Paper Info
Title
3D Reconstruction of Interior Wall Surfaces under Occlusion and Clutter
Abstract
Laser scanners are often used to create 3D models of buildings for civil engineering applications. The current manual process is time-consuming and error-prone. This paper presents a method for using laser scanner data to model predominantly planar surfaces, such as walls, floors, and ceilings, despite the presence of significant amounts of clutter and occlusion, which occur frequently in natural indoor environments. Our goal is to recover the surface shape, detect and model any openings, and fill in the occluded regions. Our method identifies candidate surfaces for modeling, labels occluded surface regions, detects openings in each surface using supervised learning, and reconstructs the surface in the occluded regions. We evaluate the method on a large, highly cluttered data set of a building consisting of forty separate rooms.
Year
DOI
Venue
2011
10.1109/3DIMPVT.2011.42
3DIMPVT
Keywords
Field
DocType
labels occluded surface region,occluded region,laser scanners,occlusion reasoning,civil engineering computing,learning (artificial intelligence),planar surfaces,surface shape,candidate surface,3d building models,point cloud,laser scanner data,optical scanners,laser scanner,current manual process,interior wall surfaces,image reconstruction,planar surface,3d model,civil engineering application,opening detection,solid modelling,civil engineering applications,clutter,3d interior wall surface reconstruction,occlusion,cluttered data,learning artificial intelligence,data models,3d reconstruction,labeling,pixel,supervised learning,data model,three dimensional,surface reconstruction
Iterative reconstruction,Surface reconstruction,Computer vision,Laser scanning,Clutter,Computer science,Supervised learning,Pixel,Artificial intelligence,Point cloud,3D reconstruction
Conference
ISBN
Citations 
PageRank 
978-0-7695-4369-7
15
0.92
References 
Authors
13
2
Name
Order
Citations
PageRank
Antonio Adan1503.75
Daniel F. Huber269946.34