Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/1333
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Modelling and interpretation of architecture from several images |
Author: | Dick, A. Torr, P. Cipolla, R. |
Citation: | International Journal of Computer Vision, 2004; 60(2):111-134 |
Publisher: | Kluwer Academic Publ |
Issue Date: | 2004 |
ISSN: | 0920-5691 1573-1405 |
Statement of Responsibility: | A. R. Dick, P. H. S. Torr and R. Cipolla |
Abstract: | This paper describes the automatic acquisition of three dimensional architectural models from short image sequences. The approach is Bayesian and model based. Bayesian methods necessitate the formulation of a prior distribution; however designing a generative model for buildings is a difficult task. In order to overcome this a building is described as a set of walls together with a ‘Lego’ kit of parameterised primitives, such as doors or windows. A prior on wall layout, and a prior on the parameters of each primitive can then be defined. Part of this prior is learnt from training data and part comes from expert architects. The validity of the prior is tested by generating example buildings using MCMC and verifying that plausible buildings are generated under varying conditions. The same MCMC machinery can also be used for optimising the structure recovery, this time generating a range of possible solutions from the posterior. The fact that a range of solutions can be presented allows the user to select the best when the structure recovery is ambiguous. |
Keywords: | architectural modelling structure and motion object recognition |
Description: | The original publication can be found at www.springerlink.com |
DOI: | 10.1023/B:VISI.0000029665.07652.61 |
Published version: | http://www.springerlink.com/content/u58m38v878732w52/ |
Appears in Collections: | Aurora harvest 2 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.