Impact of Wavelet based signal processing methods in radar classification systems using Hidden Markov Models

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.