Abstract:

Image change detection is a very important part of remote sensing image processing.Many algorithms have defects, such as highly complex or weakly antinosie. Since the dual-tree complex wavelet transform (DT-CWT) is shift invariant and has improved directional resolution, the DT-CWT is introduced in image change detection in order to provide accurate detection of small changes and attractive robustness against noise. Firstly, the DTCWT is used to decompose the image into a lowpass subband and six directional high-pass subbands at each scale. Secondly, principal component analysis (PCA) is used to create eigenvector and kmeans is used to categorize pixels into two parts (change and unchanged). Finally, both the intrascale fusion and the interscale fusion are used to detect the changed images.

Key words: DT-CWT;image change detection;PCA