thumbnail

Omnidirectional image capture on mobile devices for fast automatic generation of 2.5D indoor maps

Giovanni Pintore, Valeria Garro, Fabio Ganovelli, Enrico Gobbetti, and Marco Agus

February 2016

Abstract

We introduce a light-weight automatic method to quickly capture and recover 2.5D multi-room indoor environments scaled to real-world metric dimensions. To minimize the user effort required, we capture and analyze a single omnidirectional image per room using widely available mobile devices. Through a simple tracking of the user movements between rooms, we iterate the process to map and reconstruct entire floor plans. In order to infer 3D clues with a minimal processing and without relying on the presence of texture or detail, we define a specialized spatial transform based on catadioptric theory to highlight the room's structure in a virtual projection. From this information, we define a parametric model of each room to formalize our problem as a global optimization solved by Levenberg-Marquardt iterations. The effectiveness of the method is demonstrated on several challenging real-world multi-room indoor scenes.

Reference and download information

Giovanni Pintore, Valeria Garro, Fabio Ganovelli, Enrico Gobbetti, and Marco Agus. Omnidirectional image capture on mobile devices for fast automatic generation of 2.5D indoor maps. In Proc. IEEE Winter Conference on Applications of Computer Vision (WACV). Pages 1-9, February 2016. http://dx.doi.org/10.1109/WACV.2016.7477631.

Related multimedia productions

Bibtex citation record

@InProceedings{Pintore:2016:OIC,
    author = {Giovanni Pintore and Valeria Garro and Fabio Ganovelli and Enrico Gobbetti and Marco Agus},
    title = {Omnidirectional image capture on mobile devices for fast automatic generation of {2.5D} indoor maps},
    booktitle = {Proc. IEEE Winter Conference on Applications of Computer Vision (WACV)},
    pages = {1--9},
    month = {February},
    year = {2016},
    abstract = { We introduce a light-weight automatic method to quickly capture and recover 2.5D multi-room indoor environments scaled to real-world metric dimensions. To minimize the user effort required, we capture and analyze a single omnidirectional image per room using widely available mobile devices. Through a simple tracking of the user movements between rooms, we iterate the process to map and reconstruct entire floor plans. In order to infer 3D clues with a minimal processing and without relying on the presence of texture or detail, we define a specialized spatial transform based on catadioptric theory to highlight the room's structure in a virtual projection. From this information, we define a parametric model of each room to formalize our problem as a global optimization solved by Levenberg-Marquardt iterations. The effectiveness of the method is demonstrated on several challenging real-world multi-room indoor scenes. },
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Pintore:2016:OIC'},
}