Fusion (MSI/HSI)

Features:

• Combines low-resolution hyperspectral dataset and high-resolution multispectral dataset to generate a high-resolution hyperspectral dataset.

• *Future release* Evaluates the quality of fusion.

Steps:

1.      Open Toolboxes → Fusion (MSI/HSI) in IDCube format. A new window will pop-up.

2.      Click Browse... and locate the multispectral and hyperspectral datasets.

3.      Select an algorithm from the ALGORITHM SELECTION panel. Currently available options are:

a.      Gram-Schmidt Adaptive algorithm.

b.      Smoothing filter-based intensity modulation with hypersharpening.

c.      Generalized Laplacian pyramid with hypersharpening.

Click the green Perform Data Fusion button. Click the Plot Spectra buttons and touch the images to visualize the spectra. Click on the top of the image to expand the image.

To save the fused dataset, right-click on the fused image and select Save as New Datacube.

References:

This toolbox includes three algorithms for fusing hyperspectral and multispectral data to obtain high-resolution hyperspectral data. The toolbox is based on the following references:

N. Yokoya, C. Grohnfeldt, and J. Chanussot, "Hyperspectral and multispectral data fusion: a comparative review of the recent literature," IEEE Geoscience and Remote Sensing Magazine, vol. 5, no. 2, pp. 29-56, June 2017.

 GSA (Gram-Schmidt adaptive): N. Yokoya, C. Grohnfeldt, and J. Chanussot, "Hyperspectral and multispectral data fusion: a comparative review of the recent literature," IEEE Geoscience and Remote Sensing Magazine, vol. 5, no. 2, pp. 29-56, June 2017.

SFIM-HS (Smoothing filtered-based intensity modulation with hypersharpening): J. G. Liu (2000) Smoothing Filter-based Intensity Modulation: A spectral preserve image fusion technique for improving spatial details, International Journal of Remote Sensing, 21:18, 3461-3472, DOI: 10.1080/014311600750037499

GLP-HS (Generalized Laplacian pyramid with hypersharpening): Selva, M.; Aiazzi, B.; Butera, F.; Chiarantini, L.; Baronti, S. Hyper-sharpening: A first approach on SIM-GA data. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 2015, 8, 3008–3024.

Hyperspec-VNIR Chikusei data converted to the IDCube format is available from our website. Visit https://www.idcubes.com/examples to download.