A new IKONOS imagery fusion approach using particle swarm optimization

Abstract

Spatial resolutions of IKONOS high-resolution panchromatic (PAN) and low-resolution multispectral (MS) satellite images are 1 m and 4 m, respectively. To cope with color distortion and blocking artifacts in fused images, in this study, a new IKONOS imagery fusion approach using particle swarm optimization (PSO) is proposed. The pixels of fused images in the training set are classified into several categories based on the characteristics of MS images. Then, within each category, the smooth parameters of spatial and spectral responses between PAN and MS images are determined by PSO training. Finally, all the pixels within each category can be normalized by its own smooth parameter so that color distortion and blocking artifacts can be greatly reduced. Based on the experimental results obtained in this study, the overall visual quality of the fused images by the proposed approach is better than that by the three comparison approaches, whereas the correlation coefficients for the fused images by the proposed approach are greater than that by the three comparison approaches.