Building Footprints Extraction from Oblique Imagery

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.