The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 333–338, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-333-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 333–338, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-333-2020

  12 Aug 2020

12 Aug 2020

SEMANTIC CLASSIFICATION OF SANDSTONE LANDSCAPE POINT CLOUD BASED ON NEIGHBOURHOOD FEATURES

M. Tomková, J. Lysák, and M. Potůčková M. Tomková et al.
  • Department of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, Prague 2, Czech Republic

Keywords: Airborne Laser Scanning, Feature Extraction, Classification, Point Cloud, Sandstone Rocks

Abstract. The technology of airborne laser scanning enables fast and accurate gathering spatial data containing also echoes from the terrain below the vegetation canopy that is beneficial for topographic mapping of wooded sandstone landscapes in Czechia, Poland, and Germany. The challengeable task is to determine the ground points in the point cloud because commonly used filtration methods do not successfully distinguish between vegetation and rock pillars and faces. In this paper, we replace filtration with classification approach using the features derived from characteristics of points within a neighbourhood of optimized sizes, such as eigenvalue-based features and echo ratio. Random Forest classifier is trained and tested on the manually labelled dataset with a density of almost 650 points/m2 from the Adršpach-Teplice Rocks. The overall accuracy reaches 87% but recall and precision of non-ground points are unsatisfactory. Misclassified non-ground points are located also within trees, thus we do not consider the result as suitable for DTM processing without further processing.