ISPRS-Archives The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS-Archives Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2194-9034 Copernicus Publications Göttingen, Germany 10.5194/isprs-archives-XLVIII-3-W2-2022-97-2022 A NOVEL ADAPTIVE REMOTE SENSING PANSHARPENING ALGORITHM BASED ON THE ICM Zhao H. T. 1 2 Li X. J. 1 2 3 Li Y. K. 1 2 3 Ge J. F. 1 2 https://orcid.org/0000-0002-1459-8387 Xu X. Y. 1 2 Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, China National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou, China Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou, China 27 10 2022 XLVIII-3/W2-2022 97 102 Copyright: © 2022 H. T. Zhao et al. 2022 This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/ This article is available from https://isprs-archives.copernicus.org/articles/isprs-archives-XLVIII-3-W2-2022-97-2022.html The full text article is available as a PDF file from https://isprs-archives.copernicus.org/articles/isprs-archives-XLVIII-3-W2-2022-97-2022.pdf

In the paper, a novel Intersecting Cortical Network Model (ICM) based adaptive pansharpening algorithm is proposed to solve the deficiency of spectral distortion and texture detail missing in the remote sensing image fusion. The Shuffled Frog Leaping Algorithm (SFLA) is used in the proposed method to adaptively optimize the ICM model parameters. The fitness function of SFLA is constructed by fusion evaluation index Q4 and SAM, which can generate the irregular optimal segmentation regions. Then, these regions are used to adaptively extract the detail information of the panchromatic image. Finally, the sharpened higher resolution image is obtained with the weighted details and the multispectral upsampling image. Experiments are carried out with the WorldView-2 and GF-2 high-resolution datasets. The experimental results shown that the proposed algorithm performs better compared with the existing pansharpening fusion methods both in the spectral preservation and spatial detail enhancement, which verifies the effectiveness of the algorithm.