Volume XLII-2/W6
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W6, 145-151, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W6-145-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W6, 145-151, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W6-145-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.

  23 Aug 2017

23 Aug 2017

CONCEPT FOR CLASSIFYING FACADE ELEMENTS BASED ON MATERIAL, GEOMETRY AND THERMAL RADIATION USING MULTIMODAL UAV REMOTE SENSING

R. Ilehag, A. Schenk, and S. Hinz R. Ilehag et al.
  • Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology (KIT), Englerstr. 7, 76131 Karlsruhe, Germany

Keywords: UAV, Hyperspectral, Thermal imaging, Multimodal, Building facades

Abstract. This paper presents a concept for classification of facade elements, based on the material and the geometry of the elements in addition to the thermal radiation of the facade with the usage of a multimodal Unmanned Aerial Vehicle (UAV) system. Once the concept is finalized and functional, the workflow can be used for energy demand estimations for buildings by exploiting existing methods for estimation of heat transfer coefficient and the transmitted heat loss. The multimodal system consists of a thermal, a hyperspectral and an optical sensor, which can be operational with a UAV. While dealing with sensors that operate in different spectra and have different technical specifications, such as the radiometric and the geometric resolution, the challenges that are faced are presented. Addressed are the different approaches of data fusion, such as image registration, generation of 3D models by performing image matching and the means for classification based on either the geometry of the object or the pixel values. As a first step towards realizing the concept, the result from a geometric calibration with a designed multimodal calibration pattern is presented.