A Non-Dominated Sorting Genetic Algorithm-II-based approach to optimize the spectral and spatial quality of component substitution-based pansharpened images
Üst veriTüm öğe kaydını göster
KünyeYılmaz, V. (2020). A Non‐Dominated Sorting Genetic Algorithm‐II‐based approach to optimize the spectral and spatial quality of component substitution‐based pansharpened images. Concurrency and Computation. Doi: 10.1002/cpe.6030.
Pansharpening aims to fuse a lower-resolution multispectral (MS) image and a higher-resolution panchromatic image, resulting in an image with the color quality of the former and spatial detail quality of the latter. Of all, the component substitution (CS)-based pansharpening methods have drawn attentions with their ability to produce sharp images. Despite their success in sharpening the images, these methods deteriorate the color features of the input MS images due of the uncertainty in the calculation of the intensity component used by them. Previous studies showed that attempts to preserve the color features tend to cause spatial detail loss to a certain extent. This, of course, reveals the necessity of a compromise between the spectral and spatial fidelity of the pansharpened images produced by the CS-based techniques. This study proposed using the multi-objective Non-Dominated Sorting Genetic Algorithm-II metaheuristic algorithm with the CS-based methods to optimize the intensity component to find the best compromise between the spectral and spatial fidelity of the pansharpened images. The proposed framework was applied on two commonly used pansharpening techniques, Gram-Schmidt and Synthetic Variable Ratio. It was found that the proposed methods managed to find the best balance between the color and spatial fidelity.