DeepAI AI Chat
Log In Sign Up

Model-based image adjustment for a successful pansharpening

by   Gintautas Palubinskas, et al.

A new model-based image adjustment for the enhancement of multi-resolution image fusion or pansharpening is proposed. Such image adjustment is needed for most pansharpening methods using panchromatic band and/or intensity image (calculated as a weighted sum of multispectral bands) as an input. Due various reasons, e.g. calibration inaccuracies, usage of different sensors, input images for pansharpening: low resolution multispectral image or more precisely the calculated intensity image and high resolution panchromatic image may differ in values of their physical properties, e.g. radiances or reflectances depending on the processing level. But the same objects/classes in both images should exhibit similar values or more generally similar statistics. Similarity definition will depend on a particular application. For a successful fusion of data from two sensors the energy balance between radiances/reflectances of both sensors should hold. A virtual band is introduced to compensate for total energy disbalance in different sensors. Its estimation consists of several steps: first, weights for individual spectral bands are estimated in a low resolution scale, where both multispectral and panchromatic images (low pass filtered version) are available, then, the estimated virtual band is up-sampled to a high scale and, finally, high resolution panchromatic band is corrected by subtracting virtual band. This corrected panchromatic band is used instead of original panchromatic image in the following pansharpening. It is shown, for example, that the performance quality of component substitution based methods can be increased significantly.


page 7

page 8

page 10

page 14

page 15


Super-resolving multiresolution images with band-independant geometry of multispectral pixels

A new resolution enhancement method is presented for multispectral and m...

Studying Satellite Image Quality Based on the Fusion Techniques

Various and different methods can be used to produce high-resolution mul...

A New Pseudo-color Technique Based on Intensity Information Protection for Passive Sensor Imagery

Remote sensing image processing is so important in geo-sciences. Images ...

A Bivariate Dead Band Process Adjustment Policy

A bivariate extension to Box and Jenkins (1963) feedback adjustment prob...

S2A: Wasserstein GAN with Spatio-Spectral Laplacian Attention for Multi-Spectral Band Synthesis

Intersection of adversarial learning and satellite image processing is a...

Conditional Chromatic Filtering with Spatial Enhancement for Restoring Pansharpened Images

Pansharpening techniques aim at fusing the structural detail of the panc...