USM LINKS
Computer Science
WEB PAGES
CMInfo
RESOURCES
Math Resources
SYMPOSIUM
MINISYMPOSIA
December 4-5, 1998
University of Southern Mississippi
Hattiesburg, Mississippi
Processing of Satellite Imagery by Neural Networks
Barsi Arpad
The researchers have used numerous well-proved and new methods for processing the imagery of satellites sent to the Earth's surface. The mostly applied imaging satellite would be Landsat TM. The relatively high geometric resolution is coupled with adequate spectral one - 30 m with 7 bands. These features have made possible to elaborate classification methods to map the surface. The discovery of artificial neural networks in 1958 counts as a milestone of new computational research. The tool belonging to the artificial intelligence can be used for problems which were till nowadays not or just partly solvable. In the presenteation I'll give an overview of the land cover mapping, the mathematical base of this thematic processing, both by traditional and neural way. Connecting to the theory I'll present some practical examples how it does work. At the end of the presentation some application fields are mentioned.
To obtain more information about the meeting send e-mail to: fscc98@pax.st.usm.edu.
Return to Minisymposia 
Return to PAX
Return to USM
USM
inquire@delphi.st.usm.edu
Updated
http://pax.st.usm.edu