RNC Plugin: Plugin de QGIS para clasificar imágenes satelitales mediante redes neuronales convolucionales

Abstract

With the advance of satellite programs in resolution, either spatial or radiometric, the development of new techniques based on Machine Learning and Deep Learning algorithms are constantly emerging. In recent years the interest in automating processes and obtaining optimal supervised classifications has led to the creation of different algorithms that allow a closer approximation to the reality on the ground, thus, we present a plugin that classifies the satellite images given by the user, according to the classes indicated, from the Deep Learning algorithm Convolutional Neural Networks in the desktop software QGIS in order to facilitate quick access to the classification of satellite images.