Title :
Extraction and integration of window in a 3D building model from ground view images
Author :
Lee, Sung Chun ; Nevatia, Ram
Author_Institution :
Inst. for Robotics & Intelligent Syst., Southern California Univ., Los Angeles, CA, USA
fDate :
27 June-2 July 2004
Abstract :
Details of the building facades are needed for high quality fly-through visualization or simulation applications. Windows form a key structure in the detailed facade reconstruction. In this paper, given calibrated facade texture (i.e. the rectified texture), we extract and reconstruct the 3D window structure of the building. We automatically extract windows (rectangles in the rectified image) using a profile projection method, which exploits the regularity of the vertical and horizontal window placement. We classify the extracted windows using 2D dimensions and image texture information. The depth of the extracted windows is automatically computed using window classification information and image line features. A single ground view image is enough to compute 3D depths of the facade windows in our approach.
Keywords :
computer vision; feature extraction; image reconstruction; image texture; 3D building model; building facades; fly-through visualization; ground view images; image extraction; image texture information; profile projection method; Buildings; Cameras; Computer vision; Data mining; Focusing; Image reconstruction; Intelligent robots; Solid modeling; Visualization; Windows;
Conference_Titel :
Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on
Print_ISBN :
0-7695-2158-4
DOI :
10.1109/CVPR.2004.1315152