In this paper, a novel modification applies to the Band-Dependent Spatial Detail (BDSD) framework to improve the fusion performance interestingly. Joint multiplication terms have been added to the conventional BDSD framework to make it nonlinear BDSD. It has been shown that joint product terms would lead to a better estimation of detail maps for each spectral band. To support the idea presented here, three public domain sensors were selected to conduct the experimental studies. The objective evaluation was performed through no-referenced quality metrics. Based on the visual assessment of fusion products, the developed generalized BDSD (nonlinear BDSD) approach better preserves spectral and spatial information to the fused outcome in comparison to the competitor methods.
ASJC Scopus subject areas
- Earth and Planetary Sciences (miscellaneous)
- Electrical and Electronic Engineering