DocumentCode
2154186
Title
A road extraction method from topographical map images
Author
Ahn, Chang ; Kim, Kyu Sik ; Rhee, Sang Burm ; Lee, Kye Young
Author_Institution
Dankook Univ., South Korea
Volume
2
fYear
1997
fDate
20-22 Aug 1997
Firstpage
839
Abstract
This paper describes an automatic road extraction method from color map images. This method has been developed as a part of a research on automated geographic database extraction from scanned color maps. In many cases, maps are constructed in a number of layers, where each layer is printed in a distinct color, and it represents a subset of the map information. The proposed method consists of color separation, road image restoration, and extraction of the skeleton. To obtain accurate road information from the color-separated road image, a new road image restoration algorithm is proposed. This algorithm is based on the conditional dilation operation of mathematical morphology and has an advantage in regard to reducing the various kinds of distortions, compared with using conventional processes. Through map input experiments with the method, the desired road information is efficiently extracted
Keywords
cartography; feature extraction; geographic information systems; image colour analysis; image restoration; mathematical morphology; automated geographic database extraction; automatic road extraction method; color separation; conditional dilation; distortion reduction; image restoration algorithm; map information; map input experiments; mathematical morphology; research; road image restoration; scanned color maps; skeleton extraction; topographical map images; Cities and towns; Color; Colored noise; Costs; Data mining; Image databases; Image restoration; Manuals; Roads; Skeleton;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, Computers and Signal Processing, 1997. 10 Years PACRIM 1987-1997 - Networking the Pacific Rim. 1997 IEEE Pacific Rim Conference on
Conference_Location
Victoria, BC
Print_ISBN
0-7803-3905-3
Type
conf
DOI
10.1109/PACRIM.1997.620390
Filename
620390
Link To Document