SHAPE DETECTION OF STRUCTURAL CHANGES IN LONG TIME-SPAN AERIAL IMAGE SAMPLES BY NEW SALIENCY METHODS

The paper presents a novel, theoretically well-based methodology to find changes in remote sensing image series. The proposed method finds changes in images scanned with a long time-interval difference in very different lighting and surface conditions. The presented method is basically an exploitation of the Harris saliency function and its derivatives for finding featuring points among image samples; then a new local descriptor will be demonstrated by generating local active contours; a graph based shape descriptor will be shown based on the saliency points of the difference and in-layer features; finally, we prove the method's capabilities for finding structural changes on remote sensing images.