Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
948 IEEE JOURNAL OF OCEANIC ENGINEERING, VOL. 32, NO. 4, OCTOBER 2007 Undersea Target Classification Using Canonical
 

Summary: 948 IEEE JOURNAL OF OCEANIC ENGINEERING, VOL. 32, NO. 4, OCTOBER 2007
Undersea Target Classification Using Canonical
Correlation Analysis
Ali Pezeshki, Member, IEEE, Mahmood R. Azimi-Sadjadi, Senior Member, IEEE, and
Louis L. Scharf, Life Fellow, IEEE
Abstract--Canonical correlation analysis is employed as a mul-
tiaspect feature extraction method for underwater target classifi-
cation. The method exploits linear dependence or coherence be-
tween two consecutive sonar returns, at different aspect angles.
This is accomplished by extracting the dominant canonical corre-
lations between the two sonar returns and using them as features
for classifying mine-like objects from nonmine-like objects. The
experimental results on a wideband acoustic backscattered data
set, which contains sonar returns from several mine-like and non-
mine-like objects in two different environmental conditions, show
the promise of canonical correlation features for mine-like versus
nonmine-like discrimination. The results also reveal that in a fixed
bottom condition, canonical correlation features are relatively in-
variant to changes in aspect angle.
Index Terms--Canonical correlations, linear dependence and co-

  

Source: Azimi-Sadjadi, Mahmood R. - Department of Electrical and Computer Engineering, Colorado State University

 

Collections: Computer Technologies and Information Sciences