Change Detection for Reconstruction Monitoring based on Very High Resolution Optical Data

Abstract

Change detection techniques are widely used in environmental monitoring, however, the issue of best suitability of change detection techniques for a specific application, even study area is still unanswered. In case of reconstruction monitoring, difference-based change detection methods are compared and evaluated in detecting changes on the study area Banda Aceh by using very high resolution optical data in this paper. They are classical image differencing, iteratively reweighted multivariate alteration detection (IR-MAD) and IR-MAD incorporating some textural features. The experimental results show that IR-MAD method has the best performance. Compared with manually acquired reference data, the change detection map produced by IR-MAD method is satisfying and promising.