dc.contributor | Barroca Filho, Itamir de Morais | |
dc.contributor | http://lattes.cnpq.br/1860470288478197 | |
dc.contributor | http://lattes.cnpq.br/1093675040121205 | |
dc.contributor | Silva, Gustavo Girão Barreto da | |
dc.contributor | http://lattes.cnpq.br/9491033611706611 | |
dc.contributor | Fontes, Aluisio Igor Rego | |
dc.contributor | Araújo, Daniel Sabino Amorim de | |
dc.contributor | http://lattes.cnpq.br/4744754780165354 | |
dc.creator | Cortez, Diogo Eugênio da Silva | |
dc.date.accessioned | 2022-05-10T23:21:07Z | |
dc.date.accessioned | 2022-10-06T12:32:15Z | |
dc.date.available | 2022-05-10T23:21:07Z | |
dc.date.available | 2022-10-06T12:32:15Z | |
dc.date.created | 2022-05-10T23:21:07Z | |
dc.date.issued | 2022-03-04 | |
dc.identifier | CORTEZ, Diogo Eugênio da Silva. Desenvolvimento de um sistema de controle de tráfego inteligente baseado em visão computacional. 2022. 109f. Dissertação (Mestrado Profissional em Tecnologia da Informação) - Instituto Metrópole Digital, Universidade Federal do Rio Grande do Norte, Natal, 2022. | |
dc.identifier | https://repositorio.ufrn.br/handle/123456789/47158 | |
dc.identifier.uri | http://repositorioslatinoamericanos.uchile.cl/handle/2250/3954302 | |
dc.description.abstract | The vehicle fleet in Rio Grande do Norte has increased by 250 thousand vehicles in
the last 5, or 7% per year. Considering that 80% of the population lives in urban areas,
traffic management is becoming one of the most important issues today. The traffic
lights that the flow operates with fixed time (STF) to control the vehicles are not efficient
in all traffic situations. At that time, in the literature, many studies have been published
based on vehicle density as a solution to improve traffic flow. With the advancement of
Computer Vision (VC) technologies, such as techniques for detecting and classifying
moving objects and the requirement of little computational power to perform tasks, it
was possible to develop an intelligence control system based on VC. This low-cost
solution was implemented for the STF camera system and the logical network
infrastructure already presented in the municipalities. A computer, equipped with an
application, captured images of traffic at the traffic light, contoured the vehicles and
calculated the time required for them to cross. The Raspberry Pi 3 controls the traffic
lights. Compared to the STF, there was a gain of up to 33% in traffic flow. A VC was
used to control what they cross or traffic lights, to alert about congestion, make
decisions and also create a database that can be used for decision-making by the
district bodies on the roads. | |
dc.publisher | Universidade Federal do Rio Grande do Norte | |
dc.publisher | Brasil | |
dc.publisher | UFRN | |
dc.publisher | PROGRAMA DE PÓS-GRADUAÇÃO EM TECNOLOGIA DA INFORMAÇÃO | |
dc.rights | Acesso Aberto | |
dc.subject | OpenCV | |
dc.subject | MOG2 | |
dc.subject | YOLO-Tiny | |
dc.subject | SSD | |
dc.subject | MobileNetV2 | |
dc.subject | Inteligência artificial | |
dc.title | Desenvolvimento de um sistema de controle de tráfego inteligente baseado em visão computacional | |
dc.type | masterThesis | |