Desenvolvimento de um sistema de controle de tráfego inteligente baseado em visão computacional
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...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Estado: | Versión publicada |
| Fecha de publicación: | 2022 |
| País: | Brasil |
| Institución: | Universidade Federal do Rio Grande do Norte (UFRN) |
| Repositorio: | Repositório Institucional da UFRN |
| Idioma: | portugués |
| OAI Identifier: | oai:repositorio.ufrn.br:123456789/47158 |
| Acceso en línea: | https://repositorio.ufrn.br/handle/123456789/47158 |
| Access Level: | acceso abierto |
| Palabra clave: | OpenCV MOG2 YOLO-Tiny SSD MobileNetV2 Inteligência artificial |
| Sumario: | 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. |
|---|