Navegando por Assunto "Processamento de imagem"

Agora exibindo 1 - 3 de 3

Otimização dos tempos de um semáforo por processamento de imagem e controladores
(Centro Universitário do Estado do Pará, 2019) Silva, Raul Vitor Mesquita da; Corrêa Filho, Sérgio Teixeira; Brasil, Vitor Henrique Morais; Nascimento, Polyana Santos Fonseca; http://lattes.cnpq.br/6889523334917369; Brito, Itamar Jorge Vilhena de; http://lattes.cnpq.br/5143837732124006; Mendes, Marcelo Pinto da Costa; http://lattes.cnpq.br/3099832904134964
This course completion work has as main objective to provide an improvement to the flow of traffic with the optimization of traffic light times, through a digital image processing application and controllers. So that it is possible to create intelligent traffic lights that can contribute to a better traffic in big cities. The whole system has a set of scripts that use the Python language and its specific modules to perform different functions, such as digitally processing an urban traffic video, analyzing the state of the road and determining its state as light, moderate, intense flow and finally, to perform the optimization of the green signal time of a certain semaphore.
Portfólio da trajetória de graduação em engenharia de computação de Mayana Pontes
(Centro Universitário do Estado do Pará, 2020-07-16) Pontes, Mayana Miquelli Cardoso; Santos, Michelle Bitar Lelis dos; http://lattes.cnpq.br/1208797288539861; Ribeiro, Moshe Dayan Sousa; http://lattes.cnpq.br/5200296393526606
This work contains technical information about four products and learning processes by the author Mayana Pontes, who is about to graduate in Computer Engineering at CESUPA. The products and learning processes are the "Transportador Pessoal" in its two versions, the "Coletor Aquático de Resíduos Sólidos", the "Estação EcoMoobi" and the Internship at the "Instituto do Homem e Meio Ambiente da Amazônia - IMAZON". As it is a portfolio, each activity will be approached critically by the author, demonstrating her personal development and contribution to each one of them. Technical details of each project and an action plan are also given to show her learning and possible improvements in each project.
Utilização de inteligência artificial para mapeamento de estradas não oficiais na Amazônia
(Centro Universitário do Estado do Pará, 2020) Botelho Junnior, Jonas Paiva; Ferreira, Fábio dos Santos; http://lattes.cnpq.br/4845857829374774; Ribeiro, Moshe Dayan Sousa; http://lattes.cnpq.br/5200296393526606; Teixeira, Otávio Noura; http://lattes.cnpq.br/5784356232477760
Mapping unofficial roads in the Amazon has a really important role in understanding the dynamics of access and utilization of the Biome. The Amazon Institute of People and the Environment (IMAZON), had been conducting this procedure in a manual way, making this precise process, longstading. With that in mind, this work propose a new way of making this mapping, using artificial intelligence and remote sensing technologies for accelerate the detecting of roads, making possible to tracking constantly activities in the Amazon. The model of neural net created to accomplish this task was made using a modified U-Net and using Google’s training and prediction services. The model was tested with five locations inside state of Pará, all of those with 1200 km² of area, and it produced promising results, which indicate the capacity of the network de make predictions over satellites images and identify the existence of roads, being capable of detect different formations - Dendritic, geometric and “Fishbone”. Besides that, another test to compare results between two types of images with different resolutions was conducted, showing improvement with the rising of the resolution, when made with the right input conditions. At last, this work accomplished its objective, presenting a new method to map unofficial roads in the Amazon, this being faster, less expensive and capable of keep up with the dynamic of the region.