Bulletin des sciences géographiques de l'INCT
Volume 13, Numéro 1, Pages 40-45
2009-09-30
Automated 3d Modeling Of Urban Environments
Authors : Stamos Loannis .
Abstract
The photorealistic modeling of large scale scenes, such as urban structures, requires a fusion of range sensing technology and traditional digital photography. This paper summarizes the contributions of our group in that area. We present a system that integrates automatcd 3D-to-3D and 2D to-3D registration techniques. with multiview geometry for the photorealistic modeling of urban scenes. The 3D range scans are registered using our automated 3D-to-3D registration method that matches 3D features (linear or circular) in the ranoe images. A subset of the 2D photographs are then aligned with the 3D mode!using our automated 20- to-30 registration algorithm that matches linear features between the range scans and the photo graphs. Finally, the 20 photographs are used to generate a second 3D mode! of the scene that consists of a sparse 3D point cloud, produced by applying a multiview geometry (structure-from motion) algorithm directl y on a sequence of 2D photographs. A novel algorithm for automatically recovering the rot ation, scale. and translation that best aligns the dense and sparse models has been developed. This alignment is necessary to enable the photographs to be optimally texture mapped onto the dense mode!. Finall y, we present a segmentation and modeling algorithm for urban scenes. The contribution of this work ts that it merges the benefits of muhiview geometry with automated registration of 3D range l>Cans to produce photorealistic models with minimal human interaction. We present results from experiments in large-scale urban scenes.
Keywords
LIDAR, 3D Modeling, Urban Scenes.
Les articles similaires
سليمان أحمد عبدالكريم
.
ص 25-38.
El Azizi El Alaoui Anas
.
pages 73-86.
Abdi Nidal
.
pages 190-205.
Saouli Rim Amina
.
Benhassine Nassira
.
pages 717-728.
القصيباتي أ. د. ندى
.
ص 29-43.
