Unmanned aerial vehicles (UAVs) have become important tools in modern geospatial data acquisition, enabling rapid and high-resolution mapping of urban and rural environments. This paper investigates the efficiency of UAV-based photogrammetry and Python based workflows for extracting building footprints in areas with high buildings density. The primary objective is to assess how using Python based algorithms in data processing influences efficiency and precision in deliverables in comparison to human operators. Despite the maturity of UAV photogrammetric techniques, the extraction of vector features from derived datasets remains a bottleneck in urban mapping workflows. This research focuses on optimizing the feature extraction stage, particularly building footprint vectorization, by integrating Python-based automation into the workflow. The proposed approach streamlines the transition from processed photogrammetric datasets to structured geospatial outputs, reducing labor and costs. This study introduces an innovative approach by integrating photogrammetric data with automated Python-based feature extraction algorithms, providing a reproducible and scalable solution for urban and rural mapping. Results demonstrate that automated workflows can significantly reduce processing time while maintaining comparable accuracy to manual vectorization. The deliverables generated through this workflow, especially updated orthophoto plans, can be directly used by local authorities for a wide range of applications including urban planning, infrastructure management, cadastral updates and tax collection. The study highlights the importance of maintaining up-to-date geospatial data for informed decision-making and efficient governance.

UAV Photogrammetry, Building Extraction, Python, Urban Mapping, GIS

geodesy engineering

Presentation: poster