Presentation 2010-10-08
A study on estimating ratio of window area in building wall from streetscape images
Satoshi UENO, Ryoichi KAWADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method to estimate the ratio of window area in building wall from streetscape images on the web. In order to figure out the areas of mobile communications in advance, it is necessary to apply radio wave propagation simulation which requires 3D map data. However, it is generally very expensive to make the precise map data by field research. On the other hand, in recent years, streetscape images are published on the web. It is desirable to obtain accurate map data by analyzing these streetscape images. Among 3D map data, it is important to estimate the ratio of window area in building wall. This estimation poses a technical challenge because of the wide-baseline images and window reflection. This paper proposes a novel approach which combines two methods to deal with the window refection; a method of merging multi-view streetscape images and a method of detecting the window areas on the upper building areas.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Specific object recognition / streetscape images / window detection
Paper # PRMU2010-93,SP2010-49,WIT2010-37
Date of Issue

Conference Information
Committee WIT
Conference Date 2010/10/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on estimating ratio of window area in building wall from streetscape images
Sub Title (in English)
Keyword(1) Specific object recognition
Keyword(2) streetscape images
Keyword(3) window detection
1st Author's Name Satoshi UENO
1st Author's Affiliation KDDI R & D Laboratories Inc.()
2nd Author's Name Ryoichi KAWADA
2nd Author's Affiliation KDDI R & D Laboratories Inc.
Date 2010-10-08
Paper # PRMU2010-93,SP2010-49,WIT2010-37
Volume (vol) vol.110
Number (no) 221
Page pp.pp.-
#Pages 6
Date of Issue