DocumentCode :
2990811
Title :
Learning structural descriptions of radar backscatter images
Author :
Kokar, M. ; Gopalraman, S. ; Shukla, A.
Author_Institution :
Dept. of Ind. Eng. & Inf. Syst., Northeastern Univ., Boston, MA, USA
fYear :
1988
fDate :
14-18 Mar 1988
Firstpage :
194
Lastpage :
199
Abstract :
The authors outline efforts to develop a software system which can learn to identify objects given their radar backscatter. Variation of the intensity of the radar backscatter with respect to frequency can be plotted as a curve. The system is given a number of examples of backscatter emitted by a single object, each corresponding to one aspect angle. The system derives the maximally specific conjunctive generalization (MSC generalization) of the structural descriptions of the various backscatter. The structural descriptions are derived in the language developed for this purpose. Having learned these descriptions, the system can use this knowledge to identify backscatter not presented to it earlier
Keywords :
backscatter; computerised pattern recognition; knowledge engineering; learning systems; aspect angle; conjunctive generalization; knowledge; radar backscatter images; software system; structural descriptions; Backscatter; Calculus; Frequency; Industrial engineering; Information systems; Radar antennas; Radar imaging; Receiving antennas; Reflector antennas; Software systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Intelligence Applications, 1988., Proceedings of the Fourth Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-8186-0837-4
Type :
conf
DOI :
10.1109/CAIA.1988.196103
Filename :
196103
Link To Document :
بازگشت