Unsupervised Change Detection in Multispectral Images based on Independent Component Analysis

2006 ◽  
Author(s):  
M. Ceccarelli ◽  
A. Petrosino
Keyword(s):  
Independent Component Analysis ◽  
Change Detection ◽  
Component Analysis ◽  
Independent Component ◽  
Multispectral Images

A Novel Change Detection Method Using Independent Component Analysis and Oriented-Object Method

2014 ◽  
Vol 548-549 ◽  
pp. 633-636
Author(s):  
Xiao Chun Li ◽  
Chun Yang Jia ◽  
Wei Hua Li
Keyword(s):  
High Resolution ◽  
Independent Component Analysis ◽  
Change Detection ◽  
Component Analysis ◽  
Detection Algorithm ◽  
Independent Component ◽  
Input Vector ◽  
Detection Methods ◽  
Discrete Wavelet ◽  
Oriented Object

hrough analyzing problems brought on change detection methods of high-resolution remote sensing images, a novel change detection algorithm is proposed. First, feature images of image’s objects extracted using oriented-object method serve as data of input vector to estimate sub-space for Independent Component Analysis(ICA), which can improve effect of noise suppression, simultaneously, a new algorithm using self-adapted weight is proposed in order to extract image’s object, which optimizes processing method on oriented-object deeply；new partitioning scheme using undecimated discrete wavelet transform(UDWT) overcomes effectively prominent problem which shrinking of the size of input vector becomes leads to unprecisely estimation of sub-space for ICA. Compared with typical algorithm, such as ICA and UDWT, simulation results show that new algorithm improves robust and veracity of change detection for high-resolution images greatly.

Sign in / Sign up

Export Citation Format

Share Document