Volume II-3/W3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-3/W3, 61-66, 2013
https://doi.org/10.5194/isprsannals-II-3-W3-61-2013
© Author(s) 2013. This work is distributed under
the Creative Commons Attribution 3.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-3/W3, 61-66, 2013
https://doi.org/10.5194/isprsannals-II-3-W3-61-2013
© Author(s) 2013. This work is distributed under
the Creative Commons Attribution 3.0 License.

  08 Oct 2013

08 Oct 2013

Building Footprints Extraction from Oblique Imagery

F. Nex1, E. Rupnik2, and F. Remondino1 F. Nex et al.
  • 13D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, Italy
  • 2GEO Department, Vienna University of Technology, Austria

Keywords: Matching, Automation, Oblique images, Extraction, Building

Abstract. Nowadays, multi-camera aerial platforms combining nadir and oblique cameras are experiencing a revival and several companies have proposed new image acquisition systems. Due to their various advantages, oblique imagery have found their place in numerous companies and civil applications. However, the automatic processing of such image blocks still remains a topic of research. Camera configuration indeed poses a challenge on the traditional photogrammetric pipeline used in commercial software but, on the other hand, gives the opportunity to exploit the additional information provided by the oblique views and allows a more reliable feature extraction. In particular, the information that can be provided in correspondence of building façades can open new possibilities for the building detection and footprint extraction. In this paper, a methodology for the automated extraction of building footprints from oblique imagery is presented. The extraction is performed using dense point clouds generated using an image matching algorithm. The developed methodology and the achieved results are described in detail showing the advantages and opportunities offered by oblique aerial systems for cartographic and mapping purposes.