Caracterización de Tráfico Basada en Deep Learning para Smart Cities Fase 1

General objective Characterize the traffic around the UPS South Campus using Deep Learning Justification Several environmental and mobility problems in a SC are closely related to vehicular traffic. For this reason, the characterization of a city's traffic is of great interest for various investigations. In the Metropolitan District of Quito (DMQ) 62% of PM2.5 pollution is generated by the vehicle fleet (Oviedo, 2015). In addition, information on vehicular traffic can be used to generate noise pollution models (Bravo L., 2018). On the other hand, this information is very useful on urban planning issues such as: · road design · road maintenance planning · Evaluation of transport systems · Road maintenance programs · Sustainable mobility plans · Support for decision-making one of the objectives of a SC is to implement intelligent traffic control systems that reduce vehicular load, environmental pollution and social degradation problems (Jiri, 2018). In the case of the DMQ, the information collected and the results of the investigation could be the basis for proposing mobility policies. And in the future, it will serve to develop the activities of the Mobility Management Center (CGM), an entity in charge of mitigating and optimizing displacement in the DMQ.