Towards a Reliable Detection of Debris in High Resolution SAR Images of Urban Areas
Konferenz: EUSAR 2016 - 11th European Conference on Synthetic Aperture Radar
06.06.2016 - 09.06.2016 in Hamburg, Germany
Tagungsband: EUSAR 2016
Seiten: 4Sprache: EnglischTyp: PDF
Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt
Autoren:
Kuny, Silvia (Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Ettlingen, Germany & Institute of Photogrammetry and Remote Sensing IPF, Karlsruhe Institute of Technology KIT, Germany)
Hammer, Horst; Schulz, Karsten (Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Ettlingen, Germany)
Hinz, Stefan (Institute of Photogrammetry and Remote Sensing IPF, Karlsruhe Institute of Technology KIT, Germany)
Inhalt:
For texture based damaged detection in SAR imagery, heaps of debris surrounding damaged buildings pose the most promising signatures. However, the textural similarity to the signature of high vegetation proves to be a problem. The focus of this paper is on the effective separation of the SAR signature of debris and high vegetation in high resolution SAR imagery. The approach of training a classifier with simulated data aims at being independent from the actual SAR image to be investigated. Thus a more generic approach to the identification of destructions in SAR images can be provided.