Deep on Bogotá's streets

Technology has played an extremely important role in society during the last decades. It has brought great benefits to humanity creating some tools that have automatized processes-saving men time and effort of work. One situation where this occurs is with the video cam footage that cities produce each day using its traffic cameras. Each instant, these cameras are recording information about the cities' activities which can convey relevant information about topics of a district's agenda. Yet, making a person analyze hundreds of hours of video to extract useful information for decision making, is unfeasible. The following work documents the use of computer vision to detect a variety of classes in Bogotá by using its traffic cameras to derive insights to influence local transportation government decision making. As a reference, computer vision machine learned models from a distribution of data of a city to be considered from the first world, opposed to Bogotá, is used to compare such models in a variety of urban developments.

• Autores: Galvis Gutiérrez, Esteban
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2018
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/39324
• Acceso en línea: http://hdl.handle.net/1992/39324
• Palabra clave: Visión por computador; Cámaras de video; Tránsito local; Bogotá (Colombia); Ingeniería
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/