Title :
Moving target classification in ground surveillance radar ATR system by using novel bicepstral-based information features
Author :
Molchanov, Pavlo O. ; Astola, Jaakko T. ; Egiazarian, Karen O. ; Totsky, Alexander V.
Author_Institution :
Dept. of Signal Process., Tampere Univ. of Technol., Tampere, Finland
Abstract :
A novel bicepstrum-based strategy is suggested for moving target recognition and classification by ground surveillance Doppler radars. Bicepstral coefficients extracted from non stationary backscattered radar signals are used as the information features in automatic target recognition (ATR) system for solving a problem of moving human recognition and classification. ATR performance is studied by using Gaussian mixture model (GMM) and maximum likelihood (ML) rule. Experimental results obtained by ground surveillance homodyne radar operating in millimeter range wavelengths and continuous mode are represented and discussed. Classifier performance is examined in real-life conditions for walking human and group of walking humans in vegetation clutter environment.
Keywords :
Doppler radar; Gaussian processes; image classification; image recognition; maximum likelihood estimation; millimetre wave radar; radar imaging; radar target recognition; Doppler radars; GMM; Gaussian mixture model; ML rule; automatic target recognition; bicepstral-based information features; bicepstrum-based strategy; continuous mode radar; ground surveillance homodyne radar; ground surveillance radar ATR system; maximum likelihood rule; millimeter range wavelengths; moving human classification; moving human recognition; moving target classification; moving target recognition; nonstationary backscattered radar signals; vegetation clutter; Doppler radar; Feature extraction; Humans; Legged locomotion; Surveillance; Time frequency analysis;
Conference_Titel :
Radar Conference (EuRAD), 2011 European
Conference_Location :
Manchester
Print_ISBN :
978-1-4577-1156-5
