Multi-scale and Multi-directional Fusion Method for Building Circular Layout Image Based on Morphological Transformation

Abstract

The circular imaging technology of the building layout can obtain its internal information, which has been widely applied in the field of anti-terrorisms and combats. The problems of the imaging broadening caused by the scattering of the echo in the process of the penetrating between building walls bring the great inconvenience to the building layout reconstruction. In this paper, a multi-scale and multi-directional fusion method for the building circular layout image based on the morphological transformation has been proposed. Firstly, the multi-scale and multi-directional decomposition of the images from the various perspectives has been carried out by the nonsubsampled shearlet transformation. Moreover, the fusion method based on the morphological changes is carried out for low-frequency images, while the fusion method of taking the large regional variance is adopted for the high-frequency images. Finally, the inverse nonsubsampled shearlet transform transformation is respectively performed on the fused images, which can obtain the high-quality and high-precision building layout image. The experiment results are shown to prove the effectiveness of the proposed method.