Back to Search
Start Over
Building large urban environments from unstructured point data
- Source :
- ICCV, ICCV, Nov 2011, Barcelona, Spain
- Publication Year :
- 2011
- Publisher :
- HAL CCSD, 2011.
-
Abstract
- International audience; We present a robust method for modeling cities from unstructured point data. Our algorithm provides a more complete description than existing approaches by reconstructing simultaneously buildings, trees and topologically complex grounds. Buildings are modeled by an original approach which guarantees a high generalization level while having semantized and compact representations. Geometric 3D-primitives such as planes, cylinders, spheres or cones describe regular roof sections, and are combined with mesh-patches that represent irregular roof components. The various urban components interact through a non-convex energy minimization problem in which they are propagated under arrangement constraints over a planimetric map. We experimentally validate the approach on complex urban structures and large urban scenes of millions of points.
- Subjects :
- Geographic information system
city modeling
Generalization
Computer science
Point cloud
[INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR]
Geometry
02 engineering and technology
Energy minimization
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
11. Sustainability
0202 electrical engineering, electronic engineering, information engineering
3D reconstruction
Markov random field
business.industry
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
020207 software engineering
Vegetation
Markov Random Field
[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]
urban scenes
Mesh generation
large scale
020201 artificial intelligence & image processing
Artificial intelligence
business
Algorithm
Lidar data
point cloud
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- ICCV, ICCV, Nov 2011, Barcelona, Spain
- Accession number :
- edsair.doi.dedup.....5dd91bedf952c35d0bb5fa7608eb4326