Towards Sustainable Cities: Utilizing Computer Vision and AI for Efficient Public Lighting and Energy Management

This study showcases the optimization of public lighting systems using computer vision with an emphasis on the YOLO algorithm for pedestrian detection, aiming to reduce energy expenses. In a time when the demand for electricity is escalating due to factors like taxes and urban expansion, it is imperative to explore strategies to cut costs. One pivotal area is public lighting management. Presently, governments are transitioning from sodium vapor lighting to LED lamps, which already contributes to decreasing consumption. In this scenario, computer vision systems, particularly using YOLO, have the potential to further reduce consumption by adjusting the power of LED lamps based on pedestrian traffic. Additionally, this paper employs fuzzy logic to calculate lamp power based on detected pedestrians and ambient lighting, ensuring compliance with the NBR 5101:2018 standard. Tests with public surveillance camera images and simulations validated the proposal. Upon implementing this project in practice, a 45% reduction in public lighting consumption was observed compared to conventional LED lighting.