Abstract
In this paper we present a system for the reconstruction of 3 D models of architectural scenes from single or multiple uncalibrated images. The partial 3 D model of a building is recovered from a sing le image using geometric constraints such as parallelism and orthogonality, which are likely to be found in most architectural scenes. The approximate corner positions of a building are selected interactively by a user and then further refined automatically using Hough transform. T he relative depths of the corner points are calculated according to the perspective projection mod el. Partial 3 D models recovered from different viewpoints are registered to a common coordinate system for integration. T he integrated 3 D mod el is then fitted with piecewise planar surfaces to generate a more geometrically consistent mod el. T he acquired images are finally mapped onto the surface of the reconstructed 3 D mod el to create a photo-realistic mod el. A working system which allows a user to interactively build a 3 D mod el of an architectural scene from sing le or multiple images has been proposed and implemented . Copyright © 2005 by MVA Conference Committee.
Cite
CITATION STYLE
Lin, H. Y., Chen, S. L., & Lin, J. H. (2005). Architectural reconstruction from single or multiple uncalibrated images. In Proceedings of the 9th IAPR Conference on Machine Vision Applications, MVA 2005 (pp. 241–244). Machine Vision Applications, MVA. https://doi.org/10.5565/rev/elcvia.119
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.