PROJECT TITLE :
Forcing Scale Invariance in Multipolarization SAR Change Detection
This paper considers the problem of coherent (in the sense that both amplitudes and relative phases of the polarimetric returns are used to construct the choice statistic) multipolarization synthetic aperture radar modification detection beginning from the provision of image pairs exhibiting possible power mismatches/miscalibrations. The principle of invariance is used to characterize the class of scale-invariant call rules that are insensitive to power mismatches and guarantee the constant false alarm rate property. A maximal invariant statistic is derived together with the induced maximal invariant in the parameter space that significantly compresses the information/parameter domain. A generalized likelihood ratio check is synthesized both for the cases of two- and 3-polarimetric channels. Interestingly, for the two-channel case, it is based on the comparison of the condition range of a data-dependent matrix with a suitable threshold. Some further invariant call rules are proposed. The performance of the thought-about scale-invariant structures is compared to those from two noninvariant counterparts using each simulated and real radar data. The results highlight the robustness of the proposed technique and therefore the performance tradeoff involved.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here