Recent advances in object-based change detection

With the advances in satellite sensor technologies as to spatial resolution, the concept of object-based image analysis (OBIA) has been become widely-used in different remote sensing applications and involved the development of some COTS systems. None of the systems available today is able to achieve the accuracy of human image interpreters, how ever, all of them are able to at least provide a pre-selection of relevant object features and image objects. The procedures implemented in the systems still show some short comings in terms of segmentation, feature extraction, multitemporal analysis, and others. Against this background, this paper aims to present some recent developments and advances in object-based change detection. In detail, procedures based on multiresolution segmentation (MRS) and iteratively reweighted multivariate alteration detection (IR-MAD) were implemented as C++ stand-alone programmes and Defmiens Developer plug-in. The paper introduces the methodologies, describes the implementation and gives some (experimental) results on the application using simulated and real data.