Enhancing pedestrian detection in urban areas using high-resolution satellite imagery and CNN Models

The MUSE (Measuring U-Space Social and Environmental Impact) project aims to develop an innovative framework and toolset for measuring and forecasting environmental and social Key Performance Indicators (KPIs) related to Urban Air Mobility (UAM), with a focus on assessing drone trajectory impacts, noise emissions, visual pollution, and population exposure in urban areas. Within the scope of the MUSE project, this study addresses the challenge of accurately detecting pedestrians in complex urban environments using high-resolution satellite imagery with the goal to later evaluate the visual pollution of drones in Urban area. We employ Pléiades Neo imagery at 15 cm resolution and historical orthophotos at 10 cm resolution to train and test CNN models, including U-Net and HRNet. Our results indicate detection rates of 70.41% in February and 80.86% in July, highlighting seasonal variability due to changes in pedestrian shadow characteristics. The pilot city is Madrid and discusses the feasibility of upscaling the approach to other cities and addresses challenges related to cloud cover and data availability.