Influence of Image Fusion Methods on Land Cover/Use Classification

While many studies on the image fusion of remote sensing data aim towards deriving new algorithms for visual enhancement, there is little research on the influence of image fusion on land cover/use classification. This study focuses on the influence of image fusion on the land cover/use classification and their accuracy. SPOTS images were applied and used High Pass Filter, Brovery, Multiplication, Intensity-Hue-Saturation, Principal Component Transform methods for the fusion experiment to assess their performance. Image classification was performed with supervised and unsupervised methods. Acceptable results were achieved by HPF image fusion. BT, MLT, IHS and PCA methods performed poorly and cannot be recommended for classification of fused imagery.