Building reconstruction from optical and range images
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 380-386
- https://doi.org/10.1109/cvpr.1997.609353
Abstract
A technique is introduced for extracting and reconstructing a wide class of building types from a registered range image and optical image. An attentional focus stage, followed by model indexing, allows top-down robust surface fitting to reconstruct the 3D nature of the buildings in the data. Because of the effectiveness of model selection, top-down processing of noisy range data still succeeds and the algorithm is capable of detecting and reconstructing several different building roof classes, including flat single level, flat multi-leveled, peaked, and curved rooftops. The algorithm is applicable to range data that may have been collected from several different range sensor types. We demonstrate reconstructions of different buildings classes in the presence of large amounts of noise. Our results underline the usefulness of range data when processed in the context of a focus-of-attention area derived from the monocular optical image.Keywords
This publication has 6 references indexed in Scilit:
- Task driven perceptual organization for extraction of rooftop polygonsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Site model acquisition and extension from aerial imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Data fusion for the detection and reconstruction of buildingsPublished by Springer Nature ,1995
- Voronoi diagrams—a survey of a fundamental geometric data structureACM Computing Surveys, 1991
- Toward Automatic Cartographic Feature ExtractionPublished by Springer Nature ,1990
- Detecting buildings in aerial imagesComputer Vision, Graphics, and Image Processing, 1988