PROCEEDINGS OF THE ITE ANNUAL CONVENTION
Online ISSN : 2424-2292
Print ISSN : 1343-1846
ISSN-L : 1343-1846
2011
Session ID : 6-3
Conference information

6-3 A study on detection method of window areas on buildings from web images based on textures of windows
Satoshi UenoEmi MyodoShigeyuki Sakazawa
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
This paper studies a method of detecting the window areas on buildings from web bird's view images. Unlike conventional methods, our method does not depend on the edges of buildings, but utilizes regular patterns of textures of windows to cope with the low resolution of images and window reflection. Experimental results show that our method can precisely estimate window area ratio on the walls for 73% of all buildings.
Content from these authors
© 2011 The Institute of Image Information and Television Engineers
Previous article Next article
feedback
Top