Use Fusion of SAR and Optical images for Land Cover Classification

In this paper, we fused TM image with intensity information of ALOS1PALSAR data, the information of HV/HH polarization ratio and coherence coefficient. The support vector machine (SVM) method was used to classify the land cover. The classification results of TM image, TM+SAR intensity image, TM+HV/HH ratio image and TM+ coherence image were compared. The results showed that the highest classification accuracy was the fusion of TM and coherence image, the followed one was TM and HV/HH, then was TM and intensity image and the lowest one is TM image. To varying degrees, the classification accuracy of land utilizes and cover could be improved with the fusion of optical images and SAR images.