Seguí Mesquida, SantiVitrià i Marca, JordiBeltrán Segarra, MarcCompanys Rufián, Albert2019-05-202019-05-202018-07-03https://hdl.handle.net/2445/133457Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2018, Tutor: Santi Seguí Mesquida i Jordi Vitrià i Marca[en] A great amount of the interesting information captured by aerial imagery is still not being used given how labour intensive the processing and annotation of these images is. Despite this, improvements in technology and advancements in the computer vision field have made available tools and techniques that can help make this process semi-automatized. In this project we focus on the use case of extracting roads from aerial imagery. For this purpose, we will study and compare models based on image segmentation using deep learning and RoadTracer, a revolutionary model proposed recently.67 p.application/pdfengcc-by-nc-nd (c) Marc Beltrán Segarra i Albert companys Rufián, 2018codi: GPL (c) Marc Beltrán Segarra i Albert companys Rufián, 2018, 2018http://creativecommons.org/licenses/by-nc-nd/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlAprenentatge automàticServeis de geolocalitzacióTreballs de fi de màsterFotografia aèriaProcessament digital d'imatgesXarxes neuronals (Informàtica)Machine learningLocation-based servicesMaster's thesesAerial photographyDigital image processingNeural networks (Computer science)info:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccess