The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 179–184, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-179-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 179–184, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-179-2021

  28 Jun 2021

28 Jun 2021

AUTOMATIC MODELLING OF 3D TREES USING AERIAL LIDAR POINT CLOUD DATA AND DEEP LEARNING

R. G. Kippers1, L. Moth2, and S. J. Oude Elberink3 R. G. Kippers et al.
  • 1Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, The Netherlands
  • 2Deltas, Coasts and Rivers, Witteveen+Bos
  • 3ITC, Faculty of Geo-Information Science and Earth Observation, University of Twente, The Netherlands

Keywords: AHN, Aerial Laser Scanning, Point Cloud, PointNet, Deep Learning, CityJSON

Abstract. 3D tree objects can be used in various applications, like estimation of physiological equivalent temperature (PET). During this project, a method is designed to extract 3D tree objects from a country-wide point cloud. To apply this method on large scale, the algorithm needs to be efficient. Extraction of trees is done in two steps: point-wise classification using the PointNet deep learning network, and Watershed segmentation to split points into individual trees. After that, 3D tree models are made. The method is evaluated on 3 areas, a park, city center and housing block in the city of Deventer, the Netherlands. This resulted into an average accuracy of 92% and a F1-score of 0.96.