Rede de sensores sem fio de longo alcance aplicada a reconhecimento facial por imagem

• Ano de defesa: 2022
• Autor(a) principal: Rodrigues, Vítor José Costa
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal da Paraíba; Brasil; Engenharia Elétrica; Programa de Pós-Graduação em Engenharia Elétrica; UFPB
• Palavras-chave em Português: Redes de sensores sem fio; LoRa; Reconhecimento facial e sistemas de monitoramento; Wireless sensors networks; Facial recognition and monitoring systems; CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://repositorio.ufpb.br/jspui/handle/123456789/25192

During the last two decades, the application of technology in the integration of different areas of human daily life has become more common and intense, particularly due to the concept of IoT, or Internet of Things, which encompasses different approaches to such integration. One of these approaches are the Wireless Sensor Networks (WSNs), which make possible to monitor several devices simultaneously, or to perform readings at different (and physically separate) stages of a process or a service. Through this type of automation, you can also apply “intelligence” to environments, such as houses, roads, buildings, manufacturing sites and even cities or metropolitan regions. One of the great advantages of using WSNs in IoT applications is their low infrastructure demand, allowing both logistical and financial cost reductions. Camera Surveillance and Biometric Facial Authentication Systems are both examples of applications for smart environments which traditionally use wired technologies and/or short-range transmission media due to the high density of information characteristic in the images. In contrast to this, this work is based on the use of Wireless Sensor Networks with the goal of implementing a Monitoring and Facial Authentication Network, using the long-range LoRa technology as a means of communication among its devices. The proposed network is composed of four stages, in a modular architecture, allowing the scale of each stage to be adjusted to the needs of the environment without affecting the other stages. Through experimental tests and measurements, it was possible to confirm the feasibility of using WSNs for the transmission of static images, in particular, for Remote Facial Recognition applications.