Processing of satellite images in the context of the joint project ENVILAND/ENVILAND2

Project supporter:  

Forwarded by German Aerospace Center (Deutsche Zentrum für Luft- und Raumfahrt - DLR ) with financial resources of Bundesministeriums für Wirtschaft und Technologie 

Project partner:  

Jena-Optronik GmbH 






Project runtime:  

2004 - 2012 

Manager of subproject:  

Dr.-Ing. habil. K.-H. Franke  

Contact person:  

Dr.-Ing. habil. K.-H. Franke , Dr.-Ing. Rico Nestler  

More informations can be found at: 

Many remote-sensing missions of the earth, i.e. by ENVISAT, Landsat, Ikonos, Quickbird, ERS, RapidEye, TerraSAR-X and airborne supported ERS, rise multimodal geo-data in form of multispectral optical images as well as radar data in different polarity and resolution. These can be introduced to solve several manifoldly tasks.
The main-topic of the joint projects ENVILAND / ENVILAND 2 is the creation of land-cover mapping as a result of an automatic image processing task. Tasks, like automatic mapping of cereal crop, estimation of biophysical parameters and coverage of change dynamics, have to be solved by this way. Subject of this work is the development of a processing pipeline as software prototype. Each processing step takes on specific task (geocoding, edge extraction, registration, segmentation, classification). At this huge amount of data has to be handled (standard-size: 12000x12000 pixels).

The thematic main focus of the Zentrum für Bild- und Signalverarbeitung (ZBS) is the development of registration- and segmentation-algorithms and their efficient integration. In addition to this, several classification- (i.e. SVM & Ensemble-Systems ) and threshold-extraction-algorithms and concepts were made available and tested (see processing chain below, results of our work can be found in the red-tagged parts).

Enviland-2 Prozesskette

Basis for the synergetic data processing is the registration of specific disturbed images of different modality (radar, optical, ... ). These images may also exists in different resolutions. Here finding structural correspondences within the complementary image modalities is a special challenge. Beforehand powerful filter algorithms must be used to remove the effect of complex-built noise on the data.
Both the segmentation and the developed concepts for the segmentbased classification exploit the information content of the multimodal data for the purpose of the goals of the data processing.

Landsat-5-Szene Ergebnis der SVM-Klassifikation
Figure 1: section of Landsat-5-scene of region colone-bonn (rgb-composit of channels 5,4,3) Figure 2: result of SVM-classification (blue = urban region; yellow= water; green= forest; white,pink,light red= agriculture)
Torsten Koch
Rico Nestler
Karl-Heinz Franke
Determinierte semantische Segmentierung multikanaliger Daten zur automatischen Prozessierung von Fernerkundungsdaten

Posterveröffentlichung im Rahmen des 1. Gemeinsames Arbeitskreis-Treffen des AK „Fernerkundung“ der DGfG und des AK „Auswertung von Fernerkundungsdaten“ der DGPF in Bochum am 4./5.10.2012
Oktober 2012
Torsten Koch
Rico Nestler
Karl-Heinz Franke
Segmentierung mehrkanaliger Datenaufkommen am Beispiel einer Ver­ar­bei­tungs­ket­te für die Fern­er­kun­dung

Proceedings of 18. Workshop Farbbildverarbeitung, ISBN: 978-3-00-039639-7, Darmstadt, Deutschland, 27.-28.9.2012, pp. 149-157
September 2012
Torsten Koch,
Rico Nestler,
Karl-Heinz Franke
"Verfahren zur Registrierung von mehrkanaligem Bildmaterial unterschiedlicher Modalitäten"

Proceedings of 17. Workshop Farbbildverarbeitung, ISBN: 978-3-00-035834-0, Konstanz, Deutschland, 29.-30.9.2011, pp. 73-84
September 2011 -
T. Koch,
R. Nestler,
T. Kubertschak
"The Advantage of Segment-Based Classification of Multi-Modal, Multi-Temporal and High-Resolution Satellite Images"

Crossing Borders within the ABC - Automation, Biomedical Engineering & Computer Science, 55. Internationales Wissenschaftliches Kolloquium 2010 der TU Ilmenau, TU Ilmenau (Hrsg.), ISBN: 978-3-938843-53-6
September 2010 -
C. Lucht
R. Nestler
K.-H. Franke
"Landnutzungsklassifikation auf multisensorischen und multispektralen Bilddaten - Anforderungen und Lösungsansätze"

Beitrag zum 15. Workshop Farbbildverarbeitung 2009, Berlin, 08.-09. Oktober 2009
Oktober 2009 pdf-Dokument
T. Koch
T. Kubertschak
K.-H. Franke
"Aspekte der Segmentierung von Bildmaterial aus multispektralen Merkmalsräumen am Beispiel von Satellitendaten"

Beitrag zum 15. Workshop Farbbildverarbeitung 2009, Berlin, 08.-09. Oktober 2009
Oktober 2009 pdf-Dokument
T. Koch
K.-H. Franke
"Aspekte der strukturbasierten Fusion multimodaler Satellitendaten und der Segmentierung fusionierter Bilder"

Beitrag im Rahmen des 52. Internationalen Wissen-
schaftlichen Kolloquiums 2007
der TU Ilmenau
September 2007 pdf-Dokument

  Flyer: Modules for Registration, Segmentation and Klassification
  of multisensoral Images

Your contact: Dr.-Ing. Rico Nestler
Seitenanfang © ZBS e.V. - Kompetenz in Signal- und Bildverarbeitung Datenschutzbeftr. / Webmaster
designed by