Satellite image fusion for land cover classification

Abstract

Land cover classification provides information on how the land has been changed over the years. Through the remote sensing techniques using Synthetic Aperture Radar(SAR), SAR images are pre-processed and later segmented to produce the segmentation maps which gives the land cover classification. To further enhance the land cover classification accuracy, the processed SAR images are fused with the optical images to form a high-resolution composite image.

Therefore, this study explored the different pre-processing techniques using wiener filtering and morphological filtering and segmentation techniques including Chan-Vese and K-means clustering to produce the land cover classification of a SAR image taken from the southern west of Singapore, covering partial Malaysia. Lastly, the segmented SAR images were fused with the optical image at the same area. Visual comparisons were done on the fused images and results show that, by combining morphological filtering with K-means clustering method, it will give a better land cover classification.