Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/31701
Title: Unsupervised change detection with expectation-maximization-based level set
Authors: Hao, M
Shi, W 
Zhang, H
Li, C
Keywords: Expectation-maximization (EM)
Level set method
Remote sensing
Unsupervised change detection
Issue Date: 2014
Source: IEEE Geoscience and remote sensing letters, 2014, v. 11, no. 1, 6519319, p. 210-214 How to cite?
Journal: IEEE Geoscience and Remote Sensing Letters 
Abstract: The level set method, because of its implicit handling of topological changes and low sensitivity to noise, is one of the most effective unsupervised change detection techniques for remotely sensed images. In this letter, an expectation-maximization-based level set method (EMLS) is proposed to detect changes. First, the distribution of the difference image generated from multitemporal images is supposed to satisfy Gaussian mixture model, and expectation-maximization (EM) is then used to estimate the mean values of changed and unchanged pixels in the difference image. Second, two new energy terms, based on the estimated means, are defined and added into the level set method to detect those changes without initial contours and improve final accuracy. Finally, the improved level set method is implemented to partition pixels into changed and unchanged pixels. Landsat and QuickBird images were tested, and experimental results confirm the EMLS effectiveness when compared to state-of-the-art unsupervised change detection methods.
URI: http://hdl.handle.net/10397/31701
ISSN: 1545-598X
DOI: 10.1109/LGRS.2013.2252879
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

20
Last Week
0
Last month
1
Citations as of Mar 24, 2017

WEB OF SCIENCETM
Citations

14
Last Week
0
Last month
0
Citations as of Mar 23, 2017

Page view(s)

21
Last Week
0
Last month
Checked on Mar 19, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.