ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume IV-4/W8
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4/W8, 139–146, 2019
https://doi.org/10.5194/isprs-annals-IV-4-W8-139-2019
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4/W8, 139–146, 2019
https://doi.org/10.5194/isprs-annals-IV-4-W8-139-2019

  23 Sep 2019

23 Sep 2019

AN IMPROVED AUTOMATIC POINTWISE SEMANTIC SEGMENTATION OF A 3D URBAN SCENE FROM MOBILE TERRESTRIAL AND AIRBORNE LIDAR POINT CLOUDS: A MACHINE LEARNING APPROACH

X.-F. Xing1, M. A. Mostafavi1, G. Edwards1, and N. Sabo2 X.-F. Xing et al.
  • 1Dept. of Geomatics, Laval University, Québec, Canada
  • 2Canada Centre for Mapping and Earth Observation, Natural Resources Canada, Canada

Keywords: Semantic segmentation, 3D urban scene, 3D LiDAR point clouds

Abstract. Automatic semantic segmentation of point clouds observed in a 3D complex urban scene is a challenging issue. Semantic segmentation of urban scenes based on machine learning algorithm requires appropriate features to distinguish objects from mobile terrestrial and airborne LiDAR point clouds in point level. In this paper, we propose a pointwise semantic segmentation method based on our proposed features derived from Difference of Normal and the features “directional height above” that compare height difference between a given point and neighbors in eight directions in addition to the features based on normal estimation. Random forest classifier is chosen to classify points in mobile terrestrial and airborne LiDAR point clouds. The results obtained from our experiments show that the proposed features are effective for semantic segmentation of mobile terrestrial and airborne LiDAR point clouds, especially for vegetation, building and ground classes in an airborne LiDAR point clouds in urban areas.