Detecção de ciclistas em cenário urbano por meio de visão computacional em dispositivos móveis

• Ano de defesa: 2024
• Autor(a) principal: Santos, Leandro Alves dos
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Curitiba; Brasil; Programa de Pós-Graduação em Computação Aplicada; UTFPR
• Palavras-chave em Português: Ciclistas; Tráfego urbano; Levantamentos de trânsito; Aprendizado profundo (Aprendizado do computador); Raspberry Pi (Computador); Visão por computador; Sistemas inteligentes de veículos rodoviários; Cyclists; City traffic; Traffic surveys; Deep learning (Machine learning); Raspberry Pi (Computer); Computer vision; Intelligent transportation systems; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO; Ciência da Computação
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/34427

Automatically detecting and counting cyclists in urban scenarios is a task in intelligent transportation systems and smart cities that enables the generation of important structured data. This data contributes to understanding the dynamics of cyclists’ use of the urban space and guides the development of public policies for cycling mobility and traffic safety. In this study, we propose an embedded system for cyclist detection and counting, aiming to be a lightweight solution using computer vision and deep learning methods. It is characterized by low energy consumption and easy handling, based on the Raspberry Pi 4 platform and the Edge TPU Coral accelerator. The developed system achieved an F1-score of 0.9137 for processing pre-recorded video. In field counting experiments, where the system’s count was compared to human count, it resulted in counting performance between 78.3% and 82.2% in relation to visual counting.