A novel method for change detection in spectral imagery

摘要

A new method for change detection of two large area scenes based on the point density of the pixel distribution inthe hyperspace is presented. This method is derived from the point density approach to hyperspectral analysis,originally developed for material discrimination based on inherent dimension estimation. In this method, tworegistered large area scenes are tiled for individual scoring and comparison. The point density tail lengthis estimated for each tile in both scenes. The difference between this value for corresponding tiles indicateswhether change has likely occurred in a tile and how significant the change is relative to other changes in theimage. The method does not identify changes in individual pixels, but uses a tiling approach to identify changesin small sub-regions of the image. Preliminary results of this methodology are presented for multiple images andchanging scene phenomenology.