Unsupervised change detection in VHR remote sensing imagery – an object-based clustering approach in a dynamic urban environment

• Published in: International journal of applied earth observation and geoinformation Vol. 54; pp. 15 - 27
• Main Authors: Leichtle, Tobias, Geiß, Christian, Wurm, Michael, Lakes, Tobia, Taubenböck, Hannes
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2017
• Subjects: Change detection; Clustering; Object-based image analysis; Principal component analysis; Urban environment; Very-high resolution (VHR) remote sensing; Very-high resolution (VHR) remote sensing; Urban environment; Clustering; Change detection; Object-based image analysis; Principal component analysis
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2016.08.010

•We present a new change detection approach with focus on individual buildings.•It is capable of handling VHR remote sensing images acquired by different sensors.•Deviating viewing geometries of VHR data affect the approach only slightly.•PCA of object-based difference features is followed by k-means clustering.•Viable and robust results are achieved in the order of κ statistics of 0.8–0.9. Monitoring of changes is one of the most important inherent capabilities of remote sensing. The steadily increasing amount of available very-high resolution (VHR) remote sensing imagery requires highly automatic methods and thus, largely unsupervised concepts for change detection. In addition, new procedures that address this challenge should be capable of handling remote sensing data acquired by different sensors. Thereby, especially in rapidly changing complex urban environments, the high level of detail present in VHR data indicates the deployment of object-based concepts for change detection. This paper presents a novel object-based approach for unsupervised change detection with focus on individual buildings. First, a principal component analysis together with a unique procedure for determination of the number of relevant principal components is performed as a predecessor for change detection. Second, k-means clustering is applied for discrimination of changed and unchanged buildings. In this manner, several groups of object-based difference features that can be derived from multi-temporal VHR data are evaluated regarding their discriminative properties for change detection. In addition, the influence of deviating viewing geometries when using VHR data acquired by different sensors is quantified. Overall, the proposed workflow returned viable results in the order of κ statistics of 0.8–0.9 and beyond for different groups of features, which demonstrates its suitability for unsupervised change detection in dynamic urban environments. With respect to imagery from different sensors, deviating viewing geometries were found to deteriorate the change detection result only slightly in the order of up to 0.04 according to κ statistics, which underlines the robustness of the proposed approach.