The evaluation of performances of fusion methods is a key problem in remote sensing image fusion. In this paper, four
representative fusion methods, PCA fusion, WT fusion, CT fusion and TLS-GIF-WC, are adopted to fuse two sets of
ALI images for comparison. The fusion products are applied to two remote sensing applications, vegetation index
extraction and image classification. The normalized difference vegetation index (NDVI), vegetation coverage and
classification accuracy indices are adopted to compare the fusion products. Experiments show that the GIF fusion
products are more adaptive for vegetation application, since the NDVI and vegetation coverage extracted from the fusion
product are consistent with that extracted from the initial image, and the ARSIS concept fusion and TLS-GIF-WC
products are more adaptive for image classification, because of the higher classification accuracy.
Beijing-1 satellite is a DMC+4 microsatellite which will be used in land use, city planning field. It provides both multispectral (MS) and panchromatic (PAN) data with spatial resolutions of 32m and 4m, respectively. Fusion is used to produce high-resolution multispectral images from a PAN image and low-resolution MS images. In this paper, beijing-1 PAN image and MS images of Chengdu are fused by both COS method and wavelet transform method. Several experiments are taken to test the properties of fusion result. Experiment results show that wavelet based fusion method provided satisfied results with better quality than the other methods in both spatial and spectral domains.