Clasificación de cultivos de quinua orgánica mediante el uso de imágenes aéreas multiespectrales y técnicas de aprendizaje automáticoClassification of organic quinoa crops using
multispectral aerial imagery and machine learning techniques [Pontificia Universidad Católica del Perú]. http://hdl.handle.net/20.500.12404/20855
Flores, D., Clasificación de cultivos de quinua orgánica mediante el uso de imágenes aéreas multiespectrales y técnicas de aprendizaje automáticoClassification of organic quinoa crops using
multispectral aerial imagery and machine learning techniques []. PE: Pontificia Universidad Católica del Perú; 2021. http://hdl.handle.net/20.500.12404/20855
@mastersthesis{renati/12900,
title = "Clasificación de cultivos de quinua orgánica mediante el uso de imágenes aéreas multiespectrales y técnicas de aprendizaje automático;Classification of organic quinoa crops using
multispectral aerial imagery and machine learning techniques",
author = "Flores Espinoza, Donato Andrés",
publisher = "Pontificia Universidad Católica del Perú",
year = "2021"
}
Crop mapping is an essential tool for agricultural management and food security for which remote sensing data can be used. This study focuses on the use of machine learning techniques to classify quinoa crops from multispectral aerial images. Spectral reflectance of five optical bands are used for determining classification models which are evaluated for different phenological stages of quinoa. Decision Trees, Discriminant Analysis, Support Vector Machines, K nearest Neighbor, Ensemble Classifiers, deep learning methods Segnet and Unet were explored. Training datasets were obtained from quinoa crop fields locations at Cabana in the Puno region of Peru. An unmanned aircraft system (UAS) was used to acquire the multispectral images from an altitude of 50 meters. Results show that deep learning techniques outperform the other techniques in the classification task.
This item is licensed under a Creative Commons License