期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2005
卷号：XXXVI-3/W24
出版社：Copernicus Publications
摘要：In this paper we propose an approach for building fac.ade interpretation ranging from uncalibrated images of an image sequence to the extraction of objects such as windows. The approach comprises several novel features, such as determi- nation of the fac. ade planes by robust least squares matching, learning of implicit shape models for objects, particularly windows, and a determination of the latter by means of a Markov Chain Monte Carlo (MCMC) process employing an abstraction hierarchy. Results for the fully automatic approach show its potential and problems
关键词：Fac.ade Interpretation; Implicit Shape Models; Markov Chain Monte Carlo; Abstraction Hierarchy; 3D ; Reconstruction
