Extraction and integration of window in a 3D building model from ground view images
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Hi-index | 0.01 |
Current Internet-inspired mapping data are in the form of street maps, orthophotos, 3D models or street-side images to support searches and navigation. Images represent predominantly "eye candy" with little added value to the Internet-user. We analyze the Internet-inspired vertical aerial images themselves to add value to the data by detecting interesting data about the buildings, initially counting building floors and windows. For this purpose, oblique aerial imagery is less useful due to its excessive occlusions. This paper specifically introduces 3D point clouds to deal with balconies and awnings in the counting of floors and windows.