A Novel Pansharpening Method with Multi-scale Mutual-structure Perception

Network geographic information system (WebGIS), a branch of Internet of Things (IoT), is the extension and development of traditional GIS on the network, which integrates and upgrades many remote sensing information processing tasks such as pansharpening, mapping, classification, etc. Pansharpening technology allows a detailed redisplay of the earth surface by fusing a panchromatic (PAN) and a multispectral (MS) image acquired over the same area. The extraction of the details from the PAN image and their subsequent injection into the MS image are still the key points for the pansharpening design. In this paper, we propose a novel pansharpening method which considers the multi-scale mutual-structures of the PAN and MS image pair as a new reference for details extraction and applies a weighted details injection strategy to generate the fused MS image. The experimental results show that our proposed method can obtain high-quality sharpened results and has superior performance with respect to some recent approaches.