Share Email Print

Proceedings Paper

The research on recognition and extraction of river feature in IKNOS based on frequency domain
Author(s): Ke Wang; Xuezhi Feng; Pengfeng Xiao; Guoping Wu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Because the resolution of remotely sensed imagery becomes higher, new methods are introduced to process the high-resolution remotely sensed imagery. The algorithms introduced in this paper to recognize and extract the river features based on the frequency domain. This paper uses the Gabor filter in frequency domain to enhance the texture of river and remove the noise from remotely sensed imagery. And then according to the theory of phase congruency, this paper retrieves the PC of every point such that features such as edge of river, building and farmland in the remotely sensed imagery. Lastly, the skeletal methodology is introduced to determine the edge of river within the help of the trend of river.

Paper Details

Date Published: 30 October 2009
PDF: 10 pages
Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749533 (30 October 2009); doi: 10.1117/12.832838
Show Author Affiliations
Ke Wang, Nanjing Univ. (China)
Xuezhi Feng, Nanjing Univ. (China)
Pengfeng Xiao, Nanjing Univ. (China)
Guoping Wu, Nanjing Univ. (China)

Published in SPIE Proceedings Vol. 7495:
MIPPR 2009: Automatic Target Recognition and Image Analysis
Tianxu Zhang; Bruce Hirsch; Zhiguo Cao; Hanqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?