文章基本信息

标题：Strategies for Texturing Building Models With Low Resolution Infrared Image Sequences
本地全文：下载
作者：Ludwig Hoegner ; Holger Kumke ; Uwe Stilla 等
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/C55
出版社：Copernicus Publications
摘要：Focus of this paper is a strategies for texturing building models with partial images extracted from infrared image sequences. A given 3d building model is used for the projection of the images into the 3d object space. Caused by an insufficient camera position from the GPS the outer orientation of the virtual camera has to be corrected. Two different concepts are used depending on the geometric condition of the recorded scene and model. For scenes with many geometrical details visible in the corresponding 3d model view, the first concept is used. The polygons of the faces of the 3d model are projected into the IR image and matched to the edges for assigning the correct parts of the image to the corresponding faces of the model. These image parts are then projected onto the faces and stored as surface textures. For scenes with only few visible geometry in the projected 3d model, the second concept assumes a homography to detect surface planes of facades in two subsequent images and generates a camera path relative to those planes. Then, theses planes are matched to the 3d model to generate the final camera path. Generally, a single image does not show a complete building facade. The extracted textures of the images are combined to create complete textures for the model surfaces. For analyzing buildings these textures can be used for extraction of features or recognition of objects in a corrected image space
关键词：Texturing; 3d models; image sequences; infrared; image analysis; texture extraction