Title :
A Threshold Selection Method Using Two SAR Change Detection Measures Based on the Markov Random Field Model
Author :
Xiong, Boli ; Chen, Qi ; Jiang, Yongmei ; Kuang, Gangyao
Author_Institution :
Sch. of Electron. Sci. & Eng., Nat. Univ. of Defense Technol., Changsha, China
fDate :
3/1/2012 12:00:00 AM
Abstract :
This letter presents a threshold selection method in change detection (CD) with synthetic aperture radar (SAR) images, which combines the characteristics of two different CD measures by using the Markov random field model. One is the well-known log-ratio CD measure, and the other is derived from the likelihood ratio and is based on the statistical properties of SAR intensity images. The proposed unsupervised CD algorithm overcomes the shortcomings and strengthens the advantages of these two measures. The experimental results with two pairs of SAR images show that the proposed algorithm is effective and better than the algorithms using the two aforementioned CD measures.
Keywords :
Markov processes; image segmentation; radar imaging; statistical analysis; synthetic aperture radar; Markov random field model; SAR change detection measure; SAR intensity image; likelihood ratio; log-ratio CD measure; statistical property; synthetic aperture radar image; threshold selection method; unsupervised CD algorithm; Hidden Markov models; Histograms; Markov processes; Monitoring; Remote sensing; Speckle; Synthetic aperture radar; Change detection (CD); Markov random field (MRF); synthetic aperture radar (SAR) image; threshold selection;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2011.2166149
