Unmixing-based Fusion of Hyperspectral Images with High Spatial Resolution Images

Gercek D., Cesmeci D., GÜLLÜ M. K. , ERTÜRK A., ERTÜRK S.

21st Signal Processing and Communications Applications Conference (SIU), CYPRUS, 24 - 26 April 2013 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2013.6531495
  • Country: CYPRUS
  • Kocaeli University Affiliated: Yes


Hyperspectral images having very high spectral resolution are subject to low spatial resolution due to technical constraints. Fusion of hyperspectral images with high resolution multispectral images produces high information-content, high spectral and spatial resolution images. In this study for spatial resolution enhancement of hyperspectral images we propose unmixing-based approaches of fusion with high spatial resolution images. Accordingly; end members extracted out of hyperspectral images are adjusted to multispectral images and they are used to derive high resolution abundances to end up with a fused image. Method is applied on two datasets with hyperspectral and multispectral components as input one being a synthetic and other a real dataset. Method produced better accuracy over conventional methods used in image fusion.