A New Fusion Method for Remote Sensing Images

As a branch of Internet of Things (IoT), network geographic information (WebGIS) has the task of enhancing remote sensing images, including correction, fusion, mapping, etc. Remote sensing images captured by different satellite platforms often present earth objects with various scales. Due to the different spatial resolutions of imaging sensors, the same object will appear in different sizes. Usually panchromatic (PAN) image, without spectral diversity, has high spatial resolution and multispectral (MS) image has lower spatial resolution but more spectral information. Fusing MS and PAN images, also known as pansharpening, will increase the spatial resolution of MS image without changing its spectral information. In the fusion process, inaccurate perception and extraction of the spatial details will lead to spectral and spatial distortions in the fused image. A new multi-scale structure perception based fusion method is proposed in this paper. Firstly, an improved structure-preserving filter is designed by using MS imagery as the reference to capture the structures in the PAN image. Then the structures having different scales are progressively perceived through a multi-scale decomposition scheme and the spatial details are accurately extracted from the PAN image. Finally, the details weighted by the band-dependent gains are injected into each band of MS images. Experimental results are compared with some recently proposed edge-preserving filtering based fusion methods. Visual analysis and objective evaluations demonstrate that the proposed method can produce high-quality fused output and achieve better performance than some state-of-the-arts.