Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Feature extraction for change analysis in SAR time series

: Boldt, Markus; Thiele, Antje; Schulz, Karsten; Hinz, Stefan


Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Electro-Optical Remote Sensing, Photonic Technologies, and Applications IX : 21. September 2015, Toulouse, France
Bellingham, WA: SPIE, 2015 (Proceedings of SPIE 9649)
ISBN: 978-1-62841-859-0
Paper 964410, 10 S.
Conference "Electro-Optical Remote Sensing, Photonic Technologies, and Applications" <9, 2015, Toulouse>
Fraunhofer IOSB ()
change detection; categorization; feature extraction; synthetic aperture radar; SAR; TerraSAR-X; time series

In remote sensing, the change detection topic represents a broad field of research. If time series data is available, change detection can be used for monitoring applications. These applications require regular image acquisitions at identical time of day along a defined period. Focusing on remote sensing sensors, radar is especially well-capable for applications requiring regularity, since it is independent from most weather and atmospheric influences. Furthermore, regarding the image acquisitions, the time of day plays no role due to the independence from daylight. Since 2007, the German SAR (Synthetic Aperture Radar) satellite TerraSAR-X (TSX) permits the acquisition of high resolution radar images capable for the analysis of dense built-up areas. In a former study, we presented the change analysis of the Stuttgart (Germany) airport. The aim of this study is the categorization of detected changes in the time series. This categorization is motivated by the fact that it is a poor statement only to describe where and when a specific area has changed. At least as important is the statement about what has caused the change. The focus is set on the analysis of so-called high activity areas (HAA) representing areas changing at least four times along the investigated period. As first step for categorizing these HAAs, the matching HAA changes (blobs) have to be identified. Afterwards, operating in this object-based blob level, several features are extracted which comprise shape-based, radiometric, statistic, morphological values and one context feature basing on a segmentation of the HAAs. This segmentation builds on the morphological differential attribute profiles (DAPs). Seven context classes are established: Urban, infrastructure, rural stable, rural unstable, natural, water and unclassified. A specific HA blob is assigned to one of these classes analyzing the CovAmCoh time series signature of the surrounding segments. In combination, also surrounding GIS information is included to verify the CovAmCoh based context assignment. In this paper, the focus is set on the features extracted for a later change categorization procedure.