Unsupervised Change Detection using Image Fusion and Kernel K-Means Clustering

Change detection algorithms play a vital role in overseeing the transformations on the earth surface. Unsupervised change detection has a indispensable role in an immense range of applications like remote sensing, motion detection, environmental monitoring, medical diagnosis, damage assessment, agricultural surveys, surveillance etc In this paper, a novel method for unsupervised change detection in synthetic aperture radar(SAR) images based on image fusion and kernel K-means clustering is proposed. Here difference image is generated by performing image fusion on mean-ratio and log-ratio image and for fusion discrete wavelet transform is used. On the difference image generated by collecting the information from mean-ratio and log-ratio image kernel Kmeans clustering is performed. In kernel K-means clustering, non-linear clustering is performed, as a result the false alarm rate is reduced and accuracy of the clustering process is enhanced. The aggregation of image fusion and kernel Kmeans clustering is seen to be more effective in detecting the changes than its preexistences.