The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 283–290, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-283-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 283–290, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-283-2022
 
30 May 2022
30 May 2022

DEEP LEARNING-BASED ROAD SEGMENTATION OF 3D POINT CLOUDS FOR ASSISTING ROAD ALIGNMENT PARAMETERIZATION

M. Soilán, H. Tardy, and D. González-Aguilera M. Soilán et al.
  • Department of Cartographic and Terrain Engineering, University of Salamanca, Calle Hornos Caleros 50, 05003 Ávila, Spain

Keywords: Mobile Mapping System, 3D point cloud processing, Deep Learning, Point Transformer, Road alignment, BIM

Abstract. The need for transportation infrastructure digitalization is becoming more important, and efficient data collection and processing workflows have to be established and pose a great research challenge. This paper presents a fully automated method for the geometric parametrization of the road alignment from 3D point clouds acquired with a low-cost mobile mapping system. It exploits the Point Transformer Deep Learning architecture in order to segment the 3D point cloud in four different classes, which include road markings. Those markings are then used as a reference to extract the alignment trajectory path, classify its geometries (straight lines, circular arcs, and clothoids) and then parametrize it, extracting data to easily generate alignment data that may follow the standard schema of the Industry Foundation Classes (IFC). Both the deep learning architecture and the geometry parametrization process show promising results to develop automatic workflows that extract precise as-built data of the infrastructure from 3D point clouds.