Nowadays, it is essential to find new strategies, able to perform the first step of the scan-to-BIM process, by retrieving the geometrical information contained in point clouds that are so easily collected through laser scanners and range cameras. This paper presents a new algorithm for the automatic extraction of the layout and the height of a small indoor environment from its point cloud. In particular, the algorithm was tested on a point cloud of 600000 vertices, selected from the dataset of the ISPRS benchmark on indoor modelling. The preliminary results are encouraging: the 3D shape (layout and height) of the investigated room is effectively reconstructed.
An original algorithm for bim generation from indoor survey point clouds / Capocchiano, F.; Ravanelli, R.. - In: INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES. - ISSN 1682-1750. - 42:2/W13(2019), pp. 769-776. (Intervento presentato al convegno 4th ISPRS Geospatial Week 2019 tenutosi a Enschede, The Netherlands) [10.5194/isprs-archives-XLII-2-W13-769-2019].
An original algorithm for bim generation from indoor survey point clouds
Capocchiano F.Primo
;Ravanelli R.
Ultimo
2019
Abstract
Nowadays, it is essential to find new strategies, able to perform the first step of the scan-to-BIM process, by retrieving the geometrical information contained in point clouds that are so easily collected through laser scanners and range cameras. This paper presents a new algorithm for the automatic extraction of the layout and the height of a small indoor environment from its point cloud. In particular, the algorithm was tested on a point cloud of 600000 vertices, selected from the dataset of the ISPRS benchmark on indoor modelling. The preliminary results are encouraging: the 3D shape (layout and height) of the investigated room is effectively reconstructed.| File | Dimensione | Formato | |
|---|---|---|---|
|
Capocchiano_An-original-algorithm_2019.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
374.54 kB
Formato
Adobe PDF
|
374.54 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
