Roof model recommendation for complex buildings based on combination rules and symmetry features in footprints

• Verfasst von: Hu, Xuke [VerfasserIn]
• Verfasst von: Fan, Hongchao [VerfasserIn]
• Verfasst von: Noskov, Alexey [VerfasserIn]
• Titel: Roof model recommendation for complex buildings based on combination rules and symmetry features in footprints
• Verf.angabe: Xuke Hu, Hongchao Fan, Alexey Noskov
• Jahr: 2018
• Umfang: 25 S.
• Fussnoten: Published online: 12 Sep 2017 ; Gesehen am 10.10.2019
• Titel Quelle: Enthalten in: International journal of digital earth
• Ort Quelle: London [u.a.] : Taylor & Francis, 2008
• Jahr Quelle: 2018
• Band/Heft Quelle: 11(2018), 10, Seite 1039-1063
• ISSN Quelle: 1753-8955
• DOI: doi:10.1080/17538947.2017.1373867
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: combination rules
• Sach-SW: footprint decomposition
• Sach-SW: intrinsic roof reconstruction
• Sach-SW: OpenStreetMap
• Sach-SW: Roof recommendation
• Sach-SW: symmetry detection
• Sach-SW: symmetry rule
• K10plus-PPN: 1678628719

Abstract

Currently, very few roof shape information for complex buildings is available on OSM. Moreover, additional data requirements (e.g. 3D point clouds) limit the applicability of many roof reconstruction approaches. To mitigate this issue, we propose an approach to roof shape recommendations for complex buildings by exploring the inherited characteristics of building footprints: the disclosure of rectangles combinations in a partition of footprints and the symmetrical features of footprints. First, it decomposes a complex footprint into rectangles by using an advanced minimal non-overlapping cover algorithm. Second, a graph-based symmetry detection algorithm is proposed to identify all the symmetrical sub-clusters in partitions. Then, a set of selection rules are defined to rank partitions, and the best ones are chosen for roof shape recommendation. Finally, a set of combination rules and a symmetry rule are defined. It enables to evaluate the probability of a footprint being a certain combination of roof shapes. Experimental results show the growth of the probability of correctly recommending roof shapes for single rectangles and buildings from a prior probability of 17-45% and from a prior probability of 0.29-14.3%, removing 60% and 93% of the incorrect roof shape options, respectively.