标题：The Application of content-based indexing and retrieval of digital pictures and range images to the 3D virtual reconstruction of complex sites and architectures
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：2007
卷号：XXXVI-5/W47
出版社：Copernicus Publications
摘要：The modelling of complex objects and sites involve the acquisition of a large number of texture maps and range images; each one of them representing a particular viewing angle. These views must be combined and registered in order to create an accurate model of the original. The complexity of the resultant models, and consequently the number of views required, has increased tremendously over the past decade. Furthermore many major projects involve multinational and multilingual teams, each with different underlying methodologies. In addition, different teams may survey the same object or site over a number of years, producing complimentary results on different platforms utilizing a variety of (possible outdated) technologies. In such conditions, it is difficult to make sense of the annotation and to determine which views should be registered together. We propose a new approach in which similar views are found by content-based indexing and retrieval of textures (2D) and range images (3D). The views are described automatically, according to their appearance and their 3D geometry. A search engine allows retrieving similar and related views for registration
关键词：Content-based indexing/retrieval; model; range images; registration; three-dimensional; 3D
