thumbnail

Mobile reconstruction and exploration of indoor structures exploiting omnidirectional images

Giovanni Pintore, Fabio Ganovelli, Enrico Gobbetti, and Roberto Scopigno

December 2016

Abstract

We summarize our recent advances in acquisition, reconstruction and exploration of indoor environments with the aid of mobile devices. Our methods enable casual users to quickly capture and recover multi-room structures coupled with their visual appearance, starting from panorama images generated with the built-in capabilities of modern mobile devices, as well as emerging low-cost 360^CIRC cameras. After introducing the reconstruction algorithms at the base of our approach, we show how to build applications able to generate 3D floor plans scaled to their real-world metric dimensions and capable to manage scene not necessary limited by Manhattan World assumptions. Then, exploiting the resulting structural and visual model, we propose a client-server interactive exploration system implementing a low-DOF navigation interface, specifically developed for touch interaction on smartphones and tablets.

Reference and download information

Giovanni Pintore, Fabio Ganovelli, Enrico Gobbetti, and Roberto Scopigno. Mobile reconstruction and exploration of indoor structures exploiting omnidirectional images. In Proc. SIGGRAPH Asia Mobile Graphics and Interactive Applications. Pages 1:1-1:4, December 2016. DOI: 10.1145/2999508.2999526.

Related multimedia productions

Bibtex citation record

@InProceedings{Pintore:2016:MRE,
    author = {Giovanni Pintore and Fabio Ganovelli and Enrico Gobbetti and Roberto Scopigno},
    title = {Mobile reconstruction and exploration of indoor structures exploiting omnidirectional images},
    booktitle = {Proc. SIGGRAPH Asia Mobile Graphics and Interactive Applications},
    pages = {1:1--1:4},
    month = {December},
    year = {2016},
    isbn = {978-1-4503-4551-4/16/12},
    abstract = { We summarize our recent advances in acquisition, reconstruction and exploration of indoor environments with the aid of mobile devices. Our methods enable casual users to quickly capture and recover multi-room structures coupled with their visual appearance, starting from panorama images generated with the built-in capabilities of modern mobile devices, as well as emerging low-cost 360$^\circ$ cameras. After introducing the reconstruction algorithms at the base of our approach, we show how to build applications able to generate 3D floor plans scaled to their real-world metric dimensions and capable to manage scene not necessary limited by \emph{Manhattan World} assumptions. Then, exploiting the resulting structural and visual model, we propose a client-server interactive exploration system implementing a low-DOF navigation interface, specifically developed for touch interaction on smartphones and tablets. },
    doi = {10.1145/2999508.2999526},
    isbn = {978-1-4503-4551-4/16/12},
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Pintore:2016:MRE'},
}