ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-4-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-4-2022, 251–258, 2022
https://doi.org/10.5194/isprs-annals-V-4-2022-251-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-4-2022, 251–258, 2022
https://doi.org/10.5194/isprs-annals-V-4-2022-251-2022
 
18 May 2022
18 May 2022

ASSESSING GEO-TYPICAL TECHNIQUES FOR MODELING BUILDINGS USING THERMAL SIMULATIONS

D. Bulatov1, B. Kottler1, E. Strauss1, G. Häufel1, M. May2, P. Helmholz3, and F. Mancini2 D. Bulatov et al.
  • 1Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Gutleuthausstrasse 1, 76275 Ettlingen, Germany
  • 2School of Design and the Built Environment, Curtin University, Australia
  • 3School of Earth and Planetary Sciences, Faculty of Science and Engineering, Curtin University, Australia

Keywords: Buildings, Digital Twin, Landcover Map, Modeling, Thermal Simulation, Urban

Abstract. Building modeling from remote sensing data is essential for creating accurate 3D and 4D digital twins, especially for temperature modeling. In order to represent buildings as gap-free, visually appealing, and rich in details models, geo-typical prototypes should be represented in the scene. The sensor data and freely available OSM data are supposed to provide guidelines for best-possible matching. In this paper, the default similarity function based on intersection over union is extended by terms reflecting the similarity of elevation values, orientation towards the road, and trees in the vicinity. The goodness of fit has been evaluated by architecture experts as well as thermal simulations with a thermal image as ground truth and error measures based on mean average error, root mean square and mutual information. It could be concluded that while intersection over union measure still seems to be most preferred by architects, slightly better thermal simulation results are yielded by taking into account all similarity functions.