Detecção Inteligente de Vagas de Estacionamento Baseado em Climas Usando Imagens Aéreas e Aprendizado Profundo

Lucas D. T. Oliveira, Milena Pinto, Gabriel Araujo, João T Dias, Diego Haddad

DOI: 10.14209/SBRT.2020.1570658218

Evento: XXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2020)

Keywords: Detecção de Vagas Identificação de Clima Aprendizado Profundo Imagens Aéreas

Abstract

Automatic detection of parking lot spaces is essential for the management of large buildings. Knowing the availability of vacancies helps to reduce queues and harmful gas emissions, improve scalability, and save time to find parking space. However, vehicle detection in aerial images presents many challenges, such as the reduced scale of the images and the influence of the variation of luminosity due to the climate. This work proposes an intelligent system capable of quickly detecting parking spaces based on weather. The results revealed good accuracy in the classification and effectiveness when compared with similar methods in the literature.

Download