Change Detection using Fast Subpixel Mapping Algorithms

Abstract

As Earth’s surface prone to change over years, there is a need to perform change detection (CD). However, it is difficult to obtain remote sensing images with both fine spatial and temporal resolution. In this paper, with the help of Sub-pixel mapping (SPM) both fine spatial and temporal CD images are obtained. Three fast SPM algorithms including SPSAM, Kriging and RBF interpolation methods are proposed for calculating soft class values. FRM is constructed using the soft class values. The auxiliary information available in FRM is used to increase CD accuracy.