Automated techniques for change detection using combined edge segment texture analysis, GIS, and 3D information

Abstract

A large number of algorithms for change detection from multitemporal remotely sensed images have been developed and applied. An overview and comparison of different methods can be found, for example, in Coppin et al. (2004), Lu et al. (2003), Mas (1999), Macleod and Congalton (1998), and Singh (1989). In general, change detection methods can be divided into three categories (Mas, 1999): (1) image enhancement methods, (2) multitemporal analysis, and (3) postclassification comparison. Other approaches combine several methods or consist of novel methodologies (an overview can be found in Lu et al., 2003). Image enhancement methods combine data mathematically to enhance image quality (Im et al., 2008). Examples include standards methods such as image difference, image ratio, and principal component and regression analysis. © 2014 by Taylor & Francis Group, LLC.