The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 321–326, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-321-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 321–326, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-321-2022
 
01 Jun 2022
01 Jun 2022

A DEEP LEARNING APPROACH FOR THE RECOGNITION OF URBAN GROUND PAVEMENTS IN HISTORICAL SITES

D. Treccani1,2, J. Balado1,3, A. Fernández1, A. Adami2, and L. Díaz-Vilariño1 D. Treccani et al.
  • 1Universidade de Vigo, CINTECX, GeoTECH group, 36310 Vigo, Spain
  • 2He.Su.Tech. group, MantovaLab, Dept. of Architecture Built environment and Construction engineering (ABC), Politecnico di Milano, 46100 Mantua, Italy
  • 3LIAAD, INESC TEC, Campus Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal

Keywords: Deep Learning, semantic segmentation, urban paving, cultural heritage, material classification

Abstract. Urban management is a topic of great interest for local administrators, particularly because it is strongly connected to smart city issues and can have a great impact on making cities more sustainable. In particular, thinking about the management of the physical accessibility of cities, the possibility of automating data collection in urban areas is of great interest. Focusing then on historical centres and urban areas of cities and historical sites, it can be noted that their ground surfaces are generally characterised by the use of a multitude of different pavements. To strengthen the management of such urban areas, a comprehensive mapping of the different pavements can be very useful. In this paper, the survey of a historical city (Sabbioneta, in northern Italy) carried out with a Mobile Mapping System (MMS) was used as a starting point. The approach here presented exploit Deep Learning (DL) to classify the different pavings. Firstly, the points belonging to the ground surfaces of the point cloud were selected and the point cloud was rasterised. Then the raster images were used to perform a material classification using the Deep Learning approach, implementing U-Net coupled with ResNet 18. Five different classes of materials were identified, namely sampietrini, bricks, cobblestone, stone, asphalt. The average accuracy of the result is 94%.