Expected-likelihood covariance matrix estimation for adaptive detection

We demonstrate that by adopting the new class of "expected-likelihood" (EL) covariance matrix estimates, instead of the traditional maximum-likelihood (ML) estimates, we can significantly enhance adaptive detection performance. These new estimates are found by searching within the properly parameterized class of admissible covariance matrices for the one that produces the likelihood ratio (LR) that is "closest possible" to the LR generated by the true (exact) covariance matrix.

[1]  E. J. Kelly.  An Adaptive Detection Algorithm , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Richard Klemm,et al.  Space-time adaptive processing : principles and applications , 1998 .

[3]  L. Scharf,et al.  The CFAR adaptive subspace detector is a scale-invariant GLRT , 1998, Ninth IEEE Signal Processing Workshop on Statistical Signal and Array Processing (Cat. No.98TH8381).

[4]  Daniel R. Fuhrmann,et al.  A CFAR adaptive matched filter detector , 1992 .

[5]  Alexei Gorokhov,et al.  Bounds on maximum likelihood ratio-part I: application to antenna array detection-estimation with perfect wavefront coherence , 2004, IEEE Transactions on Signal Processing.

[6]  Karl Gerlach,et al.  Outlier resistant adaptive matched filtering , 2002 .

[7]  L.L. Scharf,et al.  Adaptive coherence estimation for radar signal processing , 1996, Conference Record of The Thirtieth Asilomar Conference on Signals, Systems and Computers.