Statistical Wavelet Subband Modeling for Multi-Temporal SAR Change Detection

Abstract

In the context of multi-temporal SAR change detection for earth monitoring applications, one critical issue is to generate accurate change map. A common method to generate change map is to apply logarithm to the ratio image. However, due to the speckle effect and without consideration of contextual information, it is usually not efficient for accurate change detection. In this paper, an unsupervised change detection method in wavelet domain based on statistical wavelet subband modeling is proposed. The motivation is to capture textures efficiently in wavelet domain. Wavelet transform is applied to decompose the image into multiple scales and probability density function of the coefficient magnitudes of each subband assumed to be Generalized Gaussian Distribution (GGD) and Generalized Gamma Distribution are obtained by fast parameter estimation. Closed-form expression of Kullback-Leibler divergence between two corresponding subbands of the same scale is computed and used to generate the change map. This approach is comprehensively evaluated and compared using different parameter setting, different scales, window sizes and estimators. The proposed SAR change detection in wavelet domain shows promising results as texture can be better characterized in wavelet domain than in spatial domain. Through this study, we conclude that the accuracy depends heavily on the estimation methods although the model is important. Both parameter estimation for GGD based on shape equation and parameter estimation for using method of log-cumulants (MoLC) in wavelet domain performs quite well. Index Terms-Generalized gamma distribution, Kullback-Leibler divergence, method of log-cumulants (MoLC), multitemporal SAR change detection, synthetic aperture radar (SAR), undecimated wavelet transform (UWT).

An Innovative Curvelet-only-Based Approach for Automated Change Detection in Multi-Temporal SAR Imagery

“…In order to develop more flexible change detection tools the logarithmic intensity quotient was investigated in terms of scale-dependent characteristics by the help of the wavelet transform [15,16]. Though using different statistical instruments, the crucial point that mostly is carried out by interactive parameter tuning still is the selection of the appropriate scale for the reliable change detection.…”

The Time Variable in Data Fusion: A Change Detection Perspective

“…To properly model multiscale/ resolution information different approaches have been used either before or after applying fusion at feature level according to the operators listed above. Among the others we recall the Wavelet decomposition [20]- [22], [24]- [28], the Contourlet transform [30], [31], and the local similarity measures computed on varying windows size [15] or multiscale segments [33]. Figure 7 shows an example of a change detection problem in high resolution SAR im-ages and of possible change indices.…”

A Benchmark Evaluation of Similarity Measures for Multitemporal SAR Image Change Detection

“…One prominent work in [7] proposed a method for multitemporal SAR change detection based on the evolution of the local statistics, which was extended to object-based change detection in [8]. A similar method has been extended to the wavelet domain [9]. In [10], several information similarity measures including distance to independence, mutual information, cluster reward, Woods criterion, and correlation ratio, were compared for change detection, among which mutual information has been demonstrated to be rather efficient.…”