Synthetic aperture radar image change detection based on an image fusion strategy

Change detection is a hot topic and of great importance in remote sensing. The logarithm operation can be an effective means of eliminating the influence of multiplicative noise in the synthetic aperture radar (SAR) image. However, due to the nature of the logarithmic function, regions of change with high gray values are attenuated. In this study, we propose SAR to detect image changes based on an image fusion strategy by combining two different methods. First, we reduce speckle by non-subsampled shearlet transform in the log-domain, since this logarithmic function has the advantage of transforming multiplicative speckle noise into additive noise. As we know, the difference method always detects the areas with the largest changes. The difference method based on saliency extraction (SE) is applied to the exponent transformational SAR image to complement the disadvantage of WLR. WLR is used to obtain a change map of WLR to reduce the influence of SE when WLR does not detect the changed areas. Finally, two change maps can be added to obtain the final result. Experimental results for real SAR image pairs show the effectiveness of the proposed method in terms of detection rate, false alarm rate, and overall accuracy.