Fusion of hyperspectral and panchromatic images with guided filter

• Published in: Signal, image and video processing Vol. 12; no. 7; pp. 1369 - 1376
• Main Authors: Dong, Wenqian, Xiao, Song, Qu, Jiahui
• Format: Journal Article
• Language: English
• Published: London Springer London 01.10.2018; Springer Nature B.V
• Subjects: Computer Imaging; Computer Science; Computer vision; Image filters; Image processing; Image Processing and Computer Vision; Multimedia Information Systems; Original Paper; Pattern Recognition and Graphics; Signal,Image and Speech Processing; Vision; Guided filter; Panchromatic (PAN); Hyperspectral (HS); Injection gains matrix
• ISSN: 1863-1703; 1863-1711
• DOI: 10.1007/s11760-018-1291-z

Guided filter has been widely used in image fusion. However, most of the guided filter-based fusion methods generate the spatial detail image by making a compromise between the spatial detail of the panchromatic (PAN) and that of the hyperspectral (HS) intensity component. The intensity component cannot well present the edge and texture features of the HS image. The spectral distortion usually occurs due to the injected redundant spatial detail. To overcome this problem, this study presents a novel HS image fusion method by taking the advantage of the guided filter. The characteristics of the PAN and HS images are simultaneously considered. The guided filter is employed to generate the spatial detail image of each HS image band successively. The generated spatial detail image is further optimized by minimizing the difference between each band of the spatial detail image and its corresponding band of the HS image, with the help of a novel injection gains matrix. Experiments performed on various satellite datasets demonstrate that the superiority of the proposed method in spectral maintenance and spatial quality aspects.