Summary
A connectionist scheme based on auto-adaptive topological feature maps is compared to conventional cluster analysis for (multi-spectral) scene identification in METEOSAT data. The identification of scenes in (multi-spectral) satellite data is equivalent to the assignment of meaningful labels to spatially coherent image regions. Automated scene detection in METEOSAT data is considered as a data reduction problem with the (optimal) preservation of the spatial coherence of scene region information. A self-organising one-dimensional feature map applied to the so-called segment space of the individual METEOSAT channels is shown to be an appropriate tool for mono-spectral scene identification. It is also shown that the presented connectionist approach for auto-adaptive mono-spectral scene identification has two important advantages compared to conventional cluster analysis, i.e. the number of detected regions is never lower than the number of nodes in the feature map and one obtains a contrast enhancement of the image regions. It is argued however that, despite these properties of feature maps, the use of conventional cluster analysis must be preferred for multi-spectral scene identification because multi-dimensional feature maps become far too slow for practical applications and require a detailed statistical analysis of the multi-spectral segment distribution in order to choose the topological dimension of the feature maps.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
METEOSAT Exploitation Project (MEP), MIEC Processing, ESA STR-224, 1987.
L. van de Berg, Segment Processing, Internal Report, ESOC/MEP, 1993.
P. Boekaerts, E. Steenput, M. Acheroy, P. Van ham and J. Cornelis, “Cloud detection in Multi-Spectral NOAA-AVHRR data using Multi-Layer Perceptrons: a pilot study”, Space Scientific Research in Belgium, Volume III, Earth Observation, Part 1, pp.173–179, Federal Office for Scientific, Technical and Cultural Affairs, Editor DWTC/SSTC, 1995.
EOS, “Neural Networks for METEOSAT Cloud Classification”, Final Report, EOS-92/078-RP-004, 1994.
P. Boekaerts, Autoadaptive cloud identification in METEOSAT images, ESA SP-1183, ISBN 92–9092–331–8, September 1995.
P. Boekaerts, E. Nyssen and J. Cornelis, “Autoadaptive mono-spectral cloud identification in METEOSAT satellite images”, EUROPTO, European Symposium on Satellite Remote Sensing, Conference on Image and Signal Processing for Remote Sensing II, EOS/SPIE vol. 2579, pp. 259–271, November 1995.
P. Boekaerts, E. Nyssen and J. Cornelis, “Autoadaptive Scene Identification in Multi-Spectral Satellite Data”, accepted for publication for the 5th Symposium on Remote Sensing: a Valuable Source of Information, NATO AGARD Sensor and Propagation Panel (SPP), 22–26 April 1996, ENSAE-CERT, Toulouse, France.
T. Kohonen, Self-organization and associative memory, Springer Verlag, Berlin, 1989.
H. Ritter and T. Kohonen, “Self-organizing semantic maps”, Biological Cybernetics, vol. 61, pp. 241–254, 1989.
H. Ritter and K. Schulten, “Convergency properties of Kohonen’s topology conserving maps: Fluctuations, stability and dimension selection”, Biological Cybernetics, vol. 60, pp. 59–71, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Boekaerts, P., Nyssen, E., Cornelis, J. (1997). A Comparative Study of Topological Feature Maps Versus Conventional Clustering for (Multi-Spectral) Scene Identification in METEOSAT Imagery. In: Kanellopoulos, I., Wilkinson, G.G., Roli, F., Austin, J. (eds) Neurocomputation in Remote Sensing Data Analysis. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59041-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-59041-2_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63828-2
Online ISBN: 978-3-642-59041-2
eBook Packages: Springer Book Archive