Detecção de Clientes Clandestinos Urbanos e Rurais Através de Ferramenta Computacional Baseada em Dados Georreferenciados Por Meio de Imagens de Satélite

Abstract

This work presents a Python tool capable of identifying buildings that are irregularly connected to an electric distribution system. The methodology employed in the proposed algorithm utilizes images from the Open Buildings database, comparing their geographical locations with the assets of an existing distribution system. Additionally, a satellite image capture algorithm is used to calculate the Normalized Difference Water Index (NDWI) and Normalized Difference Vegetation Index (NDVI) indices, which are employed in forming auxiliary layers to aid decision-making in selecting potential inspection targets. The results obtained proved satisfactory for the cases applied in three distinct locations, demonstrating potential for application and the possibility of conducting tests in other areas.