Automatic room detection and reconstruction in cluttered indoor environments with complex room layouts

• DOI: 10.1016/j.cag.2014.07.005
• Publication Date: 2014-08-01T23:15:45Z
• Authors: Claudio Mura; Oliver Mattausch; Alberto Jaspe Vil...; Enrico Gobbetti; Renato Pajarola
• Keywords: Robustness

We present a robust approach for reconstructing the main architectural structure of complex indoor environments given set cluttered 3D input range scans. Our method uses an efficient occlusion-aware process to extract planar patches as candidate walls, separating them from clutter and coping with missing data, automatically extracts individual rooms that compose environment by applying diffusion on space partitioning induced walls. This process, which has natural interpretation in terms heat propagation, makes our artifacts other imperfections occur typical scanned data interiors. For each room, algorithm reconstructs accurate polyhedral model methods statistics. demonstrate validity evaluating it both synthetic models real-world scans environments.