DocumentCode :
2371625
Title :
Impact of Wavelet based signal processing methods in radar classification systems using Hidden Markov Models
Author :
Kouemou, G. ; Opitz, F.
Author_Institution :
Defence Electron./Radar Syst. Design, EADS, Ulm
fYear :
2008
fDate :
21-23 May 2008
Firstpage :
1
Lastpage :
4
Abstract :
A classification technology is presented that uses a Wavelet based feature extractor and a Hidden Markov Model (HMM) to classify simulated and real radar signals from six classes of targets: person, tracked vehicles, wheeled vehicles, helicopters, propeller aircrafts and clutter (no match). Similar to techniques that have been well proven in speech and image recognition, the time-varying nature of radar Doppler data is exploited. The method classifies the targets by their different Doppler characteristics. The Wavelet technique has been tested on radar data where the classical signal processing methods failed. The purpose of this paper is to demonstrate the ability of Wavelet methods combined with a Discrete Hidden Markov Model (DHMM) in radar target recognition tasks.
Keywords :
feature extraction; hidden Markov models; radar signal processing; radar target recognition; wavelet transforms; discrete hidden Markov model; hidden Markov models; image recognition; radar Doppler data; radar classification systems; radar target recognition; speech recognition; wavelet based feature extractor; wavelet based signal processing methods; Airborne radar; Data mining; Doppler radar; Feature extraction; Hidden Markov models; Radar clutter; Radar imaging; Radar signal processing; Radar tracking; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Radar Symposium, 2008 International
Conference_Location :
Wroclaw
Print_ISBN :
978-83-7207-757-8
Type :
conf
DOI :
10.1109/IRS.2008.4585763
Filename :
4585763
Link To Document :
بازگشت