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

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.

@InProceedings{PGGGA16,
  author       = {Pintore, G. and Garro, V. and Ganovelli, F. and Gobbetti, E. and Agus, M.},
  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},
  keywords     = {mobile devices, fast maps generation, indoor environments},
  doi          = {10.1109/WACV.2016.7477631},
  url          = {https://publications.crs4.it/pubdocs/2016/PGGGA16},
}