×

You are using an outdated browser that does not fully support the intranda viewer.
As a result, some pages may not be displayed correctly.

We recommend you use one of the following browsers:

Full text

Title
Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects
Author
Baltsavias, Emmanuel P.

International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999
155
Year
Acquisition date of remote sensing
imagery
Ground truth information
SPOT
Landsat 5-TM
(Scene 196-23)
Information from the Environmental Protection
Agency - district Diepholz
1984
25.04.1984
aerial photographs 1984
1986
17.05.1986
1987
07.07.1987
CIR- aerial photographs 26 May 1987
1988
biotope type mapping Diepholz 1988/89
1990
15.07.1990
1991
13.04.1991
biotope type mapping Bassum 1991
1992
biotope type mapping Bamstorf 1992
1994
18.02.1994
24.06.1994
biotope type mapping Bruchhausen-Vilsen 1994
26.07.1994
biotope type mapping Bruchhausen-Vilsen 1994
1995
24.04.1995
27.06.1995
Table 1. Overview of the current database. The light grey rows show the most relevant data.
3. GROUND TRUTH
To yield acceptable classification results, training data is
needed. Training statistics for all spectral classes constituting
each information class have to be computed. A supervised
classification requires a thorough knowledge of the geographic
area. Most importantly, the quality of the training process
determines the success of the classification stage and, therefore,
the value of the information generated from the entire
classification effort. The overall objective of the training
process is to assemble a set of statistics that describe the
spectral response pattern for each landcover type to be classified
in an image (Lillesand and Kiefer, 1987).
An objective mapping key for ground truth measurements was
generated. This mapping key is adapted to the special biotope
mapping key in Lower Saxony with respect to § 28a NNatG
(Lower Saxony's Environmental Protection Statutes)
(Drachenfels, 1994). Moreover, it was adjusted to the German
ATKIS object catalogue. For selected queries and overlay
analysis, these mapped test areas were transformed to separate
GIS layers in Arclnfo® format.
Figure 1 shows the total test area (which corresponds to the
district boundary of Diepholz) and the 4 ground truth locations.
The box demonstrates the exact dimension of the central
LandsatTM scene 196-23.
Fig. 1. Overview of the total test area and ground truth areas. The box shows the outline of Landsat TM scene 196-23.