Automating the inventory of the navigable space for pedestrians on historical sites: Towards accurate path planning

A novel automated method achieves high accuracy in mapping and characterizing pedestrian navigable spaces in historic urban areas, with paving material segmentation reaching 99.08% and urban element segmentation at 88.2%. The approach leverages mobile laser scanning point clouds combined with artificial intelligence to identify sidewalks, vectorize data into highly accurate shapefiles, and generate pedestrian routes—requiring minimal manual refinement (1.3%). Tested in Sabbioneta, Italy, this method overcomes limitations of traditional techniques designed for modern urban layouts, offering a scalable solution for path planning in UNESCO World Heritage Sites.

Treccani, D., Fernández, A., Díaz-Vilariño, L., & Adami, A. (2023). Automating the inventory of the navigable space for pedestrians on historical sites: Towards accurate path planning. International Journal of Applied Earth Observation and Geoinformation, 122, 103400. https://doi.org/10.1016/j.jag.2023.103400