30 October 2009 The research on recognition and extraction of river feature in IKNOS based on frequency domain
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749533 (2009) https://doi.org/10.1117/12.832838
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
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.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ke Wang, Ke Wang, Xuezhi Feng, Xuezhi Feng, Pengfeng Xiao, Pengfeng Xiao, Guoping Wu, Guoping Wu, } "The research on recognition and extraction of river feature in IKNOS based on frequency domain", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749533 (30 October 2009); doi: 10.1117/12.832838; https://doi.org/10.1117/12.832838
PROCEEDINGS
10 PAGES


SHARE
Back to Top