Change Detection in High-Resolution SAR Images Based on Jensen–Shannon Divergence and Hierarchical Markov Model

This paper addresses the problem of change detection in high-resolution multitemporal synthetic aperture radar (SAR) images. We propose to use Jensen-Shannon divergence (JSD) to measure the dissimilarity of the two scenes acquired at different times for deriving the difference map (DM). We figure out this divergence in a nonparametric way by introducing a direct density ratio estimation, making the DM generation free of distribution assumption. We also present a multiscale change detection framework which can capture and combine change cues at different scales. First, the coregistered SAR image pairs are decomposed into different scales by multiscale decimated wavelet transform (DWT). Next, the DM in each scale is generated by computing the local JSD. These DMs are then represented by a hierarchical Markovian model based on a quad-tree structure. The change map is finally inferred relying on hierarchical marginal posterior mode (HMPM). Experimental results on multitemporal TerraSAR-X images demonstrate the effectiveness of the proposed approach.

[1]  W. Dierking,et al.  Sea ice motion and open water area at the Ronne Polynia, Antarctica: Synthetic aperture radar observations versus model results , 2013 .

[2]  Qiong Wu,et al.  A clustering approach for change detection in SAR images , 2012 .

[3]  Jordi Inglada,et al.  A New Statistical Similarity Measure for Change Detection in Multitemporal SAR Images and Its Extension to Multiscale Change Analysis , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Boli Xiong,et al.  A Threshold Selection Method Using Two SAR Change Detection Measures Based on the Markov Random Field Model , 2012, IEEE Geoscience and Remote Sensing Letters.

[5]  S. Quegan,et al.  Understanding Synthetic Aperture Radar Images , 1998 .

[6]  Sandro Martinis,et al.  A Hierarchical Spatio-Temporal Markov Model for Improved Flood Mapping Using Multi-Temporal X-Band SAR Data , 2010, Remote. Sens..

[7]  Martino Pesaresi,et al.  Statistical analysis of anisotropic rotation-invariant textural measurements of human settlements from multitemporal SAR data , 2011, 2011 Joint Urban Remote Sensing Event.

[8]  Sugiyama Masashi,et al.  Relative Density-Ratio Estimation for Robust Distribution Comparison , 2011 .

[9]  Salah Bourennane,et al.  Unsupervised change detection on SAR images using fuzzy hidden Markov chains , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Jean-Marie Nicolas,et al.  Application of log-cumulants to the detection of spatiotemporal discontinuities in multitemporal SAR images , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Stefan Voigt,et al.  Unsupervised Extraction of Flood-Induced Backscatter Changes in SAR Data Using Markov Image Modeling on Irregular Graphs , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[13]  D. Lu,et al.  Change detection techniques , 2004 .

[14]  Gabriele Moser,et al.  Unsupervised Change Detection From Multichannel SAR Data by Markovian Data Fusion , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Charles A. Bouman,et al.  A multiscale random field model for Bayesian image segmentation , 1994, IEEE Trans. Image Process..

[16]  Gabriele Moser,et al.  Classification of Very High Resolution SAR Images of Urban Areas Using Copulas and Texture in a Hierarchical Markov Random Field Model , 2013, IEEE Geoscience and Remote Sensing Letters.

[17]  Jean Carletta,et al.  Assessing Agreement on Classification Tasks: The Kappa Statistic , 1996, CL.

[18]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[19]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[20]  Patrick Pérez,et al.  Discrete Markov image modeling and inference on the quadtree , 2000, IEEE Trans. Image Process..

[21]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[22]  Josef Kittler,et al.  Minimum error thresholding , 1986, Pattern Recognit..

[23]  Luis Samaniego,et al.  Supervised Classification of Remotely Sensed Imagery Using a Modified $k$-NN Technique , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Jun Chen,et al.  Change Vector Analysis in Posterior Probability Space: A New Method for Land Cover Change Detection , 2011, IEEE Geoscience and Remote Sensing Letters.

[26]  M. Kawanabe,et al.  Direct importance estimation for covariate shift adaptation , 2008 .

[27]  Jakob J. van Zyl,et al.  Change detection techniques for ERS-1 SAR data , 1993, IEEE Trans. Geosci. Remote. Sens..

[28]  Takafumi Kanamori,et al.  A Least-squares Approach to Direct Importance Estimation , 2009, J. Mach. Learn. Res..

[29]  Martin J. Wainwright,et al.  Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization , 2008, IEEE Transactions on Information Theory.