Pakzad, Kian
6 CONCLUSIONS
The current results of the monotemporal interpretation using CIR aerial images led to correct results for the segments of
our test area. Applying the interpretation on grayscale images led for the most segments to the same results. This is
important because most existing aerial images of such areas are of grayscale type.
The extension to a multitemporal interpretation enables the distinction between more land use classes, which could not
be interpreted without the temporal knowledge. This applies e.g. to the distinction between the land use classes area of
regeneration and area of degeneration. The depiction of both classes in aerial images can be very similar. To
distinguish between these classes the temporal knowledge, whether peat extraction had been carried out or not, is
necessary. The exploitation of temporal knowledge leads to a more robust interpretation of land use classes, e.g. the
distinction between agriculturally used area and area of regeneration (section 5.4). The use of temporal knowledge can
therefore partly replace the need of color information.
The presented approach was successfully used for the multitemporal interpretation of moorland. The results show that
the exploitation of prior knowledge improves the interpretation compared to purely data driven methods. With the
presented approach we also show a suitable way to formulate and use the prior knowledge for image interpretation. The
explicit knowledge representation allows us to formulate prior knowledge easily in a standard language and also to
adapt it to similar problems in a simple way.
The research in this area will continue in different parts: The image processing operators have some parameters which
have to be adapted manually to the used images. The aim is to do this automatically. Other parts are the resegmentation
and the probabilities of the multitemporal interpretation. Furthermore the suitability of the used prior knowledge for
other moor areas has to be verified.
REFERNENCES
Abmayr, W., 1994, Einführung in die digitale Bildverarbeitung; Stuttgart
Bundesamt für Naturschutz, 1995, Systematik der Biotoptypenkartierung (Kartieranleitung), Schrifenreihe für
Landschaftspflege und Naturschutz, Heft 45, Bonn-Bad Godesberg
Eigner J., Schmatzler E., 1991, Handbuch des Hochmoorschutzes, Bedeutung, Pflege, Entwicklung, Kilda-Verlag,
Greven
Gôttlich, K., 1990, Moor- und Torfkunde; Schweizerbart; Stuttgart
Khoros Manual, 1997, Khoral Research Inc.
Liedtke, C.-E., Bückner, J., Grau, O., Growe, S., Tónjes, R., 1997, AIDA: A System for the Knowledge Based
Interpretation of Remote Sensing Data, 3rd. Int. Airborne Remote Sensing Conference and Exhibition, Copenhagen,
Denmark, July 1997.
Niemann, H., Sagerer, G., Schróder, S., Kummert, F., 1990, ERNEST: A Semantic Network System for Pattern
Understanding, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 12, No. 9, pp. 883-905, Sept. 1990.
NMU 1997, Niedersáchsisches Umweltministerium : Umweltmonitoring von Zustand und Nutzung der Hochmoore —
Auswertung der Satellitendaten für das Niedersáchsische Moorschutzprogramm, Hannover
Pakzad K., Bückner J., Growe S., 1999, Knowledge Based Moorland Interpretation using a Hybrid System for Image
Analysis, ISPRS Conference "Automatic Extraction of GIS Objects from Digital Imagery", 8.-10.9.1999, Munich,
Germany, pp.159-165.
Redslob, M., 1999, *Radarfernerkundung in niedersächsischen Hochmooren”, Dissertation, Universität Hannover
Rosenfeld, 1976, Digital Picture Processing, 1976
Schowengerdt, R. A., 1997, Remote Sensing, Models and Methods for Image Processing, 2.Ed., Academic Press
Suffrian, A., 1999, Untersuchung zur visuellen Erkennbarkeit und zeitlichen Abhängigkeit von Moorklassen,
Diplomarbeit, Universität Hannover
Toenjes, R., 1998, Wissensbasierte Interpretation und 3D-Rekonstruktion von Landschaftsszenen aus Luftbildern,
Dissertation, Universität Hannover
Von Drachenfels, O., 1994, Kartierschlüssel für Biotoptypen in Niedersachsen, Nieders. Landesamt für Ókologie
1110 International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B7. Amsterdam 2000.
i 9
eig y tp
russ
rsp rams
VEU
a ste
SESS
M RR VIDT SEES dt
CX
AM ER RE
RER
EEE n
pre pres
" haut A A anal Bum
a i a an a OF ui Si]