Study on panchromatic and multispectral image fusion based on SFIM and CA transform

With the successive launch and rapid development of the new satellite WorldView-2 and WorldView-3, panchromatic and multispectral image fusion become a hot research topic. To resolve the dilemma of the currently existing methods for panchromatic and multispectral image fusion, viz. unavoidable spectral distortion or the need to introduce cumbersome frequency analysis and reconstruction, a method has been proposed which is based on SFIM (Smoothing Filter-based Intensity Modulation) and CA (Correspondence Analysis). Firstly, the weighted gradient adaptive filtering SFIM model is introduced, whose simple calculation feature has been utilized to extract the spatial information of panchromatic images. Secondly, the statistical CA transform has been brought in and its multivariable analysis feature has been used to process the infusion of spatial information. As a result of the above two processes the novel fusion method has been proposed which is based on SFIM and CA transform. Theoretical and experimental studies show that the proposed method can not only significantly maintain spectral characteristics, in absence of frequency decomposition and reconstruction, but also effectively infuse detailed spatial information, along with the elegancy of simple calculation and real time. In the scenario of panchromatic and multi-spectral image fusion such as similar lighting conditions and physical properties, the proposed method is more suitable for the fusion systems which require fast interactive processing and real-time visualization, and is better than those which are based upon multi-scale analysis.