Urban Change Detection Based on Edge Line Segments and Texture

In this paper, a novel approach based on edge line segments and texture is presented for urban change detection. First, we extract edge line segments based on Canny edge detector and line-support regions based on gradient orientation, Then changed edge line segments are found and grouped into clusters as potential changed regions which are finally validated using the difference of pixels and texture features. The main novelty of our approach is that the combination of different features, such as edge line segments and textures, is used for change detection and validation. The experiments with real Quickbird-II images show the promising performance of the proposed method.