Fusion of Quickbird satellite images for vegetation monitoring in previously mined reclaimed areas

摘要

The goal of this study is to remotely monitor the status of re-vegetation growth in a reclaimed, previously mined region on the island of Milos, Greece. Quickbird multispectral (spatial resolution 2.4mx2.4m) and panchromatic (spatial resolution 0.6mx0.6m) images have been fused to obtain an optimal combination of the initial spatial and spectral resolution. The Blue (450nm-520nm), Green (520nm-600nm) and Near Infrared (760nm-900nm) bands of the multi-spectral image have been used for vegetation monitoring. Different fusion methods, like the Principal Component Analysis, the Intensity-Hue-Saturation transform and the Wavelet Analysis have been applied to Quickbird images. Both statistical (correlation coefficient, accuracy measures, etc.) and subjective (i.e., visual) measures have been used to evaluate the produced fused images. The degree to which each of the fused images retains the spectral and spatial features of the initial images has been thus estimated. Based on statistical measures, it has been found that the Additive Wavelet Principal Component "A Trous" and the Additive Wavelet Intensity Mallat methods effectively preserve most of the spectral information of the original multi-spectral image. On the other hand, the "A Trous" and Intensity-Hue-Saturation fusion techniques retain most of the spatial information of the panchromatic image. Additionally, the IHS transform offers a compromise between the spectral and spatial content of the fused image. Since the spectral content in the NIR band is of primary importance for monitoring re-vegetation growth, the Additive Wavelet Mallat and the IHS transforms are the most suitable choices.