Abstract
In this paper we describe an application of the Wigner-Ville distribution (WVD) for the detection of a radar target signal buried in a strong clutter background. The WVD transforms the received radar signal into a time-frequency image that accounts for the nonstationary nature of the radar signal. The cross-terms, an inherent feature of the WVD, play a constructive role in this application. In particular, their presence enhances the visibility of a target in the WVD image in a unique and significant way. The WVD image provides a common input to a pair of channels, with one channel matched to clutter and the other channel matched to target plus clutter. Each channel consists of a principal components analyzer (for feature extraction) followed by a multilayer perceptron classifier. Experimental results, based on real-life, radar data, are presented to demonstrate the superior performance of the new detection strategy compared to a conventional constant false-alarm rate (CFAR) processor. >
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
