Multivariate Statistical Modeling for Multitemporal SAR Change Detection Using Wavelet Transforms and Integrating Subband Dependencies

Citation

Bouhlel N, Akbari V, Meric S & Rousseau D (2022) Multivariate Statistical Modeling for Multitemporal SAR Change Detection Using Wavelet Transforms and Integrating Subband Dependencies. IEEE Transactions on Geoscience and Remote Sensing, 60. https://doi.org/10.1109/tgrs.2022.3215783

Abstract
In this article, we propose a new method for automatic change detection in multitemporal fully polarimetric synthetic aperture radar (PolSAR) images based on multivariate statistical wavelet subband modeling. The proposed method allows us to consider the correlation structure between subbands by modeling the wavelet coefficients through multivariate probability distributions. Three types of correlation are investigated: interscale, interorientation, and interpolarization dependences. The multivariate generalized Gaussian distribution (MGGD) is used to model the interdependencies between wavelet coefficients at different orientations, scales, and polarizations. Kullback–Leibler similarity measures are computed and used to generate the change map. Simulated and real multilook PolSAR data are employed to assess the performance of the method and are compared to the multivariate Gaussian distribution (MGD)-based method. We show that the information embedded in the correlation between subbands improves the accuracy of the change map, leading to better performance. Moreover, the MGGD represents better the correlations between wavelet coefficients and outperforms the MGD.

Keywords
Change detection; Kullback–Leibler (KL) divergence; multitemporal polarimetric synthetic aperture radar (PolSAR) images; multivariate generalized Gaussian distribution (MGGD); subband correlations; wavelet transform

Journal
IEEE Transactions on Geoscience and Remote Sensing: Volume 60

People

Dr Vahid Akbari

Lect in Artificial Intelligence/Data Sci, Computing Science and Mathematics - Division