Share Email Print

Proceedings Paper

Feature extraction for change analysis in SAR time series
Author(s): Markus Boldt; Antje Thiele; Karsten Schulz; Stefan Hinz
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

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.

Paper Details

Date Published: 20 October 2015
PDF: 10 pages
Proc. SPIE 9644, Earth Resources and Environmental Remote Sensing/GIS Applications VI, 964410 (20 October 2015); doi: 10.1117/12.2193763
Show Author Affiliations
Markus Boldt, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Karlsruher Institut für Technologie (Germany)
Antje Thiele, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Karlsruher Institut für Technologie (Germany)
Karsten Schulz, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Stefan Hinz, Karlsruher Institut für Technologie (Germany)

Published in SPIE Proceedings Vol. 9644:
Earth Resources and Environmental Remote Sensing/GIS Applications VI
Ulrich Michel; Karsten Schulz; Manfred Ehlers; Konstantinos G. Nikolakopoulos; Daniel Civco, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?