Presentation 2003/9/2
Road Extraction from Aerial Imagery based on Crossing Detection(Intelligent Transport Systems Technology)
Go KOUTAKl, Keiichi UCHIMURA, Shinji WAKISAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The freshness of map data is more important important element in a Geographic Information Systems(GIS), and due to update of a map data in the shorter cycle, the automatic generation of a road map from a aerial imagery gets a lot of attention. Many reserches on this subject have reported different methods. However, an operational environment is still quite small. In this paper, we propose a method that generates road network from aerial imagery using a top-down approach. In the method, crossing is extracted, and road tracking method connects two crossing. For reconstructing the road shape, we use the method of "Snakes". Finally, we applied successfully to extract the road in the image of residential area in suburb.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Road Extraction / Aerial Imagery / Road Network
Paper # ITS2003-30
Date of Issue

Conference Information
Committee ITS
Conference Date 2003/9/2(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 Intelligent Transport Systems Technology (ITS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Road Extraction from Aerial Imagery based on Crossing Detection(Intelligent Transport Systems Technology)
Sub Title (in English)
Keyword(1) Road Extraction
Keyword(2) Aerial Imagery
Keyword(3) Road Network
1st Author's Name Go KOUTAKl
1st Author's Affiliation Faculty of Engineering, Kumamoto University()
2nd Author's Name Keiichi UCHIMURA
2nd Author's Affiliation Faculty of Engineering, Kumamoto University
3rd Author's Name Shinji WAKISAKA
3rd Author's Affiliation (C)ZENRIN
Date 2003/9/2
Paper # ITS2003-30
Volume (vol) vol.103
Number (no) 294
Page pp.pp.-
#Pages 7
Date of Issue