Ricostruzione di una scena urbana 3D utilizzando VisualSfM.
DOI:
https://doi.org/10.6092/issn.1828-5961/3873Parole chiave:
Modellazione da immagini, Ricostruzione 3D, Scena urbana, Image-based modeling, 3D reconstruction, Urban SceneAbstract
Le tecniche di computer vision oggi danno la possibilità di costruire in maniera rapida e automatica modelli 3D dettagliati a partire da dataset fotografici. La comunità accademica ha visto una crescente attenzione alla ricostruzione 3D a scala urbana. Tra i vari strumenti oggi a disposizione spicca VisualSfM sviluppato dall’università di Washingthon e Google. Si tratta di una Interfaccia grafica open source strutturata in algoritmi dedicati alla tecnica di Structure from Motion (SfM). VisualSfM utilizza un estrattore di features chiamato SIFTGPU e un algoritmo di Bundle Adjustment Multicore. Inoltre è possibile ottenere una nuvola di punti densa utilizzando gli algoritmi CMVS/PMVS2. La finalità di questo studio è di verificare l’accuratezza metrica delle ricostruzioni attraverso l’utilizzo integrato di VisualSfM e CMVS/PMVS2. L’approccio quindi è stato testato su diversi dataset di una certa entità strutturati da collezioni fotografiche ragionate.
Riferimenti bibliografici
Agarwal, Saran, Furukawa, Yasutaka, Snavely, Noah, Curless, Brian, Seitz, Steve, Szeliski, Richard, (2010), Reconstructing Rome, in Computer, 43 (6), pp. 40-47.
Bandiera, Adriana, Beraldin, Jean Angelo, Gaiani, Marco (2011), Nascita ed utilizzo delle tecniche digitali di 3D imaging, modellazione e visualizzazione per l’architettura e i beni culturali, in Ikhnos, Siracusa, Lombardi editore, pp. 81-134.
Dellepiane, Matteo, Dell’Unto, Nicolò, Callieri, Marco, Lindgren, Stefan, Scopigno, Roberto (2013), Archaeological excavation monitoring using dense stereo matching techniques, in JOURNAL OF CULTURAL HERITAGE, 14(3), pp. 201-210.
Furukawa, Yasutaka, Ponce, Jean, (2010), Accurate, Dense, and Robust Multi-View Stereopsis, in IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), vol. 32, n. 8, pp. 1362-1376.
Furukawa, Yasutaka, Curless, Brian, Seitz, Steve, Szeliski, Richard, (2010), Towards Internet-scale Multi-view Stereo, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
Galizia, Mariateresa, (2012), Il disegno delle torri medievali di Enna nel paesaggio urbano tra passato e presente, Giuseppe Maimone Editore, Catania.
Galizia, Mariateresa, Santagati, Cettina, (2012), Low-cost image based modeling techniques for archaeological heritage digitalization: more than just a good tool for 3D visualization?, Proceedings of ARQUEOLÓGICA 2.0, Seville, Spain.
Kersten, Thomas, Stallmann, Dirk, (2012), Automatic texture mapping of architectural and archaeological 3d models, in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXIX-B5, pp. 273-278.
Kersten, Thomas, Lindstaedt, Maren, (2012), Image-Based Low- Cost Systems For Automatic 3d Recording And Modelling Of Archaeological Finds And Objects, in EuroMed 2012, Progress In Cultural Heritage Preservation, LNCS 7616, Springer-Verlag Berlin Heidelberg, pp 1-10.
Lo Brutto, Mauro, Meli, Paola, (2012), Computer vision tools for 3d modelling in archaeology, in International Journal of Heritage in the Digital Era, Volume 1, Supplement, pp. 1-6.
Nguyen, Hoai-Minh, Wunsche, Burkhard, Delmas, Patrice, Lutteroth, Christof, (2012), 3D Models from the Black Box: Investigating the Current State of Image-Based Modeling, in Proceedings of the 20th International Conference on Computer Graphics, Visualization and Computer Vision, WSCG, Pilsen, Czech Republic.
Manferdini, Anna Maria, Galassi, Mark, (2013), Assessments for 3d reconstructions of cultural heritage using digital technologies, in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-5/W1, pp. 167-174.
Pierrot-Deseilligny, Marc, De Luca, Livio, Remondino, Fabio, (2011), Automated image-based procedures for accurate artifacts 3D modeling and orthoimage generation, Proc. CIPA.
Remondino, Fabio, Del Pizzo, Silvio, Kersten, Thomas, Troisi, Salvatore, (2012), Low-Cost and Open-Source Solutions for Automated Image Orientation–A Critical Overview in EuroMed 2012, Progress In Cultural Heritage Preservation, LNCS 7616, Springer-Verlag Berlin Heidelberg, pp. 40-54.
Restuccia, Franca, Galizia, Mariateresa, Santagati, Cettina, (2012), Urban and Architectural Design of the “Piazza del Governo” in Enna, Journal of Literature and Art Studies, vol 2 (6), pp. 606-621.
Rodriguez-Navarro, Pablo (2012), Automated Digital Photogrammetry versus the systems based on active 3D sensors. La Fotogrametría Digital Automatizada frente a los sistemas basados en sensores 3D activos, in EGA, 17(20), pp. 100-111
Santagati, Cettina, Inzerillo, Laura, (in press), 123D Catch: efficiency, accuracy, constraints and limitations in architectural heritage field, in International Journal of Heritage in Digital Era.
Snavely, Noah, Seitz, Steve, Szeliski, Richard, (2006), Photo tourism: Exploring photo collections in 3D, in ACM Transactions on Graphics (SIGGRAPH Proceedings), 25(3), pp. 835-846.
Snavely, Noah, Seitz, Steve, Szeliski, Richard, (2008), Modeling the World from Internet Photo Collections, in International Journal of Computer Vision, 80(2), pp. 189-
Vergauwen, Maarten, Van Gool, Luc, (2006), Web-based 3D Reconstruction Service, in Machine Vision and Applications, vol. 17, pp. 411–426.
Vu, Hoang, Keriven, Renaud, Labatut, Patrick, Pons, Jean-Philippe, (2009), Towards high-resolution large-scale multi-view stereo, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Wu, Changchang, Agarwal, Sameer, Curless, Brian, Seitz, Steve, (2011), Multicore Bundle Adjustment, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
Wu, Changchang, (2012), SiftGPU: A GPU Implementation of Scale Invariant Feature Transform (SIFT) http://www.cs.unc.edu/~ccwu/siftgpu/ 10/04/2012.
Wu, Changchang, (2011), VisualSFM:A Visual Structure from Motion System http://homescs.washington.edu/~ccwu/vsfm/
Downloads
Pubblicato
Come citare
Fascicolo
Sezione
Licenza
Copyright (c) 2013 Laura Inzerillo, Cettina Santagati, Francesco Di Paola
Questa rivista è distribuita con licenza Creative Commons Attribuzione - Non commerciale 3.0 Unported.
