Clemens Listner

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, however, 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 shortcomings 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 Definiens Developer plug-in. The paper introduces the methodologies, describes the implementation and gives some (experimental) results on the application using simulated and real data.

Object-based change detection and classification

The paper presents some recent developments on object-based change detection and classification. In detail, the following algorithms were implemented either as Matlab or IDL programmes or as plug-ins for Definiens Developer: i) object-based change detection: segmentation of bitemporal datasets, change detection using the Multivariate Alteration Detection1 based on object features; ii) object features and object feature extraction: moment invariants, automated extraction of object features using Bayesian statistics; iii) object-based classification by neural networks: FFN and Class- dependent FFN using five different learning algorithms. The paper introduces the methodologies, describes the implementation and gives some examples results on the application.

Multiresolution segmentation adapted for object-based change detection

In object-based change detection approaches using specified object features as change measures, segmentation is the crucial step, especially when also shape changes are considered. In this paper we present an enhanced segmentation procedure based on the multiresolution segmentation. The procedure segments the first image using the multiresolution segmentation. The segmentation is then applied to the second image and checked for its consistency. If a segment is found to be inconsistent with the second image, it is split up. The performance of the proposed procedure is demonstrated based on simulated and real image data.

Treaty monitoring from space: satellite imagery analysis for verifying treaty compliance

Earth observation generally represents a key source of information for the different national and international bodies involved in the implementation of international agreements. If the area of interest is not accessible, remote sensing sensors represent one of the few opportunities to gather almost realtime data over the area. Taking into consideration recent developments in satellite sensor technologies and software solutions, the given paper discusses some challenges with regard to both technical and political issues.