Banca de QUALIFICAÇÃO: CICERO MATIAS FERREIRA DO NASCIMENTO NETO
2025-05-13 08:31:07.834
Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa. DISCENTE: CICERO MATIAS FERREIRA DO NASCIMENTO NETO DATA: 26/05/2025 HORA: 11:00 TÍTULO: A Mobile Crowdsensing Approach to Vehicle Multi-Tracking in Smart Cities PALAVRAS-CHAVES: smart cities, vehicle multi-tracking, participatory sensing PÁGINAS: 15 GRANDE ÁREA: Ciências Exatas e da Terra ÁREA: Ciência da Computação RESUMO: In the context of Smart Cities, vehicle tracking plays a crucial role in enhancing public safety and in the identification and recovery of stolen or illegally taken vehicles. This paper proposes a low-cost multi-tracking system, integrating vehicle detection based on smartphones positioned inside vehicles or at roadside checkpoints. The approach consists of vehicle detection, tracking, and license plate extraction using YOLO, along with character recognition using PaddleOCR. To improve accuracy, the model differentiates between the Mercosul license plate standard and the discontinued Brazilian plate format, applying specific corrections and adjustments for each type. The proposed system is based on participatory sensing and can be utilized both by law enforcement officers and by citizens who wish to contribute to public safety, thus reducing the dependence on state infrastructure such as fixed cameras, which often involve high costs and may suffer from unavailability, particularly due to maintenance issues. Experimental results demonstrate an accuracy higher than 87\% in license plate detection, even in scenarios where both the tracked vehicle and the device hosting the camera are in motion. MEMBROS DA BANCA: Presidente - 407513 - FRANCISCO JOSE DA SILVA E SILVA Interno - 1930277 - DAVI VIANA DOS SANTOS Interno - 1178141 - MARIO ANTONIO MEIRELES TEIXEIRA Co-orientador - 1564359 - LUCIANO REIS COUTINHO
