Multi-spectral and digital elevation model information fusion for automatic 3d change detection

Abstract

Various 2D and 3D change detection techniques have been developed in the literature to monitor changes inside urban areas. Nevertheless, most of theses techniques require the interaction of the user either to input data, set parameters, or to train classifiers. Automatic unsupervised processes have been seldom tackled since they are very difficult to develop if high accuracies are necessary. This paper provides a fully automatic change detection procedure for urban areas monitoring. It exploits at best the information provided by multi-spectral images and Digital Elevation Model (DEM) from two different epochs. A fusion both at feature and decision levels is thus proposed to detect automatically for each epoch the following land cover classes: buildings, shadows, water areas, ground, low and high vegetation. Applying such fusion on Ikonos stereo data acquired over an Asian urban area in spring 2006 and winter 2010 and their ensuing DEMs has proved both the efficiency and worth of the joint use of the multi-spectral and height information. A class-for-class comparison is carried out between the two obtained classification maps to detect the changes that have occurred between 2006 and 2010 over the studied area. A set of standard evaluation measures are finally computed to assess the quality of the proposed procedure.