Unsupervised change detection on SAR images using a new fractal-based measure

Change detection for land use/cover is very important in the application of remote sensing. This paper proposes a new fractal measure for automatic change detection in synthetic aperture radar (SAR) images. The proposed measure is computed based on the fractal dimension and intensity information. The fractal dimension is calculated using the wavelet multi-resolution analysis based on the concept of fractional Brownian motion. In the next stage, a binary decision is made at each pixel location to determine whether it is a change or not, by applying a threshold on the image derived from the proposed measure. The threshold is computed from the distribution of the proposed fractal measure using the well-known Otsu method. The proposed change indicator is compared to the classical log-ratio detector as well as two other statistical similarity measures, namely Gaussian Kullback-Leibler and cumulant-based Kullback-Leibler detectors. Experiments on simulated and real data show that the proposed approach achieves better results than the other detectors.