Deep Learning for Computer Vision in Smart Cities

Abstract

The Digital Age has caused a rapid shift from traditional industry to an economy mainly based upon information technology. According to recent studies, 74 zettabytes (ZB) of data have been generated, captured and replicated in the world in 2021, with video accounting for 82% of internet traffic. This figure has been amplified due to the coronavirus pandemic, and it is expected to keep increasing, reaching 149 ZB by 2024. Processing this impressive amount of information is one of the main scientific challenges of our time. Against this backdrop, Machine Learning (ML) and two related paradigms have emerged: big data and deep learning. These disciplines take advantage of mathematical optimization methods, bioinspiration and modern Graphics Processing Units (GPUs) to manage large datasets efficiently and effectively.Cities from around the world have adapted the previous methods to make use of the newly available data, promoting themselves as "smart". Apart from aiming to integrate I would like to express my gratitude to all those who, with their support, encouragement and kindness; have made this great milestone of my career possible -this dissertation is dedicated to you.First of all, I must thank my supervisors, Sara Rodríguez and Pablo Chamoso, for their dedication and guidance. This thesis wouldn't have been possible without their valuable support. Secondly, I want to express my profound gratitude to John A. Lee and the rest of the MIRO Machine Learning Group from the Université catholique de Louvain for their overwhelming hospitality during my research stay in their lab. The months I spent working with them greatly enriched my scientific capabilities and the research which lead to this dissertation. I also want to thank Besik Dundua for his earnest hospitality, valuable pieces of advice and for going out of his way to welcome me. His interest in quality research, not quantity, taught me to deal with the state of the art as an old friend with whom to have an enjoyable conversation, instead of as a intimidating professor I must learn from. The months I spent under your supervision truly touched me. Moreover, I also want to thank my colleagues at BISITE research group for their company and friendship over the years. May the future take us apart, may the destiny bring us together.Lastly, I am grateful to my encouraging relatives, my fellow professors of "Programación II" and my hard-working students.