Automatic Change Detection on Satellite Images using Principal Component Analysis, ISODATA and Fuzzy C-Means Methods

Change detection is the process of comparing two or more images and identifying the parts where a change has occurred. Difference detection processing between simple digital images, such as photographic images, is easy to implement. Whereas for satellite images, which compose of several images' grayscale and bands, this requires a methodological approach to image processing appropriate to the exploitation of these data because this will allow to follow the evolution over time of a region of interest through change detection techniques, so these images are a tool of choice in the management of natural resources. So, in this paper, we propose a hybrid automatic change detection approach for multi-temporal satellite images. It is based on several algorithms: ISODATA for automatic thresholding, Principal Component Analysis as transformation technique, Fuzzy C-Means as classification technique. Experiments were performed and assessed by their overall accuracy and results validated the effectiveness and efficiency of the proposed approach, named ISOFAP.