Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards a reliable detection of debris in high resolution SAR images of urban areas

: Kuny, Silvia; Hammer, Horst; Schulz, Karsten; Hinz, Stefan

Fulltext urn:nbn:de:0011-n-4189244 (4.4 MByte PDF)
MD5 Fingerprint: 2313794be6c5bfacd36e76355c110d9e
Created on: 4.11.2016

Verband Deutscher Elektrotechniker e.V. -VDE-, Berlin; Informationstechnische Gesellschaft -ITG-:
EUSAR 2016, 11th European Conference on Synthetic Aperture Radar. Proceedings : June 6-9, 2016, Hamburg/Germany; DVD
Berlin: VDE-Verlag, 2016
ISBN: 978-3-8007-4228-8
ISBN: 3-8007-4228-4
European Conference on Synthetic Aperture Radar (EUSAR) <11, 2016, Hamburg>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

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.